SlideShare a Scribd company logo
1 of 24
Download to read offline
Optimized Image Processing
for Automotive Image Sensors
with Novel Color Filter Arrays
Young-Jun Yoo
VP
Nextchip Co., Ltd.
Today’s contents
2
© 2023 Nextchip Co.,Ltd.
• Nextchip: Vision Professional
• Challenge for Both Human & Machine Vision
• Nextchip’s ISP Topology
• Test Results of Nextchip’s Image Processing for Each CFA
• Sophisticated methodology for design and tuning
3
© 2023 Nextchip Co.,Ltd.
Nextchip: Vision Professional
Nextchip overview
World-class ISP (ASIC/IP/Tuning)
Automotive reliability
• 420million shipping units
• 51+ MP car models
Listed on the KOSDAQ
Market Proven Technology
• Went public in July 2022
Advanced ADAS technology
Customer support
• Know-how in tuning against various customers’ criteria
• AEC-Q100 Gr.2/CMMI Lv.-3/ISO26262/A-Spice process
• Developing image signal processing tech. for 26 years
• Open architecture with various imagers
• Edge processor /w hard-wired ML algorithms
• ADAS SoCs with CNN capability
• Tuning capability human & machine vision
© 2023 Nextchip Co.,Ltd. 4
5
Challenge for both
Human & Machine Vision
© 2023 Nextchip Co.,Ltd.
6
Key factor of machine vision
<Ref. Basler “High-Sensitivity Image Processing Cameras”>
• High sensitivity is the key factor of machine vision for achieving a quality video image with low image noise even
in poor lighting conditions.
• The higher the signal-to-noise ratio, the better the object can be detected.
• Sensitivitiy is more important than color in machine vision.
<Ref. gla.ac.uk “Sensitivity and noise”>
How to get higher sensitivity
7
Diverse bayer pattern with pixels
Rear Blind Spot
Guidance
Rear Camera
Fully Automatic Parking
Function
MOD Camera Motion
Object Detection
LDWS(Lane Departure
Warning System)
Night Vision Function
Stereo/Lidar Camera
System
Front Camera
Adaptive Camera
Drowsy Driving
Monitoring
R G B
G
R G B
I
R
High
sensitivity;
Moderate
color
Good
sensitivity;
Moderate
color
R Y C
y
Y
R C C B
High
sensitivity;
Less color
default
• Special CFAs have popped in a variety of
scenarios depending on how the camera
is used.
• All about the color & sensitivity for
human & machine vision.
• HOWEVER, newly proposed CFAs have
an issue in color reproduction.
© 2023 Nextchip Co.,Ltd.
< Ref1. MCNEX official website>
Moderate
sensitivity;
Strong
color
This is Machine’s view, but are you (human) ok with that?
© 2023 Nextchip Co.,Ltd.
What is the difference between
human vision & machine vision?
Issues when color reproduction fails
9
• Hard to distinguish red light. And, it is directly linked to malfunction in autonomous driving.
• Even for sensing application, color reproduction is required at the very least.
© 2023 Nextchip Co.,Ltd.
< Ref3. Non-RGB color filter options and traffic signal detection capabilities>
10
Nextchip’s ISP Topology
Attempts to get sensitivity and color at the same time
© 2023 Nextchip Co.,Ltd.
What is special?
11
R G
G B
R C
C G
R Y
Y Cy
Front Sensing
With Higher Resolution
General Purpose
R G
B IR
In-cabin sensing
for Occupant Monitoring
• While maintaining Red,
R G gets more color than RGGB.
R Cy subtracts varying degrees of red, green, and blue from white light to produce a full spectrum of colors.
RGBIR uses IR to get higher sensitivity under the dark cabin environment.
• There is a trend to change color filter array from RGB to others.
It is based on applications like RGB-IR for in-cabin camera system, RCCG and RYYCy for exterior cameras in
automotive market.
© 2023 Nextchip Co.,Ltd.
<Ref4. Image Sensor World>
The key is
how to fill the lack of pixel information
12
IR
G
IR
G
G
B
G
R
IR
G
G
R
IR
G
G
B
Color Reproduction Edge Enhancer Noise Reduction
G:8 B:2 R:2 IR:4
• Since several pixels had been converted to
another pixels compared to RGGB, the key is
how to handle and improve the color and edge
characteristics given the lack of pixel
information.
• With specialty in image signal processing
technology as the fundamental vision
technology of Nextchip, it provides the
differentiated image quality for embedded
systems.v
© 2023 Nextchip Co.,Ltd.
G
C
G
C
C
R
C
R
G
C
C
R
G
C
C
R
G:4 B:0 R:4 C:4
Cy
Y
Cy
Y
Y
R
Y
R
Cy
Y
Y
R
Cy
Y
Y
R
G:0 Y:8 B:0 R:4 Cy:4
In RGB-IR case
13
R G
B IR
In-cabin sensing
for Occupant Monitoring
OMS
Application
Dual Band
Pass Filter
Interpolation & RGB IR
separation
R = (R + IR) – IR = R
G = (G + IR) – IR = G
B = (B + IR) – IR = B
IR = IR
Day
Vision
Night
Vision
G B
R
I
R
© 2023 Nextchip Co.,Ltd.
• RGB-IR is the most complicated case because it needs to extract IR from each pixels.
• Dedicated processing block for extracting IR is required.
14
Test Results of Nextchip’s
Image Processing for Each CFA
© 2023 Nextchip Co.,Ltd.
RGBIR image
15
RAW RGB
© 2023 Nextchip Co.,Ltd.
• Despite the lack of pixel information, the Nextchip ISP is able to reproduce color at the same level as RGGB.
• If you want both RAW and YUV, you can get 2 separate image streams.
• They can be used for both human vision and machine vision.
RCCG image
16
RAW RCCG
• Despite the lack of pixel information, the Nextchip ISP is able to reproduce color at the same level as RGGB.
• If you want both RAW and YUV, you can get 2 separate image streams.
• They can be used for both human vision and machine vision.
© 2023 Nextchip Co.,Ltd.
RCCG image
17
RAW RCCG
© 2023 Nextchip Co.,Ltd.
• Despite the lack of pixel information, the Nextchip ISP is able to reproduce color at the same level as RGGB.
• If you want both RAW and YUV, you can get 2 separate image streams.
• They can be used for both human vision and machine vision.
RYYCy image
18
RAW RYYCy
© 2023 Nextchip Co.,Ltd.
• Despite the lack of pixel information, the Nextchip ISP is able to reproduce color at the same level as RGGB.
• If you want both RAW and YUV, you can get 2 separate image streams.
• They can be used for both human vision and machine vision.
Sophisticated methodology
for design and tuning
19
Realtime processing through well partitioning
20
© 2023 Nextchip Co.,Ltd.
• Real-time constraint is one of the most common challenge found in many critical embedded applications,
namely image and video processing. However, software tools and general purpose microprocessor are not
suitable for deals with such as problems. The implementation method is based on Hardware/Software (HW/SW)
codesign approach.
• To achieve a partition that will give us the required performance within the overall system requirements (in
size, weight, power, cost, etc.)
• In addition to the advantage of easily modifying parameters to suit various environments, blocks that require
fast image processing speed are designed with hardware that uses as little calculation line memory as possible,
so they have the advantage of being processed in real time and displayed on the screen without delay.
Image analysis for machine vision
21
© 2023 Nextchip Co.,Ltd.
• Key ISP modules which impact CV performance are MTF and Low light sensibility by sensor side,
and Sharpening, HDR, Tone mapping and Color contrast by ISP side.
• ISP vendor should understand each algorithms and trys to find out ultimate setting values for better detection.
<Ref. “Overview and Empirical Analysis of ISP Parameter Tuning for Visual Perception in Autonomous Driving”>
Best for MV
Best for HV
22
Takeaways
© 2023 Nextchip Co.,Ltd.
Market proven ISP technology
23
Well-partitioned flexible ISP core technology
2 dedicated processing topologies for human vision and machine vision
Capable of analyzing the image based on understanding of HV and MV
© 2023 Nextchip Co.,Ltd.
ISP is not a one function. It is a bunch of functions.
Resources
24
High-Sensitivity Image Processing Cameras
https://www.baslerweb.com/en/vision-campus/camera-technology/high-sensitivity-industrial-cameras/
Sensitivity and noise
https://radio.astro.gla.ac.uk/a2_oa/a2oa_sec4.pdf
MCNEX AUTOMOTIVE DRIVING- RELATED TECHNOLOGY
https://www.mcnex.com/en/business/020201.automotive-camera
Robot Bionic Vision Technologies: A Review
https://www.mdpi.com/2076-3417/12/16/7970
Non-RGB color filter options and traffic signal detection capabilities
https://library.imaging.org/ei/articles/34/16/AVM-215
Aptina Explains Clarity+ Technology, Reveals 1.1um Pixel Product
http://image-sensors-world.blogspot.com/2013/07/aptina-explains-clarity-technology.html
Design of Image Signal Processor greatly reduced chip area
by role sharing of hardware and software
https://koreascience.kr/article/JAKO201031559288071.pdf
Other images
www.nextchip.com/en/ & Nextchip’s internal reports
Please visit booth #109 and enjoy the latest image processing technologies.
© 2023 Nextchip Co.,Ltd.

More Related Content

Similar to “Optimized Image Processing for Automotive Image Sensors with Novel Color Filter Arrays,” a Presentation from Nextchip

"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...
"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio..."Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...
"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...Edge AI and Vision Alliance
 
Different Methodologies for Indian License Plate Detection
Different Methodologies for Indian License Plate DetectionDifferent Methodologies for Indian License Plate Detection
Different Methodologies for Indian License Plate DetectionIRJET Journal
 
“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...
“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...
“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...Edge AI and Vision Alliance
 
MIPI DevCon 2016: Image Sensor and Display Connectivity Disruption
MIPI DevCon 2016: Image Sensor and Display Connectivity DisruptionMIPI DevCon 2016: Image Sensor and Display Connectivity Disruption
MIPI DevCon 2016: Image Sensor and Display Connectivity DisruptionMIPI Alliance
 
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion Systems
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion SystemsMIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion Systems
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion SystemsMIPI Alliance
 
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...IRJET Journal
 
"Selecting the Right Imager for Your Embedded Vision Application," a Presenta...
"Selecting the Right Imager for Your Embedded Vision Application," a Presenta..."Selecting the Right Imager for Your Embedded Vision Application," a Presenta...
"Selecting the Right Imager for Your Embedded Vision Application," a Presenta...Edge AI and Vision Alliance
 
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLAB
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLABCOMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLAB
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLABIRJET Journal
 
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro..."High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...Edge AI and Vision Alliance
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002Enrico Busto
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002Enrico Busto
 
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...Lori Moore
 
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...Edge AI and Vision Alliance
 
Automatic Fetching of Vehicle details using ANPR Camera
Automatic Fetching of Vehicle details using ANPR CameraAutomatic Fetching of Vehicle details using ANPR Camera
Automatic Fetching of Vehicle details using ANPR CameraIRJET Journal
 
UHK-430 White paper
UHK-430 White paperUHK-430 White paper
UHK-430 White paperKris Hill
 
Realtimeimageprocessing
RealtimeimageprocessingRealtimeimageprocessing
RealtimeimageprocessingGopi Nath
 
AUTOMATIC DETECTION OF OVERSPEED VEHICLE
AUTOMATIC DETECTION OF OVERSPEED VEHICLEAUTOMATIC DETECTION OF OVERSPEED VEHICLE
AUTOMATIC DETECTION OF OVERSPEED VEHICLEIRJET Journal
 
“Selecting Image Sensors for Embedded Vision Applications: Three Case Studies...
“Selecting Image Sensors for Embedded Vision Applications: Three Case Studies...“Selecting Image Sensors for Embedded Vision Applications: Three Case Studies...
“Selecting Image Sensors for Embedded Vision Applications: Three Case Studies...Edge AI and Vision Alliance
 
Vlsi matlab -titles-2014-15
Vlsi matlab -titles-2014-15Vlsi matlab -titles-2014-15
Vlsi matlab -titles-2014-15Raja Ram
 

Similar to “Optimized Image Processing for Automotive Image Sensors with Novel Color Filter Arrays,” a Presentation from Nextchip (20)

"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...
"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio..."Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...
"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...
 
Real Time Image Processing
Real Time Image ProcessingReal Time Image Processing
Real Time Image Processing
 
Different Methodologies for Indian License Plate Detection
Different Methodologies for Indian License Plate DetectionDifferent Methodologies for Indian License Plate Detection
Different Methodologies for Indian License Plate Detection
 
“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...
“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...
“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...
 
MIPI DevCon 2016: Image Sensor and Display Connectivity Disruption
MIPI DevCon 2016: Image Sensor and Display Connectivity DisruptionMIPI DevCon 2016: Image Sensor and Display Connectivity Disruption
MIPI DevCon 2016: Image Sensor and Display Connectivity Disruption
 
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion Systems
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion SystemsMIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion Systems
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion Systems
 
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
 
"Selecting the Right Imager for Your Embedded Vision Application," a Presenta...
"Selecting the Right Imager for Your Embedded Vision Application," a Presenta..."Selecting the Right Imager for Your Embedded Vision Application," a Presenta...
"Selecting the Right Imager for Your Embedded Vision Application," a Presenta...
 
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLAB
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLABCOMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLAB
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLAB
 
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro..."High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002
 
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
 
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...
 
Automatic Fetching of Vehicle details using ANPR Camera
Automatic Fetching of Vehicle details using ANPR CameraAutomatic Fetching of Vehicle details using ANPR Camera
Automatic Fetching of Vehicle details using ANPR Camera
 
UHK-430 White paper
UHK-430 White paperUHK-430 White paper
UHK-430 White paper
 
Realtimeimageprocessing
RealtimeimageprocessingRealtimeimageprocessing
Realtimeimageprocessing
 
AUTOMATIC DETECTION OF OVERSPEED VEHICLE
AUTOMATIC DETECTION OF OVERSPEED VEHICLEAUTOMATIC DETECTION OF OVERSPEED VEHICLE
AUTOMATIC DETECTION OF OVERSPEED VEHICLE
 
“Selecting Image Sensors for Embedded Vision Applications: Three Case Studies...
“Selecting Image Sensors for Embedded Vision Applications: Three Case Studies...“Selecting Image Sensors for Embedded Vision Applications: Three Case Studies...
“Selecting Image Sensors for Embedded Vision Applications: Three Case Studies...
 
Vlsi matlab -titles-2014-15
Vlsi matlab -titles-2014-15Vlsi matlab -titles-2014-15
Vlsi matlab -titles-2014-15
 

More from Edge AI and Vision Alliance

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...Edge AI and Vision Alliance
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...Edge AI and Vision Alliance
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...Edge AI and Vision Alliance
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...Edge AI and Vision Alliance
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...Edge AI and Vision Alliance
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...Edge AI and Vision Alliance
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...Edge AI and Vision Alliance
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsightsEdge AI and Vision Alliance
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...Edge AI and Vision Alliance
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...Edge AI and Vision Alliance
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...Edge AI and Vision Alliance
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...Edge AI and Vision Alliance
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...Edge AI and Vision Alliance
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...Edge AI and Vision Alliance
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...Edge AI and Vision Alliance
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from SamsaraEdge AI and Vision Alliance
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...Edge AI and Vision Alliance
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...Edge AI and Vision Alliance
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...Edge AI and Vision Alliance
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...Edge AI and Vision Alliance
 

More from Edge AI and Vision Alliance (20)

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
 

Recently uploaded

Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 

Recently uploaded (20)

Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 

“Optimized Image Processing for Automotive Image Sensors with Novel Color Filter Arrays,” a Presentation from Nextchip

  • 1. Optimized Image Processing for Automotive Image Sensors with Novel Color Filter Arrays Young-Jun Yoo VP Nextchip Co., Ltd.
  • 2. Today’s contents 2 © 2023 Nextchip Co.,Ltd. • Nextchip: Vision Professional • Challenge for Both Human & Machine Vision • Nextchip’s ISP Topology • Test Results of Nextchip’s Image Processing for Each CFA • Sophisticated methodology for design and tuning
  • 3. 3 © 2023 Nextchip Co.,Ltd. Nextchip: Vision Professional
  • 4. Nextchip overview World-class ISP (ASIC/IP/Tuning) Automotive reliability • 420million shipping units • 51+ MP car models Listed on the KOSDAQ Market Proven Technology • Went public in July 2022 Advanced ADAS technology Customer support • Know-how in tuning against various customers’ criteria • AEC-Q100 Gr.2/CMMI Lv.-3/ISO26262/A-Spice process • Developing image signal processing tech. for 26 years • Open architecture with various imagers • Edge processor /w hard-wired ML algorithms • ADAS SoCs with CNN capability • Tuning capability human & machine vision © 2023 Nextchip Co.,Ltd. 4
  • 5. 5 Challenge for both Human & Machine Vision © 2023 Nextchip Co.,Ltd.
  • 6. 6 Key factor of machine vision <Ref. Basler “High-Sensitivity Image Processing Cameras”> • High sensitivity is the key factor of machine vision for achieving a quality video image with low image noise even in poor lighting conditions. • The higher the signal-to-noise ratio, the better the object can be detected. • Sensitivitiy is more important than color in machine vision. <Ref. gla.ac.uk “Sensitivity and noise”>
  • 7. How to get higher sensitivity 7 Diverse bayer pattern with pixels Rear Blind Spot Guidance Rear Camera Fully Automatic Parking Function MOD Camera Motion Object Detection LDWS(Lane Departure Warning System) Night Vision Function Stereo/Lidar Camera System Front Camera Adaptive Camera Drowsy Driving Monitoring R G B G R G B I R High sensitivity; Moderate color Good sensitivity; Moderate color R Y C y Y R C C B High sensitivity; Less color default • Special CFAs have popped in a variety of scenarios depending on how the camera is used. • All about the color & sensitivity for human & machine vision. • HOWEVER, newly proposed CFAs have an issue in color reproduction. © 2023 Nextchip Co.,Ltd. < Ref1. MCNEX official website> Moderate sensitivity; Strong color
  • 8. This is Machine’s view, but are you (human) ok with that? © 2023 Nextchip Co.,Ltd. What is the difference between human vision & machine vision?
  • 9. Issues when color reproduction fails 9 • Hard to distinguish red light. And, it is directly linked to malfunction in autonomous driving. • Even for sensing application, color reproduction is required at the very least. © 2023 Nextchip Co.,Ltd. < Ref3. Non-RGB color filter options and traffic signal detection capabilities>
  • 10. 10 Nextchip’s ISP Topology Attempts to get sensitivity and color at the same time © 2023 Nextchip Co.,Ltd.
  • 11. What is special? 11 R G G B R C C G R Y Y Cy Front Sensing With Higher Resolution General Purpose R G B IR In-cabin sensing for Occupant Monitoring • While maintaining Red, R G gets more color than RGGB. R Cy subtracts varying degrees of red, green, and blue from white light to produce a full spectrum of colors. RGBIR uses IR to get higher sensitivity under the dark cabin environment. • There is a trend to change color filter array from RGB to others. It is based on applications like RGB-IR for in-cabin camera system, RCCG and RYYCy for exterior cameras in automotive market. © 2023 Nextchip Co.,Ltd. <Ref4. Image Sensor World>
  • 12. The key is how to fill the lack of pixel information 12 IR G IR G G B G R IR G G R IR G G B Color Reproduction Edge Enhancer Noise Reduction G:8 B:2 R:2 IR:4 • Since several pixels had been converted to another pixels compared to RGGB, the key is how to handle and improve the color and edge characteristics given the lack of pixel information. • With specialty in image signal processing technology as the fundamental vision technology of Nextchip, it provides the differentiated image quality for embedded systems.v © 2023 Nextchip Co.,Ltd. G C G C C R C R G C C R G C C R G:4 B:0 R:4 C:4 Cy Y Cy Y Y R Y R Cy Y Y R Cy Y Y R G:0 Y:8 B:0 R:4 Cy:4
  • 13. In RGB-IR case 13 R G B IR In-cabin sensing for Occupant Monitoring OMS Application Dual Band Pass Filter Interpolation & RGB IR separation R = (R + IR) – IR = R G = (G + IR) – IR = G B = (B + IR) – IR = B IR = IR Day Vision Night Vision G B R I R © 2023 Nextchip Co.,Ltd. • RGB-IR is the most complicated case because it needs to extract IR from each pixels. • Dedicated processing block for extracting IR is required.
  • 14. 14 Test Results of Nextchip’s Image Processing for Each CFA © 2023 Nextchip Co.,Ltd.
  • 15. RGBIR image 15 RAW RGB © 2023 Nextchip Co.,Ltd. • Despite the lack of pixel information, the Nextchip ISP is able to reproduce color at the same level as RGGB. • If you want both RAW and YUV, you can get 2 separate image streams. • They can be used for both human vision and machine vision.
  • 16. RCCG image 16 RAW RCCG • Despite the lack of pixel information, the Nextchip ISP is able to reproduce color at the same level as RGGB. • If you want both RAW and YUV, you can get 2 separate image streams. • They can be used for both human vision and machine vision. © 2023 Nextchip Co.,Ltd.
  • 17. RCCG image 17 RAW RCCG © 2023 Nextchip Co.,Ltd. • Despite the lack of pixel information, the Nextchip ISP is able to reproduce color at the same level as RGGB. • If you want both RAW and YUV, you can get 2 separate image streams. • They can be used for both human vision and machine vision.
  • 18. RYYCy image 18 RAW RYYCy © 2023 Nextchip Co.,Ltd. • Despite the lack of pixel information, the Nextchip ISP is able to reproduce color at the same level as RGGB. • If you want both RAW and YUV, you can get 2 separate image streams. • They can be used for both human vision and machine vision.
  • 20. Realtime processing through well partitioning 20 © 2023 Nextchip Co.,Ltd. • Real-time constraint is one of the most common challenge found in many critical embedded applications, namely image and video processing. However, software tools and general purpose microprocessor are not suitable for deals with such as problems. The implementation method is based on Hardware/Software (HW/SW) codesign approach. • To achieve a partition that will give us the required performance within the overall system requirements (in size, weight, power, cost, etc.) • In addition to the advantage of easily modifying parameters to suit various environments, blocks that require fast image processing speed are designed with hardware that uses as little calculation line memory as possible, so they have the advantage of being processed in real time and displayed on the screen without delay.
  • 21. Image analysis for machine vision 21 © 2023 Nextchip Co.,Ltd. • Key ISP modules which impact CV performance are MTF and Low light sensibility by sensor side, and Sharpening, HDR, Tone mapping and Color contrast by ISP side. • ISP vendor should understand each algorithms and trys to find out ultimate setting values for better detection. <Ref. “Overview and Empirical Analysis of ISP Parameter Tuning for Visual Perception in Autonomous Driving”> Best for MV Best for HV
  • 23. Market proven ISP technology 23 Well-partitioned flexible ISP core technology 2 dedicated processing topologies for human vision and machine vision Capable of analyzing the image based on understanding of HV and MV © 2023 Nextchip Co.,Ltd. ISP is not a one function. It is a bunch of functions.
  • 24. Resources 24 High-Sensitivity Image Processing Cameras https://www.baslerweb.com/en/vision-campus/camera-technology/high-sensitivity-industrial-cameras/ Sensitivity and noise https://radio.astro.gla.ac.uk/a2_oa/a2oa_sec4.pdf MCNEX AUTOMOTIVE DRIVING- RELATED TECHNOLOGY https://www.mcnex.com/en/business/020201.automotive-camera Robot Bionic Vision Technologies: A Review https://www.mdpi.com/2076-3417/12/16/7970 Non-RGB color filter options and traffic signal detection capabilities https://library.imaging.org/ei/articles/34/16/AVM-215 Aptina Explains Clarity+ Technology, Reveals 1.1um Pixel Product http://image-sensors-world.blogspot.com/2013/07/aptina-explains-clarity-technology.html Design of Image Signal Processor greatly reduced chip area by role sharing of hardware and software https://koreascience.kr/article/JAKO201031559288071.pdf Other images www.nextchip.com/en/ & Nextchip’s internal reports Please visit booth #109 and enjoy the latest image processing technologies. © 2023 Nextchip Co.,Ltd.