2. INTRODUCTION
What is ComputerVision?
• Computer Vision is a field that includes methods for acquiring, processing,
analyzing, and understanding images known as Image analysis, Scene
Analysis and Image Understanding.
• It is concerned with the theory and technology for building artificial systems
that obtain information from images. The image data can take many forms,
such as a video sequence, views from multiple cameras, or multi-
dimensional data from a medical scanner.
Does ComputerVision really matter?
3. THE EVOLUTION OF VISION TECHNOLOGY
Computer vision: research and fundamental technology for extracting
meaning from images
Machine vision: factory applications
Embedded vision: thousands of applications
1)Consumer, automotive, medical, defense, retail, gaming, security,
education, transportation, …
2)Embedded systems, mobile devices, PCs and the cloud
4. ARCHITECTURE
• Analyzing the process of a computer vision application, one can perceive that the
different tasks demand different efforts from the various computational resources.
• One can conclude that a single processor architecture may not be able to carry all
these operations efficiently; there is a need for a hybrid processing configuration,
with specific architectures for each level.
• Architectures for low-level operations are heavily explored, due to their specific
characteristics and the large amount of data involved.
5. TYPES OF CAMERA SENSORS:
CCD
(Charged Coupled Device)
● Passive-pixel device
● Less noise in pixel data
● Used in high quality video cameras and satellites
● No electronics at pixel level
● All electric signals need to be transferred to external
electronics for conversion into voltage
● Provides better quantum efficiency
● Ideal for poor lighting conditions
CMOS
(Complementary Metal Oxide
Semiconductor)
● Active-pixel device
● More noise
● Used in smartphones and DSLR
● Each pixel contains separate electronics e.g. amplifier
● The signal from each pixel can be read directly
without any changes
● Provides higher frame rate
● Image is scanned row-wise causing rolling shutter
effect
6. SYSTEM OF COMPUTER VISION
• Image acquisition
• Pre-processing
• Feature extraction
• Detection/Segmentation
• High Level Processing
7. OPERATIONS
• A computer vision system consists basically of four elements: capture,
pre-processing, processing and output.
• The complete processing in a computer vision application involves 4
main steps-
• In the first step, a digital image is produced.
• In the 2nd step low-level operations are applied to the captured image,
with the aim to get clearer image.
• The 3rd step consists of extraction of information relevant to the
application.
• The 4th and last step makes decisions dictated by the application, using
high-level operations.
Low level
operations
Extraction of
information
Decision
Making
8. REQUIREMENTS
• There is a need for tools (hardware and software) to help the
developer of computer vision systems. Hardware platforms must
achieve all the application requirements, and software tools should
ease the programming task.
• It is desirable that a computer vision system include other benefits like
modularity, portability, extensibility, and configuration and operation
facilities.
• Hardware elements: A power source , camera, processor, and
communication cables and connectors or some kind of wireless
interconnection mechanism.
• Software elements : Open CV, CUDA, MATLAB, Open CL and other
research libraries.
9. PROCESSORS
In addition, a processor can be accelerated by dedicated hardware that
improves performance on computer vision algorithms.
• General-purpose CPUs
• Graphics Processing Units
• Digital Signal Processors
• Field Programmable Gate Arrays (FPGAs)
• Vision-Specific Processors and Cores.
The videantis processor is the most power-efficient and highest-performing
visual processing architecture that you can license on the market. Whether
you need to run deep learning algorithms, video compression or
decompression, image manipulation or computer vision, the v-MP6000UDX
architecture provides a very efficient implementation. The multicore v-
MP6000UDX architecture scales from ultra-low-cost single-core applications to
ultra-high-performance many-core applications. The architecture is optimized
for efficient deep learning, computer vision, image and video processing.
10. SOFTWARE REQUIREMENTS
OpenCV: The videantis OpenCV library is an adaption of the publicly available open
source computer vision library OpenCV, with additions to speed up processing of the
OpenCV API functions on systems that have a videantis processor IP integrated.
OpenVX: The videantis v-MP6000UDX processor architecture supports acceleration of
the OpenVX primitives, resulting in a low-power, high-performance embedded vision
system.
MATLAB: MATLAB is a numerical computing environment that was developed by
MathWorks in 1984. It contains the Computer Vision Toolbox which provides various
algorithms and functions for computer vision. These include object detection, object
tracking, feature detection, feature matching, camera calibration in 3-D, 3D
reconstruction, etc
CUDA: CUDA or the Compute Unified Device Architecture)is a parallel computing platform
that was created by Nvidia and released in 2007. It is used by software engineers for
general purpose processing using the CUDA-enabled graphics processing unit or GPU.
11. APPLICATIONS
The computer vision and machine vision fields have significant overlap. Computer vision covers
the core technology of automated image analysis which is used in many fields:
2. Tracking Objects :
● Using surveillance cameras we can keep track of
household items.
● We can keep an eye on our important stuff.
1. Automotive Safety :
● Vision system can assure safety of vehicles in auto pilot
mode.
● Using cameras we can detect objects nearby and can avoid
the obstacles.
12. APPLICATIONS
3. Hazardous Areas Scanning :
● Cameras and drones can go where human eyes can not reach.
● Humans can take a look inside the hazardous areas using drones.
4. Biological Applications :
● Small cameras are used in surgeries to detect the area of body.
● Vision systems can also detect various samples of microbes and DNA.
13. TASKS
Computer vision includes methods for acquiring, processing, analyzing and
understanding digital images, and extraction of high-dimensional data from
the real world in order to produce numerical or symbolic information.
Some examples of typical computer vision tasks are :
• Object Detection
• Image Classification
• Visual Relationship Detection
• Image Reconstruction
14. CLASSIFICATION OF TASKS
The tasks of a computer vision application may be classified into three
levels (low, medium, and high)
• Low-level operations
• Medium-level operations
• High-level operations
15. CONCLUSION
• Computer vision will become ubiquitous and invisible
• It will be a huge creator of value, both for suppliers as well as those who leverage
the technology in their applications
• Deep learning will become a dominant technique (but not the only technique)
• Development shifts from implementation to integration