SlideShare a Scribd company logo
1 of 43
Download to read offline
Enhancing Computer Vision in
Low Visibility Conditions
Pushing the limits for machine learning and computer vision
Dr. Pratik Narang
Assistant Professor,
Department of Computer Science and Information Systems
BITS Pilani
What is Machine Learning?
● The science of getting computers to act without being explicitly programmed.
● Study of computer algorithms that improve automatically through experience
● Composition of non-linear transformation of data
Goal : Learn useful representation
● These representations, known as features, are derived directly from data
● There can be several varieties to achieve this goal - supervised, unsupervised,
reinforcement etc.
What is Machine Learning?
astroml.org
And, what is Computer Vision ?
“ Learning feature representations” from
visual data is not enough.
The classical 3 R’s of computational vision :
Reconstruction
Recognition
Re-organization
- Jitendra Malik, UC Berkeley
Real World
Images, videos, 3D scans,
sensor data, Structured Visual
Sets etc.
3
Model of the
Visual World
Image filtering, Interest points,
Feature Encoding, Wavelet
descriptors ...
2
Information
Object Recognition, Acton
Recognition, Video
Summarization, Large-Scale
Scene Understanding etc.
1
What has Computer Vision
achieved today?
Face Recognition
Autonomous Vehicles Object Detection
Healthcare 3D reconstruction
Driver Surveillance
LIMITATIONS… ??
● Would you use an autonomous vehicle on a dark night, in a
severe snowstorm / sand storm, or in dense fog?
● Most approaches are designed to work on images/videos
captured in clear lighting conditions and good resolution.
● The performance deteriorates in low visibility conditions.
● Conditions of low-visibility are a frequent occurrence in real-life.
Computer Vision in Low Visibility?
● Indonesia's airlines face losses of flight delays and
cancellations caused by smoke from wildfires. From Sep 3 to
Sep 21, 750 flights have been cancelled.
● Delhi air pollution: 19 flights cancelled, over 550 delayed
and 37 diverted.
● Malaysia’s Penang International Airport chooses to shut
down as visibility drops below 800m.
GENERATIVE MODELS
“What I cannot create, I do not understand.”
● Computer Vision and Deep Learning
are great at classification models
● The tricky part is to develop models
and algorithms that can analyze and
understand treasure of data we have
today.
● Generative models are one of the
most promising approaches towards
this goal.
Image-to-Image Translation
Generative Adversarial Networks
● Train two algorithms simultaneously (Goodfellow et al 2014)
“Competition is always a good thing. It forces us to do our best. A monopoly
renders people complacent and satisfied with mediocrity.” – Nancy Pearcy.
Generative Adversarial Net framework
● A game between two players
a. Discriminator D
b. Generator G
● D tries to discriminate between
a. A sample from data distribution
b. And a sample from the generator G
● G tries to trick D by generating samples that are hard for D to distinguish
from data
● Choose actions, pivoting on mixed strategy equilibrium
Generating faces
Recent Developments
Isola et al. CVPR 2017
Image domain translation
Enhancing computer vision
in low visibility
USING GANs
● Given enough data of
○ Clear images
○ Images in low visibility
Can we learn to generate clear images from the images captured in low
visibility?
Note: the data need not be paired
Goal
• Image dehazing • Low light vision
Our Hypothesis
Clean Image
Low Visibility Images
Hyperspectral
Translation
Post Processing
HIDeGAN: A Hyperspectral-guided Image Dehazing GAN
Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang
CVPRW 2020
Image-to-Hyperspectral Translation
● Key Motivation: extending
the input image domain to
incorporate the complete
visual spectrum
HIDeGAN: A Hyperspectral-guided Image Dehazing GAN
Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang
CVPRW 2020
Visualizing the visual-spectrum
Comparison of reconstructed luminance across several spectral
bands for a hazy input image
HIDeGAN: A Hyperspectral-guided Image Dehazing GAN
Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang
CVPRW 2020
Visualizing the visual-spectrum
Comparison of reconstructed luminance across several spectral
bands for a hazy input image
HIDeGAN: A Hyperspectral-guided Image Dehazing GAN
Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang
CVPRW 2020
Visualizing the visual-spectrum
Comparison of reconstructed luminance across several spectral
bands for a hazy input image
HIDeGAN: A Hyperspectral-guided Image Dehazing GAN
Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang
CVPRW 2020
Hyperspectral Imagery?
● Obtain the spectrum for each pixel in the image of a scene, with the
purpose of finding objects, identifying materials.
● Special spectral cameras are required.
● Hyperspectral images consist of rich information from visual bands
● However, existing techniques for primary vision tasks such as
segmentation and classification are based on RGB images.
Roadmap
● RGB-to-Hyperspectral
Reconstruction
● Unsupervised Domain
Adaptation
● High acquisition cost of
hyperspectral images
● Lack of large-scale
hyperspectral datasets
Unsupervised Domain Adaptation
● Distributional Discrepancy
between RGB and
hyperspectral images
Roadmap
● Feature Alignment for
hyperspectral images
Haze Removal from Aerial Images
Domain Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing
Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang
WACV 2021
Domain Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing
Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang
WACV 2021
Proposed Architecture
Domain Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing
Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang
WACV 2021
Domain Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing
Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang
WACV 2021
Low-Light Image Enhancement
Learning to Enhance Visual Quality via Hyperspectral Domain Mapping
Harsh Sinha, Aditya Mehta, Murari Mandal and Pratik Narang
AAAI 2021
Improving Image-to-Hyperspectral translation
● GAN based image-translation
have a common basic structure.
● The loss functions used are
focused entirely on the output
image space.
● Although the results are visually
pleasing, but they often cause
spectral aberrations. Durall et al. CVPR 2020
Spectral profile Optimization
Learning to Enhance Visual Quality via Hyperspectral Domain Mapping
Harsh Sinha, Aditya Mehta, Murari Mandal and Pratik Narang
AAAI 2021
Comparative Results
Learning to Enhance Visual Quality via Hyperspectral Domain Mapping
Harsh Sinha, Aditya Mehta, Murari Mandal and Pratik Narang
AAAI 2021
Domain Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing
Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang
WACV 2021
● RGB-HSI Unsupervised Domain Adaptation
● A novel GAN framework to incorporate HSI guidance in image-to-image
translation tasks
○ Distributional Discrepancy between RGB and hyperspectral images
○ Non-existence of hazy hyperspectral datasets
○ Robust to distortions and visual degradation
○ Combines adversarial distribution discrepancy alignment and cycle-consistency
constraint
Key Contributions
● A novel neuro-symbolic approach to image-translation task using multi-
channel spectral-profile optimization
● Extending the viability of using hyperspectral images in image enhancement.
● Proposed a large-scale Hazy Aerial Image Dataset (HAI) with 65000 images
Learning to Enhance Visual Quality via Hyperspectral Domain Mapping
Harsh Sinha, Aditya Mehta, Murari Mandal and Pratik Narang
AAAI 2021
Key Contributions
References
● Harsh Sinha, Aditya Mehta, Murari Mandal and Pratik Narang.Learning to Enhance Visual Quality via Hyperspectral Domain
Mapping. Proceedings of the AAAI Conference on Artificial Intelligence 2021
● Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang. Domain-Aware Un-supervised Hyperspectral Reconstruction
for Aerial Image Dehazing. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2021
● Aditya Mehta, Harsh Sinha, Pratik Narang and Murari Mandal. HIDeGAN: A Hyperspectral-guided Image Dehazing GAN.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops 2020
Thank you!

More Related Content

What's hot

Backbone can not be trained at once rolling back to pre trained network for p...
Backbone can not be trained at once rolling back to pre trained network for p...Backbone can not be trained at once rolling back to pre trained network for p...
Backbone can not be trained at once rolling back to pre trained network for p...NAVER Engineering
 
[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniquesJaeJun Yoo
 
State-of-the-art Image Processing across all domains
State-of-the-art Image Processing across all domainsState-of-the-art Image Processing across all domains
State-of-the-art Image Processing across all domainsKnoldus Inc.
 
Dataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problemsDataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problemsPetteriTeikariPhD
 
Visión SenS - Why should blind people be limited to information in Braille ?
Visión SenS - Why should blind people be limited to information in Braille ?Visión SenS - Why should blind people be limited to information in Braille ?
Visión SenS - Why should blind people be limited to information in Braille ?icchp2012
 
Towards Accurate Multi-person Pose Estimation in the Wild (My summery)
Towards Accurate Multi-person Pose Estimation in the Wild (My summery)Towards Accurate Multi-person Pose Estimation in the Wild (My summery)
Towards Accurate Multi-person Pose Estimation in the Wild (My summery)Abdulrahman Kerim
 
[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of FunctionsJaeJun Yoo
 
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...Edge AI and Vision Alliance
 

What's hot (10)

Backbone can not be trained at once rolling back to pre trained network for p...
Backbone can not be trained at once rolling back to pre trained network for p...Backbone can not be trained at once rolling back to pre trained network for p...
Backbone can not be trained at once rolling back to pre trained network for p...
 
PPI_Technology_Overview
PPI_Technology_OverviewPPI_Technology_Overview
PPI_Technology_Overview
 
14
1414
14
 
[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques
 
State-of-the-art Image Processing across all domains
State-of-the-art Image Processing across all domainsState-of-the-art Image Processing across all domains
State-of-the-art Image Processing across all domains
 
Dataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problemsDataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problems
 
Visión SenS - Why should blind people be limited to information in Braille ?
Visión SenS - Why should blind people be limited to information in Braille ?Visión SenS - Why should blind people be limited to information in Braille ?
Visión SenS - Why should blind people be limited to information in Braille ?
 
Towards Accurate Multi-person Pose Estimation in the Wild (My summery)
Towards Accurate Multi-person Pose Estimation in the Wild (My summery)Towards Accurate Multi-person Pose Estimation in the Wild (My summery)
Towards Accurate Multi-person Pose Estimation in the Wild (My summery)
 
[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions
 
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...
 

Similar to Pratik ibm-open power-ppt

Face-GAN project report.pptx
Face-GAN project report.pptxFace-GAN project report.pptx
Face-GAN project report.pptxAndleebFatima16
 
Learning visual representation without human label
Learning visual representation without human labelLearning visual representation without human label
Learning visual representation without human labelKai-Wen Zhao
 
Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.IRJET Journal
 
Retinal Image Analysis using Machine Learning and Deep.pptx
Retinal Image Analysis using Machine Learning and Deep.pptxRetinal Image Analysis using Machine Learning and Deep.pptx
Retinal Image Analysis using Machine Learning and Deep.pptxDeval Bhapkar
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningAli Alkan
 
A Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question AnsweringA Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question AnsweringIRJET Journal
 
Object based Classification of Satellite Images by Combining the HDP, IBP and...
Object based Classification of Satellite Images by Combining the HDP, IBP and...Object based Classification of Satellite Images by Combining the HDP, IBP and...
Object based Classification of Satellite Images by Combining the HDP, IBP and...IRJET Journal
 
IRJET- Exploring Image Super Resolution Techniques
IRJET- Exploring Image Super Resolution TechniquesIRJET- Exploring Image Super Resolution Techniques
IRJET- Exploring Image Super Resolution TechniquesIRJET Journal
 
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...Tulipp. Eu
 
Rotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET Transform
Rotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET TransformRotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET Transform
Rotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET TransformIRJET Journal
 
10.1.1.432.9149.pdf
10.1.1.432.9149.pdf10.1.1.432.9149.pdf
10.1.1.432.9149.pdfmoemi1
 
https://uii.io/0hIB
https://uii.io/0hIBhttps://uii.io/0hIB
https://uii.io/0hIBmoemi1
 
10.1.1.432.9149
10.1.1.432.914910.1.1.432.9149
10.1.1.432.9149moemi1
 
Quality assessment of stereoscopic 3 d image compression by binocular integra...
Quality assessment of stereoscopic 3 d image compression by binocular integra...Quality assessment of stereoscopic 3 d image compression by binocular integra...
Quality assessment of stereoscopic 3 d image compression by binocular integra...Shakas Technologies
 
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEWFACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEWIRJET Journal
 
A Literature Survey: Neural Networks for object detection
A Literature Survey: Neural Networks for object detectionA Literature Survey: Neural Networks for object detection
A Literature Survey: Neural Networks for object detectionvivatechijri
 
10.1109@ICCMC48092.2020.ICCMC-000167.pdf
10.1109@ICCMC48092.2020.ICCMC-000167.pdf10.1109@ICCMC48092.2020.ICCMC-000167.pdf
10.1109@ICCMC48092.2020.ICCMC-000167.pdfmokamojah
 

Similar to Pratik ibm-open power-ppt (20)

Face-GAN project report.pptx
Face-GAN project report.pptxFace-GAN project report.pptx
Face-GAN project report.pptx
 
Face-GAN project report
Face-GAN project reportFace-GAN project report
Face-GAN project report
 
Learning visual representation without human label
Learning visual representation without human labelLearning visual representation without human label
Learning visual representation without human label
 
Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.
 
Retinal Image Analysis using Machine Learning and Deep.pptx
Retinal Image Analysis using Machine Learning and Deep.pptxRetinal Image Analysis using Machine Learning and Deep.pptx
Retinal Image Analysis using Machine Learning and Deep.pptx
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
 
A Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question AnsweringA Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question Answering
 
Object based Classification of Satellite Images by Combining the HDP, IBP and...
Object based Classification of Satellite Images by Combining the HDP, IBP and...Object based Classification of Satellite Images by Combining the HDP, IBP and...
Object based Classification of Satellite Images by Combining the HDP, IBP and...
 
ObjectDetection.pptx
ObjectDetection.pptxObjectDetection.pptx
ObjectDetection.pptx
 
IRJET- Exploring Image Super Resolution Techniques
IRJET- Exploring Image Super Resolution TechniquesIRJET- Exploring Image Super Resolution Techniques
IRJET- Exploring Image Super Resolution Techniques
 
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
 
Rotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET Transform
Rotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET TransformRotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET Transform
Rotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET Transform
 
10.1.1.432.9149.pdf
10.1.1.432.9149.pdf10.1.1.432.9149.pdf
10.1.1.432.9149.pdf
 
https://uii.io/0hIB
https://uii.io/0hIBhttps://uii.io/0hIB
https://uii.io/0hIB
 
10.1.1.432.9149
10.1.1.432.914910.1.1.432.9149
10.1.1.432.9149
 
Quality assessment of stereoscopic 3 d image compression by binocular integra...
Quality assessment of stereoscopic 3 d image compression by binocular integra...Quality assessment of stereoscopic 3 d image compression by binocular integra...
Quality assessment of stereoscopic 3 d image compression by binocular integra...
 
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEWFACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
 
Image recognition
Image recognitionImage recognition
Image recognition
 
A Literature Survey: Neural Networks for object detection
A Literature Survey: Neural Networks for object detectionA Literature Survey: Neural Networks for object detection
A Literature Survey: Neural Networks for object detection
 
10.1109@ICCMC48092.2020.ICCMC-000167.pdf
10.1109@ICCMC48092.2020.ICCMC-000167.pdf10.1109@ICCMC48092.2020.ICCMC-000167.pdf
10.1109@ICCMC48092.2020.ICCMC-000167.pdf
 

More from Vaibhav R

Ics21 workshop decoupling compute from memory, storage & io with omi - ...
Ics21 workshop   decoupling compute from memory, storage & io with omi - ...Ics21 workshop   decoupling compute from memory, storage & io with omi - ...
Ics21 workshop decoupling compute from memory, storage & io with omi - ...Vaibhav R
 
Cineca 2021 open power
Cineca 2021   open powerCineca 2021   open power
Cineca 2021 open powerVaibhav R
 
Open source tools for logic synthesis and soc design an overview
Open source tools for logic synthesis and soc design  an overviewOpen source tools for logic synthesis and soc design  an overview
Open source tools for logic synthesis and soc design an overviewVaibhav R
 
Iit roorkee 2021
Iit roorkee 2021Iit roorkee 2021
Iit roorkee 2021Vaibhav R
 
Mayflower external overview
Mayflower external overviewMayflower external overview
Mayflower external overviewVaibhav R
 
Cyber security analysis presentation
Cyber security analysis presentationCyber security analysis presentation
Cyber security analysis presentationVaibhav R
 
Industry 4.0 scopes (1)
Industry 4.0 scopes (1)Industry 4.0 scopes (1)
Industry 4.0 scopes (1)Vaibhav R
 
Presentation1
Presentation1Presentation1
Presentation1Vaibhav R
 

More from Vaibhav R (8)

Ics21 workshop decoupling compute from memory, storage & io with omi - ...
Ics21 workshop   decoupling compute from memory, storage & io with omi - ...Ics21 workshop   decoupling compute from memory, storage & io with omi - ...
Ics21 workshop decoupling compute from memory, storage & io with omi - ...
 
Cineca 2021 open power
Cineca 2021   open powerCineca 2021   open power
Cineca 2021 open power
 
Open source tools for logic synthesis and soc design an overview
Open source tools for logic synthesis and soc design  an overviewOpen source tools for logic synthesis and soc design  an overview
Open source tools for logic synthesis and soc design an overview
 
Iit roorkee 2021
Iit roorkee 2021Iit roorkee 2021
Iit roorkee 2021
 
Mayflower external overview
Mayflower external overviewMayflower external overview
Mayflower external overview
 
Cyber security analysis presentation
Cyber security analysis presentationCyber security analysis presentation
Cyber security analysis presentation
 
Industry 4.0 scopes (1)
Industry 4.0 scopes (1)Industry 4.0 scopes (1)
Industry 4.0 scopes (1)
 
Presentation1
Presentation1Presentation1
Presentation1
 

Recently uploaded

obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...yulianti213969
 
Abortion Clinic in Kempton Park +27791653574 WhatsApp Abortion Clinic Service...
Abortion Clinic in Kempton Park +27791653574 WhatsApp Abortion Clinic Service...Abortion Clinic in Kempton Park +27791653574 WhatsApp Abortion Clinic Service...
Abortion Clinic in Kempton Park +27791653574 WhatsApp Abortion Clinic Service...mikehavy0
 
sourabh vyas1222222222222222222244444444
sourabh vyas1222222222222222222244444444sourabh vyas1222222222222222222244444444
sourabh vyas1222222222222222222244444444saurabvyas476
 
👉 Tirunelveli Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Gir...
👉 Tirunelveli Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Gir...👉 Tirunelveli Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Gir...
👉 Tirunelveli Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Gir...vershagrag
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...Elaine Werffeli
 
Huawei Ransomware Protection Storage Solution Technical Overview Presentation...
Huawei Ransomware Protection Storage Solution Technical Overview Presentation...Huawei Ransomware Protection Storage Solution Technical Overview Presentation...
Huawei Ransomware Protection Storage Solution Technical Overview Presentation...LuisMiguelPaz5
 
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Klinik kandungan
 
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证pwgnohujw
 
Pentesting_AI and security challenges of AI
Pentesting_AI and security challenges of AIPentesting_AI and security challenges of AI
Pentesting_AI and security challenges of AIf6x4zqzk86
 
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证acoha1
 
ℂall Girls In Navi Mumbai Hire Me Neha 9910780858 Top Class ℂall Girl Serviℂe...
ℂall Girls In Navi Mumbai Hire Me Neha 9910780858 Top Class ℂall Girl Serviℂe...ℂall Girls In Navi Mumbai Hire Me Neha 9910780858 Top Class ℂall Girl Serviℂe...
ℂall Girls In Navi Mumbai Hire Me Neha 9910780858 Top Class ℂall Girl Serviℂe...Amara arora$V15
 
Identify Rules that Predict Patient’s Heart Disease - An Application of Decis...
Identify Rules that Predict Patient’s Heart Disease - An Application of Decis...Identify Rules that Predict Patient’s Heart Disease - An Application of Decis...
Identify Rules that Predict Patient’s Heart Disease - An Application of Decis...ThinkInnovation
 
RESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptx
RESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptxRESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptx
RESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptxronsairoathenadugay
 
Predictive Precipitation: Advanced Rain Forecasting Techniques
Predictive Precipitation: Advanced Rain Forecasting TechniquesPredictive Precipitation: Advanced Rain Forecasting Techniques
Predictive Precipitation: Advanced Rain Forecasting TechniquesBoston Institute of Analytics
 
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样jk0tkvfv
 
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarj
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarjSCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarj
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarjadimosmejiaslendon
 
Seven tools of quality control.slideshare
Seven tools of quality control.slideshareSeven tools of quality control.slideshare
Seven tools of quality control.slideshareraiaryan448
 
Digital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareDigital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareGraham Ware
 
Displacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second DerivativesDisplacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second Derivatives23050636
 

Recently uploaded (20)

obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
 
Abortion Clinic in Kempton Park +27791653574 WhatsApp Abortion Clinic Service...
Abortion Clinic in Kempton Park +27791653574 WhatsApp Abortion Clinic Service...Abortion Clinic in Kempton Park +27791653574 WhatsApp Abortion Clinic Service...
Abortion Clinic in Kempton Park +27791653574 WhatsApp Abortion Clinic Service...
 
sourabh vyas1222222222222222222244444444
sourabh vyas1222222222222222222244444444sourabh vyas1222222222222222222244444444
sourabh vyas1222222222222222222244444444
 
👉 Tirunelveli Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Gir...
👉 Tirunelveli Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Gir...👉 Tirunelveli Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Gir...
👉 Tirunelveli Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Gir...
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
 
Huawei Ransomware Protection Storage Solution Technical Overview Presentation...
Huawei Ransomware Protection Storage Solution Technical Overview Presentation...Huawei Ransomware Protection Storage Solution Technical Overview Presentation...
Huawei Ransomware Protection Storage Solution Technical Overview Presentation...
 
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
 
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证
 
Pentesting_AI and security challenges of AI
Pentesting_AI and security challenges of AIPentesting_AI and security challenges of AI
Pentesting_AI and security challenges of AI
 
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证
 
ℂall Girls In Navi Mumbai Hire Me Neha 9910780858 Top Class ℂall Girl Serviℂe...
ℂall Girls In Navi Mumbai Hire Me Neha 9910780858 Top Class ℂall Girl Serviℂe...ℂall Girls In Navi Mumbai Hire Me Neha 9910780858 Top Class ℂall Girl Serviℂe...
ℂall Girls In Navi Mumbai Hire Me Neha 9910780858 Top Class ℂall Girl Serviℂe...
 
Identify Rules that Predict Patient’s Heart Disease - An Application of Decis...
Identify Rules that Predict Patient’s Heart Disease - An Application of Decis...Identify Rules that Predict Patient’s Heart Disease - An Application of Decis...
Identify Rules that Predict Patient’s Heart Disease - An Application of Decis...
 
RESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptx
RESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptxRESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptx
RESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptx
 
Predictive Precipitation: Advanced Rain Forecasting Techniques
Predictive Precipitation: Advanced Rain Forecasting TechniquesPredictive Precipitation: Advanced Rain Forecasting Techniques
Predictive Precipitation: Advanced Rain Forecasting Techniques
 
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
 
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarj
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarjSCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarj
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarj
 
Seven tools of quality control.slideshare
Seven tools of quality control.slideshareSeven tools of quality control.slideshare
Seven tools of quality control.slideshare
 
Digital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareDigital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham Ware
 
Abortion pills in Doha {{ QATAR }} +966572737505) Get Cytotec
Abortion pills in Doha {{ QATAR }} +966572737505) Get CytotecAbortion pills in Doha {{ QATAR }} +966572737505) Get Cytotec
Abortion pills in Doha {{ QATAR }} +966572737505) Get Cytotec
 
Displacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second DerivativesDisplacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second Derivatives
 

Pratik ibm-open power-ppt

  • 1. Enhancing Computer Vision in Low Visibility Conditions Pushing the limits for machine learning and computer vision Dr. Pratik Narang Assistant Professor, Department of Computer Science and Information Systems BITS Pilani
  • 2. What is Machine Learning? ● The science of getting computers to act without being explicitly programmed. ● Study of computer algorithms that improve automatically through experience ● Composition of non-linear transformation of data Goal : Learn useful representation ● These representations, known as features, are derived directly from data ● There can be several varieties to achieve this goal - supervised, unsupervised, reinforcement etc.
  • 3. What is Machine Learning? astroml.org
  • 4. And, what is Computer Vision ? “ Learning feature representations” from visual data is not enough. The classical 3 R’s of computational vision : Reconstruction Recognition Re-organization - Jitendra Malik, UC Berkeley
  • 5. Real World Images, videos, 3D scans, sensor data, Structured Visual Sets etc. 3 Model of the Visual World Image filtering, Interest points, Feature Encoding, Wavelet descriptors ... 2 Information Object Recognition, Acton Recognition, Video Summarization, Large-Scale Scene Understanding etc. 1
  • 6. What has Computer Vision achieved today?
  • 7. Face Recognition Autonomous Vehicles Object Detection Healthcare 3D reconstruction Driver Surveillance
  • 8. LIMITATIONS… ?? ● Would you use an autonomous vehicle on a dark night, in a severe snowstorm / sand storm, or in dense fog? ● Most approaches are designed to work on images/videos captured in clear lighting conditions and good resolution. ● The performance deteriorates in low visibility conditions. ● Conditions of low-visibility are a frequent occurrence in real-life.
  • 9. Computer Vision in Low Visibility? ● Indonesia's airlines face losses of flight delays and cancellations caused by smoke from wildfires. From Sep 3 to Sep 21, 750 flights have been cancelled. ● Delhi air pollution: 19 flights cancelled, over 550 delayed and 37 diverted. ● Malaysia’s Penang International Airport chooses to shut down as visibility drops below 800m.
  • 11. “What I cannot create, I do not understand.” ● Computer Vision and Deep Learning are great at classification models ● The tricky part is to develop models and algorithms that can analyze and understand treasure of data we have today. ● Generative models are one of the most promising approaches towards this goal.
  • 13. Generative Adversarial Networks ● Train two algorithms simultaneously (Goodfellow et al 2014) “Competition is always a good thing. It forces us to do our best. A monopoly renders people complacent and satisfied with mediocrity.” – Nancy Pearcy.
  • 14. Generative Adversarial Net framework ● A game between two players a. Discriminator D b. Generator G ● D tries to discriminate between a. A sample from data distribution b. And a sample from the generator G ● G tries to trick D by generating samples that are hard for D to distinguish from data ● Choose actions, pivoting on mixed strategy equilibrium
  • 17. Isola et al. CVPR 2017 Image domain translation
  • 18. Enhancing computer vision in low visibility USING GANs
  • 19. ● Given enough data of ○ Clear images ○ Images in low visibility Can we learn to generate clear images from the images captured in low visibility? Note: the data need not be paired Goal
  • 20. • Image dehazing • Low light vision
  • 21. Our Hypothesis Clean Image Low Visibility Images Hyperspectral Translation Post Processing HIDeGAN: A Hyperspectral-guided Image Dehazing GAN Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang CVPRW 2020
  • 22. Image-to-Hyperspectral Translation ● Key Motivation: extending the input image domain to incorporate the complete visual spectrum HIDeGAN: A Hyperspectral-guided Image Dehazing GAN Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang CVPRW 2020
  • 23. Visualizing the visual-spectrum Comparison of reconstructed luminance across several spectral bands for a hazy input image HIDeGAN: A Hyperspectral-guided Image Dehazing GAN Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang CVPRW 2020
  • 24. Visualizing the visual-spectrum Comparison of reconstructed luminance across several spectral bands for a hazy input image HIDeGAN: A Hyperspectral-guided Image Dehazing GAN Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang CVPRW 2020
  • 25. Visualizing the visual-spectrum Comparison of reconstructed luminance across several spectral bands for a hazy input image HIDeGAN: A Hyperspectral-guided Image Dehazing GAN Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang CVPRW 2020
  • 26. Hyperspectral Imagery? ● Obtain the spectrum for each pixel in the image of a scene, with the purpose of finding objects, identifying materials. ● Special spectral cameras are required. ● Hyperspectral images consist of rich information from visual bands ● However, existing techniques for primary vision tasks such as segmentation and classification are based on RGB images.
  • 27. Roadmap ● RGB-to-Hyperspectral Reconstruction ● Unsupervised Domain Adaptation ● High acquisition cost of hyperspectral images ● Lack of large-scale hyperspectral datasets
  • 29. ● Distributional Discrepancy between RGB and hyperspectral images Roadmap ● Feature Alignment for hyperspectral images
  • 30. Haze Removal from Aerial Images Domain Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang WACV 2021
  • 31. Domain Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang WACV 2021 Proposed Architecture
  • 32.
  • 33. Domain Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang WACV 2021
  • 34. Domain Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang WACV 2021
  • 35. Low-Light Image Enhancement Learning to Enhance Visual Quality via Hyperspectral Domain Mapping Harsh Sinha, Aditya Mehta, Murari Mandal and Pratik Narang AAAI 2021
  • 36. Improving Image-to-Hyperspectral translation ● GAN based image-translation have a common basic structure. ● The loss functions used are focused entirely on the output image space. ● Although the results are visually pleasing, but they often cause spectral aberrations. Durall et al. CVPR 2020
  • 37. Spectral profile Optimization Learning to Enhance Visual Quality via Hyperspectral Domain Mapping Harsh Sinha, Aditya Mehta, Murari Mandal and Pratik Narang AAAI 2021
  • 38.
  • 39. Comparative Results Learning to Enhance Visual Quality via Hyperspectral Domain Mapping Harsh Sinha, Aditya Mehta, Murari Mandal and Pratik Narang AAAI 2021
  • 40. Domain Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang WACV 2021 ● RGB-HSI Unsupervised Domain Adaptation ● A novel GAN framework to incorporate HSI guidance in image-to-image translation tasks ○ Distributional Discrepancy between RGB and hyperspectral images ○ Non-existence of hazy hyperspectral datasets ○ Robust to distortions and visual degradation ○ Combines adversarial distribution discrepancy alignment and cycle-consistency constraint Key Contributions
  • 41. ● A novel neuro-symbolic approach to image-translation task using multi- channel spectral-profile optimization ● Extending the viability of using hyperspectral images in image enhancement. ● Proposed a large-scale Hazy Aerial Image Dataset (HAI) with 65000 images Learning to Enhance Visual Quality via Hyperspectral Domain Mapping Harsh Sinha, Aditya Mehta, Murari Mandal and Pratik Narang AAAI 2021 Key Contributions
  • 42. References ● Harsh Sinha, Aditya Mehta, Murari Mandal and Pratik Narang.Learning to Enhance Visual Quality via Hyperspectral Domain Mapping. Proceedings of the AAAI Conference on Artificial Intelligence 2021 ● Aditya Mehta, Harsh Sinha, Murari Mandal and Pratik Narang. Domain-Aware Un-supervised Hyperspectral Reconstruction for Aerial Image Dehazing. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2021 ● Aditya Mehta, Harsh Sinha, Pratik Narang and Murari Mandal. HIDeGAN: A Hyperspectral-guided Image Dehazing GAN. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops 2020