The Computer Vision Developer Conference, CVDC 2020, has interesting talks and sessions around the latest developments in the field of computer vision. The two-day conference, scheduled for 13 and 14 August will host paper presentations, tech talks and workshops for computer vision practitioners. The virtual conference will uncover some of the most interesting developments, and the latest research and advancements in this area, which is witnessing some interesting use cases across the world.
Here are 11 interesting talks, workshops and sessions that you should definitely attend.
1| Create your own Camscanner using OpenCV in Python by Shirish Gupta, Head of Data Science & Partnerships at NBFC Loan2Grow
This talk by Shirish Gupta will focus on how apps such as CamScanner and similar apps can be created using computer vision. Apps such as Camsanner are very effective in allowing users to scan documents from mobile and sharing it as an image. It brings several advantages such as cleaning, sharpening, denoising the camera-clicked image into a refined output. It can do so using computer vision, and Gupta will take the attendees through a session on using the technology, especially using the basics of OpenCV in Python to create a similar app. OpenCV is an open-source computer vision library which was built to provide a common infrastructure for computer vision applications. After the completion of this workshop, the audience will be able to use OpenCV to understand different transformation functions such as blurring, thresholding, canny edge detection, etc.; create a functional CamScanner Bonus, using Pytesseract (OCR) to extract data from images. It requires candidates to have familiarity with Python, basics of OpenCV (preferred, not mandatory).
2| Leveraging Computer Vision in drone tech by Animesh Dutta Machine Learning Developer at Kesowa
Drone technology is being widely explored, especially with the emergence of technologies such as artificial intelligence, deep learning, autonomy and more. Researchers are working on creating unmanned aerial systems to deliver solutions. In this talk by Animesh Dutta, he will take attendees to how computer vision can help in drone technology. He believes that the day is not far away when we will see flying cars. There are several use cases of drones attainable with the help of Computer Vision — such as detecting anomalous behaviour in a crowd. Using Bayesian Loss for Crowd Count Estimation with Point Supervision it can generate a density map showing humans. Furthermore, computer vision techniques can detect cracks in a building, detect potholes, and more.
3| Autonomous Driving Perception Using Cameras in Unstructured Environments: Challenges & Solutions by Sanjeev Sharma Founder and CEO at Swaayatt Robots
One of the fields where computer vision is extensively used is self-driving cars. In this talk by Sanjeev Sharma, he will talk about numerous challenges associated with enabling autonomous driving perception using only cameras. Especially in highly unstructured environments. He will focus on developing real-time deep learning inference models to overcome such challenges. Swaayatt Robots is one of the leading companies in India working in the self-driving space. The technology by this startup enables self-driving vehicles to perceive their environments using off-the-shelf cameras.
4| Explainable AI for Computer Vision by Avni Gupta Technology Lead at SYNDUIT
While creating computer vision models, researchers may often find themselves interacting with a black box, unaware of what feature extraction is happening at each layer. Explainable AI makes it easy to comprehend and know when enough layers have been added and what feature extraction has taken place at each layer. In this session, Avni Gupta we will take the attendees through various libraries that make this possible.
5| Intercepting youth at risk using Computer vision on Social Media Platform by Dr Murphy Choy Executive Director at MC EduTech
The lockdown due to the ongoing pandemic has forced many to stay indoors. There were reports about family feuds and violence happening at a much higher frequency compared to the pre-Covid 19 periods. This is a cause of major concerns to many social workers. Younger members of the population generally take to social media to air their frustrations, which provides a channel for social workers to reach out. However, social workers can only screen a limited amount of information on social media. With his talk, Dr Choy will discuss how computer vision can be used to augment a social worker’s ability to identify youth at risk using Computer Vision combined with a Knowledge Graph.
6 | Understanding robustness of computer vision by Indrajit Kar Principal Solution Architect at Accenture
This talk by Indrajit Kar will focus on the threat to current computer Vision models and how we can subsequently make AI more resilient to attack. It will focus on the motivations, feasibility, and risks posed by adversarial input/Perturbations. It will explore how intelligent systems based on computer vision can be made more robust against adversarial input. AI not only competes with human capabilities in areas such as image, audio, and text processing but often exceeds human accuracy and speed. While we celebrate advancements in AI, deep neural networks (DNNs)—the algorithms intrinsic to much of AI—have recently been proven to be at risk from attack through seemingly benign inputs. It is, therefore, important to identify and detect these problems, which is what this talk will deal with.
7| How Computer Vision is improving healthcare by Akshit Priyesh Data Scientist at Capgemini
Computer vision can potentially support the healthcare industry in many different applications and deliver life-saving functionalities for patients. Currently, the technology is assisting doctors to better diagnose their patients, monitor the evolution of diseases, and prescribe the right treatments. It has been used in imaging analysis, predictive analysis, and healthcare monitoring. Currently, the most widespread use cases for computer vision and healthcare are related to the field of radiology and imaging. In this talk, Akshit will discuss how it can be explored in many different areas including Covid.
8| Challenges for Deep Learning in Medical Imaging and how to overcome them by Abdul Jilani Lead Data Scientist at DataRobot
While deep learning on medical imaging is popular, it doesn’t translate easily or quickly into practical or production-ready tech. This talk by Abdul Jilani will address the challenges faced by applied machine learners and how they can overcome these challenges in real-time environments. It will take a deep dive into the problems faced by Medical Imaging researchers such as building good training datasets, wrong practices such as leakage and more. He will talk about sampling biases and strategies for medical image datasets., discuss data augmentation strategies used for different image types like x-rays, how to mimic real-time imaging in datasets built in perfect lab conditions and more.
9| Workshop on Deep Learning for Computer Vision by Dr Vaibhav Kumar Director at Association of Data Scientists
This full-day workshop aims at familiarising the concepts of deep learning techniques applied in the field of computer vision. Deep learning has added a boost to the rapidly growing field of computer vision by providing powerful tools to distil actionable information from images. With deep learning, a lot of new applications of computer vision techniques have been introduced and are now becoming parts of our daily lives. This workshop by Dr Kumar aims to take through such use cases.
10| Best practices in machine learning and the art of research management by Dan Malowany Head of Deep Learning Research at allegro.ai
ML and deep learning projects involve iterative and recursive R&D process of data gathering, data annotation, research, QA, deployment, additional data gathering from deployed units and back again. The strong coupling between data and model means various teams, with various backgrounds and capabilities, without the use of a unifying R&D management tool can be detrimental in the long run as it can result in reduced collaboration, loss of work, irreproducible training, and a negative effect on the overall effectiveness of the company. As such, companies must use R&D infrastructure tailored for AI projects that supports the R&D workflow from research to production and enables them to adapt their offering to the evolving demand. In this talk, Dan Malowany will share the experience from numerous deep learning projects and describe the features such infrastructure requires in order to boost productivity as well as being adaptive to the different R&D stages.
11| End to end AI by Matthew Zeiler, Founder and CEO at Clarifai
This interesting session by Matthew Zeiler will take attendees through insights on how end-to-end AI platforms can help your business by providing a unified AI strategy. As a founder of Clarifi, he works on simplifying the complexities of image and video recognition and making it easily accessible to all. Having built an incredible platform and demonstrated its problem-solving capabilities across numerous industries, Zeiler has tremendous experience in the field, which will be included in his talk as well.
Provide your comments below
If you loved this story, do join our Telegram Community.
Also, you can write for us and be one of the 500+ experts who have contributed stories at AIM. Share your nominations here.
Srishti currently works as Associate Editor at Analytics India Magazine. When not covering the analytics news, editing and writing articles, she could be found reading or capturing thoughts into pictures.