The Computer Vision Lab is a cutting-edge research facility focused on advancing the field of computer vision, which encompasses the development of algorithms, models, and systems that enable computers to understand, interpret, and analyze visual information from images and videos. Machine and autonomous systems aims to push the boundaries of computer vision technology, explore innovative approaches, and apply embedded AI based vision techniques to various domains and applications.
Key Areas/Features of Computer Vision Lab are:
The lab is committed to conducting high-quality research in computer vision, exploring novel algorithms, models, and methodologies. We strive to contribute to the state-of-the-art in the field and address complex challenges in visual understanding.
Object Detection and Recognition:
This area specializes in developing robust algorithms for detecting and recognizing objects within images and videos. We explore AI techniques for feature extraction, and image segmentation to enable accurate and efficient object detection and classification.
Image and Video Understanding:
This focuses on advancing the understanding of visual content in images and videos by developing algorithms for tasks such as scene understanding, image captioning, and activity recognition, allowing computers to comprehend and interpret visual scenes.
Image and Video Generation:
This generates new images and visual contents using AI techniques for various tasks such as image synthesis, video prediction, and image-to-image translation, enabling the creation of realistic and vivid contents.
3D Vision and Reconstruction:
This area focuses on AI techniques for 3D vision and reconstruction, aiming to understand the geometry and structure of 3D objects and scenes using passive and active sensors. We explore approaches such as stereo vision, depth estimation, and 3D reconstruction to enable 3D modeling and understanding.
This focuses on developing visual analytics techniques that combine computer vision with data analytics and interactive visualizations enabling users to gain insights and make decisions based on visual exploration and analysis of large-scale visual data.
Robotics and Autonomous Systems:
This area focuses on AI vision techniques for machines, robots, and autonomous systems, enabling them to perceive the environment and interact with it for various tasks such as object manipulation, sorting, etc. These applications span across industries such as space, industry, military, medical, and warehousing.
Medical Image Analysis:
This area specializes in the application of AI techniques to medical imaging for various tasks such as medical image segmentation, registration, disease diagnosis, and treatment planning, aiding healthcare professionals in accurate and efficient analysis of medical images.
This explores the application of AI techniques in various industrial sectors, such as manufacturing, surveillance, quality control, and augmented reality, by developing computer vision systems and solutions, to enhance productivity, efficiency, and safety in industrial settings.
Academia and Industry Partnerships:
The Computer Vision Lab actively collaborates with industry partners, academic, research institutions, and experts to drive the adoption and real-world impact of computer vision and AI technologies. We collaborate on projects, share knowledge, and engage in technology transfer to bridge the gap among academia, research institutions, and industry.
Through our research, innovation and collaborations, the Computer Vision Lab aims to advance the state-of-the-art AI techniques in computer vision, develop practical solutions for real-world challenges, and contribute to the progress of computer vision technology across a wide range of applications in the industry.