Who Are We?
This research lab aims to conduct research in the areas of applied machine (deep) learning to solve problems related to 2D/3D Computer Vision. Specifically, the application areas in computer vision include Medical image analysis, Intelligent visual surveillance, semantic understanding of visual data, remote sensing, and 3D point cloud processing.
Some of the focused areas are cancer image analytics, digital/computational pathology, diagnostic retinal image analysis, person and vehicle re-identification for visual surveillance, fine-grained object detection, semantic understanding and natural language description of visual data (images and videos), processing drone acquired aerial imagery and/or multispectral satellite imagery to perform land cover classification, forest monitoring, crop type classification and 2D /3D urban modeling.
The lab continues to drive research and technology innovation to develop cutting-edge AI algorithms and methods with a special emphasis on designing deep learning architectures for solving various computer vision problems in academia and industry. The lab maintains close links with Pakistani as well as foreign collaborators working in similar domains.