Vision 

The Computer Vision Lab is a multidisciplinary group performing basic and applied research in image manipulation, image analysis, computer vision, and related areas of machine learning. The Computer Vision Lab investigates and develops advanced statistical and machine learning techniques for automatically analyzing, understanding, and organizing visual information. A key characteristic of the Computer Vision Lab is its high level of engagement with other departments and labs. We have strong links with other labs including Deep Learning, IoT, Smart Agriculture, Smart City, and Urban Planning lab.  

Aims & Objectives 

  • To develop novel and efficient techniques for the extraction of quantitative descriptions of viewed objects from a variety of images and videos.  
  • To translate those techniques into high-quality software tools that can be used to address real-world problems. 
  • To work both on new models and methods for studying computer vision and applications of developed models and methods to real-world problems in diverse fields of study. 

Research Areas

  • Anomaly Detection from Realtime Videos 
  • Ambient Assisted Living (AAL) 
  • High-Level Video Analysis 
  • Human Action Detection and Recognition 
  • Night thermal tracking 
  • Driving Behavior Analysis 
  • License Plate RecognitionTraffic Monitoring, and Management 
  • Crowd Analysis  
  • Medical Imaging 
  • Plants Species Identification and Early Prediction of Crop Diseases  
  • Detection of Potholes in Asphalt Pavement Images 
  • Facial Recognition 
  • Video Surveillance 
  • Sports Video Analysis  
  • Power Line Inspection 

Equipment

  • NVIDIA Jetson Nano Developer Kit  
  • NVIDIA Jetson TX2 Development Kit 
  • NVIDIA Jetson AGX Xavier Developer Kit 
  • Google Coral Dev Board Kit  
  • Intel Neural Compute Stick 2 
  • Intel® RealSense™ Depth Camera D435 
  • Microsoft, Azure Kinect DK 
  • OpenMV Cam H7 Plus 
  • OpenCV AI Kit: OAK—D 
  • HD Cameras 

Courses 

  • Introduction to Computer Vision and Image Processing 
  • Advanced Computer Vision with TensorFlow 
  • Deep Learning in Computer Vision 
  • Fundamentals of Digital Image and Video Processing 
  • Hands-on Machine Learning with Google Cloud Labs 

Projects

  • IntelliSurv: An Intelligent Surveillance System for Detection of Anomalies in Real-time Videos 
  • Face Detection and Recognition 
  • Driving Behaviour Analysis 
  • License Plate RecognitionTraffic Monitoring, and Management 
  • Passenger Detection and Counting during Getting on and off from Public Transport Systems