ICVRL International Computer Vision Research Laboratory
Home About Lab Research Areas Computer Vision
Core Research Specialization

Computer Vision

Fundamental research in visual understanding, image analysis, and scene interpretation using computational methods.

1 Researchers 4 Projects 4 Publications
Collaborate in this Area Join Research Lab
In-Depth Overview

Research Focus & Scope

Computer Vision at ICVRL is dedicated to empowering intelligent systems with visual cognition that rivals human perception. We conduct fundamental and applied research across image understanding, low-level vision enhancement, multi-modal vision-language architectures, 3D reconstruction, and robust visual scene parsing. Our research is driven by mathematical rigor and practical applicability in automated robotics, smart city infrastructure, and real-time visual computing.
Methodological Approach

How We Conduct Research in Computer Vision

Our methodology blends advanced convolutional neural network backbones, vision transformers (ViTs), attention mechanisms, and self-supervised visual representation learning. We emphasize model efficiency, lightweight edge optimization, and robust generalization under challenging real-world visual conditions (e.g. poor lighting, adverse weather, motion blur, and low-resolution data streams).
Impact & Deployments

Real-World Applications

Autonomous driving and drone navigation
Smart visual surveillance and anomaly detection
Industrial automated visual quality inspection
Augmented and Virtual Reality (AR/VR) scene understanding
High-resolution document and historical image preservation
Lab Projects

Projects in this Domain

All Projects

ActionNet: Video Understanding for Smart Surveillance

Intelligent video analytics system for automated activity detection and anomaly recognition in surveillance fo...

active Code

SkyWatch: Real-Time UAV Object Detection System

A real-time object detection system optimized for UAV-mounted cameras with edge computing capabilities.

active Code

TerraVision: Satellite Image Analysis for Environmental Monitoring

Deep learning-based satellite image analysis platform for land use classification and environmental change det...

active Code

FaceGuard: Robust Facial Recognition Under Adverse Conditions

Advanced face recognition system resilient to occlusion, varying lighting, and pose changes for security appli...

active
Scholarly Output

Recent Publications

All Publications
conference

Efficient Panoptic Segmentation for Autonomous Driving Scenes

Ahmad Khan, Hassan Ahmed, Ali Raza, Shams ur Rehman

International Conference on Computer Vision (ICCV), 2025

conference

Temporal Action Detection in Surveillance Videos Using Graph Neural Networks

Hassan Ahmed, Muhammad Hamza, Shams ur Rehman

European Conference on Computer Vision (ECCV), 2024

journal

Multi-Spectral Satellite Image Classification Using Hybrid CNN-Transformer Architecture

Ali Raza, Shams ur Rehman, Ahmad Khan

Remote Sensing of Environment, 2024

journal

Robust Face Recognition Under Occlusion Using Part-Based Feature Fusion

Ayesha Malik, Ahmad Khan, Shams ur Rehman

Pattern Recognition, 2024

Tech Stack & Tools

PyTorch OpenCV Vision Transformers (ViT) TensorRT ONNX CUDA Scikit-Image Albumentations Python

Active Researchers

View All Researchers

Join Our Research

Interested in conducting MS/PhD research or undergraduate projects in Computer Vision?

Apply to Join ICVRL
More Domains

Explore Other Research Areas

All Areas

Deep Learning

Advanced neural network architectures including CNNs, Transformers, and novel training paradigms for visual ta...

Explore Area

Medical Image Analysis

AI-driven analysis of medical images including X-rays, MRI, CT scans for automated diagnosis and treatment pla...

Explore Area

Object Detection

Real-time detection, localization, and classification of objects in images and video streams.

Explore Area

Image Segmentation

Pixel-level understanding of images through semantic, instance, and panoptic segmentation techniques.

Explore Area