Vision & Learning Laboratory

Multi-Object Tracking

The goal of multi-object tracking is to estimate the states of multiple objects, such as locations, velocities, and sizes, while conserving their identifications. We developed confidence-based tracking and online appearance learning, and deep learning algorithms to solve this problem.

Light Detection

Accurate detection of these light sources is crucial for recognizing objects, predicting behaviors, and understanding the environment, particularly in the context of autonomous driving and surveillance systems.

On Board AI

On Board AI refers to integrated artificial intelligence systems within devices or vehicles that enable autonomous operation and real-time data processing without constant internet connectivity.

Data Free Quantization

Data-Free Quantization is a model compression technique that reduces the precision of neural network weights and activations without requiring access to the original training data, typically by generating synthetic data or using statistical information to preserve model performance.

Multi-Modal Tracking

Multi-Modal Tracking is the process of simultaneously using and integrating information from multiple sensor modalities—such as RGB images, thermal cameras, depth sensors, or LiDAR—to robustly track objects over time, even in challenging environments.

3D Object Detection

3D Object Detection is a computer vision task that involves identifying, localizing, and estimating the size and orientation of objects in three-dimensional space using input data such as images, LiDAR point clouds, or RGB-D information.