[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking." Our approach relies on an appearance-based object matching network jointly-learned with an underlying object detection network. An LSTM is also added to capture motion constraints.

Simple model to Track and Re-identify individuals in different cameras/videos.(Yolov3 & Yolov4)

Collection of papers, code, notebooks, datasets and other resources for Multi Object Tracking (Vehicle tracking, Pedestrian tracking) | Google colab

[WACV-2023] Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker

[IEEE Access - 2022] LMOT : Efficient Light-Weight Detection and Tracking in Crowds

An inference-only C++ implementation of FairMOT.