Multiple Object Tracker, Based on Hungarian algorithm + Kalman filter.

This is the official implementation of TransCenter (TPAMI). The code and pretrained models are now available here: https://gitlab.inria.fr/yixu/TransCenter_official.

An introduction to AI methods for flying agents (birds, UAVs, etc.)

[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

Official code of CAMO-MOT

Real time face recognition with multiple object tracking

During my summer UG research internship, I explored the use of vision transformers (ViTs) for object detection, focusing on mitigating the computational requirements of transformer models. This project successfully achieved multiple objectives and identified crucial features for future advancements in object detection using ViTs.

cell cycle analysis

Library for tracking-by-detection multi object tracking implemented in python

Unofficial implementation of the Motion Feature SORT algorithm

Multiple traffic entities detection and tracking from bird-view drone stationary videos https://engyasin.github.io/Offline_MOT/

Standalone ByteTrack in Python, extracted from official implementation with very few dependencies

Accepted for CVPR 2019 Tracking Challenge, workshop "4th BMTT MOTChallenge Workshop - How crowded can it get?"

People tracking in crowded locations using multiple object Tracking (MOT)

Simple implementation of multiple object tracking using Kalman filter and SSD Object detector

C++ implementation of SORT, a simple online and realtime tracking algorithm

[BMVC 2022] SearchTrack: Multiple Object Tracking with Object-Customized Search and Motion-Aware Features

Addition to multiple object tracker "Tracktor" from "Tracking without bells and whistles" paper.

Program for detection and tracking players on a sports ground and calculation of basic statistical indicators using deep learning

[ECCV'22 Oral] Towards Grand Unification of Object Tracking

The official code for our ECCV22 oral paper: tracking objects as pixel-wise distributions.

C++ implementation to Detect, track and classify multiple objects using LIDAR scans or point cloud

This repository contains the code used for ClusterTracker, a multiple object tracking method that is listed as "CTv0" in the MOT20 and HT21 challenges of https://motchallenge.net. ClusterTracker is described in the following paper: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4102945

Fast and accurate multiple-object tracking and segmentation on edge devices

Joint Detection and Embedding for fast multi-object tracking

Python package to label and track unique geospatial features from gridded datasets

A solution for NFL Health & Safety -- Helmet Assignment Kaggle, based on helmet mapping and multiple object tracking.

Contains implementation of multi-threaded object detection followed by tracking

Multiple Object Tracking using Graph Attention