StrongSORT: Make DeepSORT Great Again

Overview

StrongSORT

StrongSORT: Make DeepSORT Great Again

MOTA-IDF1-HOTA

StrongSORT: Make DeepSORT Great Again

Yunhao Du, Yang Song, Bo Yang, Yanyun Zhao

arxiv 2202.13514

Abstract

Existing Multi-Object Tracking (MOT) methods can be roughly classified as tracking-by-detection and joint-detection-association paradigms. Although the latter has elicited more attention and demonstrates comparable performance relative to the former, we claim that the tracking-by-detection paradigm is still the optimal solution in terms of tracking accuracy. In this paper, we revisit the classic tracker DeepSORT and upgrade it from various aspects, i.e., detection, embedding and association. The resulting tracker, called StrongSORT, sets new HOTA and IDF1 records on MOT17 and MOT20. We also present two lightweight and plug-and-play algorithms to further refine the tracking results. Firstly, an appearance-free link model (AFLink) is proposed to associate short tracklets into complete trajectories. To the best of our knowledge, this is the first global link model without appearance information. Secondly, we propose Gaussian-smoothed interpolation (GSI) to compensate for missing detections. Instead of ignoring motion information like linear interpolation, GSI is based on the Gaussian process regression algorithm and can achieve more accurate localizations. Moreover, AFLink and GSI can be plugged into various trackers with a negligible extra computational cost (591.9 and 140.9 Hz, respectively, on MOT17). By integrating StrongSORT with the two algorithms, the final tracker StrongSORT++ ranks first on MOT17 and MOT20 in terms of HOTA and IDF1 metrics and surpasses the second-place one by 1.3 - 2.2. Code will be released soon.

vs. SOTA

comparison

Data&Model Preparation

  1. Download MOT17 & MOT20 from the official website.

    path_to_dataset/MOTChallenge
    ├── MOT17
    	│   ├── test
    	│   └── train
    └── MOT20
        ├── test
        └── train
    
  2. Download our prepared data

    path_to_dataspace
    ├── AFLink_epoch20.pth  # checkpoints for AFLink model
    ├── MOT17_ECC_test.json  # CMC model
    ├── MOT17_ECC_val.json  # CMC model
    ├── MOT17_test_YOLOX+BoT  # detections + features
    ├── MOT17_test_YOLOX+simpleCNN  # detections + features
    ├── MOT17_trainval_GT_for_AFLink  # GT to train and eval AFLink model
    ├── MOT17_val_GT_for_TrackEval  # GT to eval the tracking results.
    ├── MOT17_val_YOLOX+BoT  # detections + features
    ├── MOT17_val_YOLOX+simpleCNN  # detections + features
    ├── MOT20_ECC_test.json  # CMC model
    ├── MOT20_test_YOLOX+BoT  # detections + features
    ├── MOT20_test_YOLOX+simpleCNN  # detections + features
    
  3. Set the paths of your dataset and other files in "opts.py", i.e., root_dataset, path_AFLink, dir_save, dir_dets, path_ECC.

Requirements

  • Python3.6
  • torch 1.7.0 + torchvision 0.8.0

Tracking

  • Run DeepSORT on MOT17-val

    python strong_sort.py MOT17 val
  • Run StrongSORT on MOT17-val

    python strong_sort.py MOT17 val --BoT --ECC --NSA --EMA --MC --woC
  • Run StrongSORT++ on MOT17-val

    python strong_sort.py MOT17 val --BoT --ECC --NSA --EMA --MC --woC --AFLink --GSI
  • Run StrongSORT++ on MOT17-test

    python strong_sort.py MOT17 test --BoT --ECC --NSA --EMA --MC --woC --AFLink --GSI
  • Run StrongSORT++ on MOT20-test

    python strong_sort.py MOT20 val --BoT --ECC --NSA --EMA --MC --woC --AFLink --GSI

Note

  • To evaluate the tracking results, we recommend using the official code.
  • You can also try to apply AFLink and GSI to other trackers.
  • Tuning the hyperparameters carefully would brings better performance.

Citation

@misc{2202.13514,
Author = {Yunhao Du and Yang Song and Bo Yang and Yanyun Zhao},
Title = {StrongSORT: Make DeepSORT Great Again},
Year = {2022},
Eprint = {arXiv:2202.13514},
}

Acknowledgement

A large part of the codes, ideas and results are borrowed from DeepSORT, JDE, YOLOX and ByteTrack. Thanks for their excellent work!

This repo. is an implementation of ACFFNet, which is accepted for in Image and Vision Computing.

Attention-Guided-Contextual-Feature-Fusion-Network-for-Salient-Object-Detection This repo. is an implementation of ACFFNet, which is accepted for in I

5 Nov 21, 2022
RepVGG: Making VGG-style ConvNets Great Again

RepVGG: Making VGG-style ConvNets Great Again (PyTorch) This is a super simple ConvNet architecture that achieves over 80% top-1 accuracy on ImageNet

2.8k Jan 04, 2023
Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

Official code of APHYNITY Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting (ICLR 2021, Oral) Yuan Yin*, Vincent Le Guen*

Yuan Yin 24 Oct 24, 2022
Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers"

Recurrent Fast Weight Programmers This is the official repository containing the code we used to produce the experimental results reported in the pape

IDSIA 36 Nov 15, 2022
Pytorch based library to rank predicted bounding boxes using text/image user's prompts.

pytorch_clip_bbox: Implementation of the CLIP guided bbox ranking for Object Detection. Pytorch based library to rank predicted bounding boxes using t

Sergei Belousov 50 Nov 27, 2022
FedML: A Research Library and Benchmark for Federated Machine Learning

FedML: A Research Library and Benchmark for Federated Machine Learning 📄 https://arxiv.org/abs/2007.13518 News 2021-02-01 (Award): #NeurIPS 2020# Fed

FedML-AI 2.3k Jan 08, 2023
DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction (3DV 2021)

DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction (3DV 2021) This repo is the implementation of DPC. Tested environment Pyth

Dvir Ginzburg 30 Nov 30, 2022
The official repo of the CVPR2021 oral paper: Representative Batch Normalization with Feature Calibration

Representative Batch Normalization (RBN) with Feature Calibration The official implementation of the CVPR2021 oral paper: Representative Batch Normali

Open source projects of ShangHua-Gao 76 Nov 09, 2022
SGoLAM - Simultaneous Goal Localization and Mapping

SGoLAM - Simultaneous Goal Localization and Mapping PyTorch implementation of the MultiON runner-up entry, SGoLAM: Simultaneous Goal Localization and

10 Jan 05, 2023
The Ludii general game system, developed as part of the ERC-funded Digital Ludeme Project.

The Ludii General Game System Ludii is a general game system being developed as part of the ERC-funded Digital Ludeme Project (DLP). This repository h

Digital Ludeme Project 50 Jan 04, 2023
Object-aware Contrastive Learning for Debiased Scene Representation

Object-aware Contrastive Learning Official PyTorch implementation of "Object-aware Contrastive Learning for Debiased Scene Representation" by Sangwoo

43 Dec 14, 2022
My implementation of DeepMind's Perceiver

DeepMind Perceiver (in PyTorch) Disclaimer: This is not official and I'm not affiliated with DeepMind. My implementation of the Perceiver: General Per

Louis Arge 55 Dec 12, 2022
Parameterising Simulated Annealing for the Travelling Salesman Problem

Parameterising Simulated Annealing for the Travelling Salesman Problem

Gary Sun 55 Jun 15, 2022
Learning Generative Models of Textured 3D Meshes from Real-World Images, ICCV 2021

Learning Generative Models of Textured 3D Meshes from Real-World Images This is the reference implementation of "Learning Generative Models of Texture

Dario Pavllo 115 Jan 07, 2023
Public repository containing materials used for Feed Forward (FF) Neural Networks article.

Art041_NN_Feed_Forward Public repository containing materials used for Feed Forward (FF) Neural Networks article. -- Illustration of a very simple Fee

SolClover 2 Dec 29, 2021
Deep Crop Rotation

Deep Crop Rotation Paper (to come very soon!) We propose a deep learning approach to modelling both inter- and intra-annual patterns for parcel classi

Félix Quinton 5 Sep 23, 2022
Official implementation of Monocular Quasi-Dense 3D Object Tracking

Monocular Quasi-Dense 3D Object Tracking Monocular Quasi-Dense 3D Object Tracking (QD-3DT) is an online framework detects and tracks objects in 3D usi

Visual Intelligence and Systems Group 441 Dec 20, 2022
MusicYOLO framework uses the object detection model, YOLOx, to locate notes in the spectrogram.

MusicYOLO MusicYOLO framework uses the object detection model, YOLOX, to locate notes in the spectrogram. Its performance on the ISMIR2014 dataset, MI

Xianke Wang 2 Aug 02, 2022
PESTO: Switching Point based Dynamic and Relative Positional Encoding for Code-Mixed Languages

PESTO: Switching Point based Dynamic and Relative Positional Encoding for Code-Mixed Languages Abstract NLP applications for code-mixed (CM) or mix-li

Mohsin Ali, Mohammed 1 Nov 12, 2021
Project looking into use of autoencoder for semi-supervised learning and comparing data requirements compared to supervised learning.

Project looking into use of autoencoder for semi-supervised learning and comparing data requirements compared to supervised learning.

Tom-R.T.Kvalvaag 2 Dec 17, 2021