Decode-MOT: How Can We Hurdle Frames to Go Beyond Tracking-by-Detection?
- 28 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 4378-4392
Abstract
The speed of tracking-by-detection (TBD) greatly depends on the number of running a detector because the detection is the most expensive operation in TBD. In many practical cases, multi-object tracking (MOT) can be, however, achieved based tracking-by-motion (TBM) only. This is a possible solution without much loss of MOT accuracy when the variations of object cardinality and motions are not much within consecutive frames. Therefore, the MOT problem can be transformed to find the best TBD and TBM mechanism. To achieve it, we propose a novel decision coordinator for MOT (Decode-MOT) which can determine the best TBD/TBM mechanism according to scene and tracking contexts. In specific, our Decode-MOT learns tracking and scene contextual similarities between frames. Because the contextual similarities can vary significantly according to the used trackers and tracking scenes, we learn the Decode-MOT via self-supervision. The evaluation results on MOT challenge datasets prove that our method can boost the tracking speed greatly while keeping the state-of-the-art MOT accuracy. Our code will be available at https://github.com/reussite-cv/Decode-MOT.Keywords
Funding Information
- National Research Foundation of Korea (NRF-2022R1C1C1009208)
- Institute of Information and communications Technology Planning and evaluation (IITP) (2022-0-00448)
- IITP (RS-2022-00155915)
- Basic Science Research Program through the NRF (2022R1A6A1A03051705)
This publication has 69 references indexed in Scilit:
- Person Re-identification in the Wild2017
- CityPersons: A Diverse Dataset for Pedestrian Detection2017
- Deep Feature Flow for Video Recognition2017
- Online Multi-target Tracking with Strong and Weak Detections2016
- Simple online and realtime tracking2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- FlowNet: Learning Optical Flow with Convolutional Networks2015
- Evaluating Multiple Object Tracking Performance: The CLEAR MOT MetricsEURASIP Journal on Image and Video Processing, 2008
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955