ReIMOT: Rethinking and Improving Multi-object Tracking Based on JDE Approach

The multi-object tracking (MOT) algorithms of the joint detection and embedding (JDE) approach estimate bounding boxes and re-identification (re-ID) features of objects with the single network, which balance the tracking accuracy and inference speed. However, when the appearance information between...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI) s. 498 - 502
Hlavní autori: Hou, Haoxiong, Zhang, Ximing, Sun, Zhonghan, Gao, Wei
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 19.08.2022
Predmet:
Classification algorithms
coordinate attention
Feature extraction
Inference algorithms
Interference
joint detection and embedding
joint loss function
Measurement
multi-object tracking
Pattern recognition
re-identification
Task analysis
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The multi-object tracking (MOT) algorithms of the joint detection and embedding (JDE) approach estimate bounding boxes and re-identification (re-ID) features of objects with the single network, which balance the tracking accuracy and inference speed. However, when the appearance information between different objects is highly similar, these algorithms are usually easy to cause identity switches, and the comprehensive tracking performance is poor in crowded scenes. Aiming at the above problems, we propose a stronger multi-object tracking algorithm termed as ReIMOT, based on FairMOT. A joint loss function of combining normalized Softmax Loss and the center distance penalty term is designed to supervise the re-ID branch, which increases the intra-class similarity and makes the extracted appearance features more discriminative. To further improve the tracking performance, we introduce coordinate attention to make the encoder-decoder network focus more on features of interest. The experimental results show that the proposed ReIMOT is more effective than the other advanced multi-object tracking algorithms, and decreases the number of ID switches by 13.8% compared to FairMOT on the MOT17 dataset.
DOI:10.1109/PRAI55851.2022.9904121