Combining thermal histogram similarity with motion similarity improves ByteTrack and OCSORT MOT scores by about one to two MOTA points on a new RGB-thermal pedestrian dataset.
In:2023 IEEE/CVFConference onComputer Vision andPatternRecognition Title Suppressed Due to Excessive Length 15 Workshops (CVPRW)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Thermal MOT: A Novel Box Association Method Leveraging Thermal Identity and Motion Similarity
Combining thermal histogram similarity with motion similarity improves ByteTrack and OCSORT MOT scores by about one to two MOTA points on a new RGB-thermal pedestrian dataset.