SAMIDARE: Advanced Tracking-by-Segmentation for Dense Scenarios
Automated sports analysis demands robust multi-object tracking (MOT), yet segmentation-based methods often struggle with mask errors and ID switches in dense scenes. We propose SAMIDARE, a framework that enhances SAM2MOT for crowded scenes through three key components: (1) density-aware mask re-generation and (2) selective memory updates, both for adaptive mask control to preserve target feature integrity, and (3) state-aware association and new track initialization, which improves robustness under mutual occlusions and frequent frame-out events. Evaluated on the SportsMOT dataset, SAMIDARE achieves state-of-the-art performance, outperforming the baseline by 2.5 HOTA and 4.2 IDF1 points on the validation set. These results demonstrate that adaptive feature management using mask control and state-aware association provide a robust and efficient solution for dense sports tracking. Code is available at https://github.com/ZabuZabuZabu/SAMIDARE
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-Object TrackingSimilar Papers 제목 키워드 기반
DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM
SLAM systems based on NeRF have demonstrated superior performance in rendering quality and scene reconstruction for static environments compared to traditional dense SLAM. However, they encounter tracking drift and mappi…
Loop Closure DetectionNeRFOptical Flow EstimationSemantic SLAMPerSense: Personalized Instance Segmentation in Dense Images
Leveraging large-scale pre-training, vision foundational models showcase notable performance benefits. Recent segmentation algorithms for natural scenes have advanced significantly. However, existing models still struggl…
Instance SegmentationLanguage ModellingSegmentationSemantic SegmentationMulti-Granularity Video Object Segmentation
Current benchmarks for video segmentation are limited to annotating only salient objects (i.e., foreground instances). Despite their impressive architectural designs, previous works trained on these benchmarks have strug…
ObjectSegmentationSemantic SegmentationVideo Object Segmentation+2Direction-Aware Semi-Dense SLAM
To aide simultaneous localization and mapping (SLAM), future perception systems will incorporate forms of scene understanding. In a step towards fully integrated probabilistic geometric scene understanding, localization …
Scene UnderstandingSegmentationSimultaneous Localization and MappingDeep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art
Multi-object tracking (MOT) is a core task in computer vision that involves detecting objects in video frames and associating them across time. The rise of deep learning has significantly advanced MOT, particularly withi…
Deep LearningMulti-Object TrackingObject Tracking