Paper Reading AI Learner

Occlusion-Aware SORT: Observing Occlusion for Robust Multi-Object Tracking

2026-03-06 08:40:07
Chunjiang Li, Jianbo Ma, Li Shen, Yanru Chen, Liangyin Chen

Abstract

Multi-object tracking (MOT) involves analyzing object trajectories and counting the number of objects in video sequences. However, 2D MOT faces challenges due to positional cost confusion arising from partial occlusion. To address this issue, we present the novel Occlusion-Aware SORT (OA-SORT) framework, a plug-and-play and training-free framework that includes the Occlusion-Aware Module (OAM), the Occlusion-Aware Offset (OAO), and the Bias-Aware Momentum (BAM). Specifically, OAM analyzes the occlusion status of objects, where a Gaussian Map (GM) is introduced to reduce background influence. In contrast, OAO and BAM leverage the OAM-described occlusion status to mitigate cost confusion and suppress estimation instability. Comprehensive evaluations on the DanceTrack, SportsMOT, and MOT17 datasets demonstrate the importance of occlusion handling in MOT. On the DanceTrack test set, OA-SORT achieves 63.1% and 64.2% in HOTA and IDF1, respectively. Furthermore, integrating the Occlusion-Aware framework into the four additional trackers improves HOTA and IDF1 by an average of 2.08% and 3.05%, demonstrating the reusability of the occlusion awareness.

Abstract (translated)

多目标跟踪(MOT)涉及分析对象轨迹并统计视频序列中的对象数量。然而,二维 MOT 面临着由于部分遮挡导致的位置成本混淆的挑战。为了解决这一问题,我们提出了一个新的 Occlusion-Aware SORT (OA-SORT) 框架,这是一个即插即用且无需训练的框架,包括了 Occlusion-Aware Module(OAM)、Occlusion-Aware Offset(OAO)和 Bias-Aware Momentum(BAM)。具体来说,OAM 分析对象的遮挡状态,在这里引入了一个高斯图(GM),以减少背景的影响。相对地,OAO 和 BAM 利用 OAM 描述的遮挡状态来缓解成本混淆并抑制估计不稳定。 在 DanceTrack、SportsMOT 以及 MOT17 数据集上进行的全面评估显示了处理遮挡在 MOT 中的重要性。在 DanceTrack 测试集中,OA-SORT 在 HOTA(Hit Rate-Orientation Accuracy)和 IDF1(Inverse Detection Fraction Overlap @ 1)两个指标中分别取得了63.1% 和 64.2% 的成绩。此外,将 Occlusion-Aware 框架整合到四个额外的跟踪器中后,HOTA 和 IDF1 平均提高了 2.08% 和 3.05%,这证明了对遮挡感知重用性的认可。

URL

https://arxiv.org/abs/2603.06034

PDF

https://arxiv.org/pdf/2603.06034.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot