中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 遥感图像处理团队
Non-Maximum Suppression Guided Label Assignment for Object Detection in Crowd Scenes

文献类型：期刊论文

作者Jiang, Hangzhi1,2; Zhang, Xin3; Xiang, Shiming1,2
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2024
卷号26页码:2207-2218
关键词Object detection Crowd scenes Label assignment Non-maximum suppression
ISSN号1520-9210
DOI10.1109/TMM.2023.3293333
通讯作者Xiang, Shiming(smxiang@nlpr.ia.ac.cn)
英文摘要The detection performance in crowd scenes is limited by recalling hard objects (e.g., occluded objects). It requires that this kind of objects can be successfully detected and retained by the non-maximum suppression (NMS) while controlling false positives. The existing dynamic label assignment algorithms can help recall these objects by adaptively allocating appropriate positive samples, however, they ignore the alignment with the selecting rules of NMS. This leads to the fact that detecting objects in crowd scenes are still very sensitive to the NMS threshold setting. As a result, the existing methods can only set a low NMS threshold to avoid the excessive false positives, causing some objects failed to be recalled. And these methods also generally lack more excitation for positive samples, which hinders further facilitating the recall of hard instances in crowd scenes. This article proposes a novel dynamic label assignment strategy for object detection in crowd scenes, called non-maximum suppression guided label assignment (NGLA), which aligns the assignment strategy with NMS process and learns more prominent positive samples. Following NMS, NGLA introduces the IoU between samples with their corresponding best samples to define positive and negative samples. To cooperate with NGLA, an NMS-aware loss is proposed to dynamically assign sample weights when supervising sample predictions, which also considers the IoU with the best sample. In addition, for better classification prediction, a regression assisted classification branch is designed to help detectors perceive the relation between the regression predictions of each sample and the corresponding best sample. Experiments demonstrate that NGLA outperforms other label assignment methods on CrowdHuman and Citypersons, and is less sensitive to the NMS threshold in crowd scenes.
WOS关键词PEDESTRIAN DETECTION ; PROPOSAL
资助项目National Key Research and Development Program of China
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:001168330100023
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China
源URL[http://ir.ia.ac.cn/handle/173211/58130]  
专题自动化研究所_模式识别国家重点实验室_遥感图像处理团队
通讯作者Xiang, Shiming
作者单位1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
3.Beijing Inst Technol, Sch Informat & Elect, Radar Res Lab, Beijing 100081, Peoples R China
推荐引用方式
GB/T 7714		 Jiang, Hangzhi,Zhang, Xin,Xiang, Shiming. Non-Maximum Suppression Guided Label Assignment for Object Detection in Crowd Scenes[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2024,26:2207-2218.
APA Jiang, Hangzhi,Zhang, Xin,&Xiang, Shiming.(2024).Non-Maximum Suppression Guided Label Assignment for Object Detection in Crowd Scenes.IEEE TRANSACTIONS ON MULTIMEDIA,26,2207-2218.
MLA Jiang, Hangzhi,et al."Non-Maximum Suppression Guided Label Assignment for Object Detection in Crowd Scenes".IEEE TRANSACTIONS ON MULTIMEDIA 26(2024):2207-2218.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。