SIA OpenIR  > 机器人学研究室
融合人群密度的自适应深度多目标跟踪算法
Alternative TitleAdaptive Deep Multi-object Tracking Algorithm Fusing Crowd Density
刘金文1,2,3; 任卫红4; 田建东1,2
Department机器人学研究室
Source Publication模式识别与人工智能
ISSN1003-6059
2021
Volume34Issue:5Pages:385-397
Indexed ByEI
EI Accession number20212610549784
Contribution Rank1
Funding Organization国家自然科学基金项目(No.U2013210, 61821005)
Keyword多目标跟踪 人群密度图 行人重识别 三元组损失
Abstract

多目标跟踪技术不能较好地解决目标严重遮挡场景下的多目标跟踪问题,因此文中提出融合人群密度的自适应深度多目标跟踪算法.首先,融合人群密度图和目标检测结果,利用人群密度图的位置和计数信息修正检测器结果,消除漏检、误检.然后,使用自适应三元组损失改进行人重识别模型的损失函数,提高对重识别特征的辨别能力.最后,使用外观和运动信息进行目标关联,得到最终的跟踪结果.实验验证文中算法可有效解决目标严重遮挡场景下的多目标跟踪问题.

Other Abstract

Multi-object tracking technology cannot well solve the problem of multi-object tracking in the scenarios with objects severely occluded, and therefore an adaptive deep multi-object tracking algorithm fusing crowd density is proposed. Firstly, the crowd density maps and object detection results are fused, and the location and the count information of crowd density maps are utilized to correct the detector results to eliminate missing and false detections. Then, adaptive triplet loss is employed to improve the loss function of the re-identification model and thus the discrimination of the algorithm for the re-identification feature is enhanced. Finally, final tracking results are obtained using the appearance and motion information for objects association. It is verified through the experiments that the proposed algorithm effectively solves the problem of multi-object tracking in severely occluded scenes.

Language中文
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/29184
Collection机器人学研究室
Corresponding Author田建东
Affiliation1.中国科学院沈阳自动化研究所 机器人学研究室
2.中国科学院机器人与智能制造创新研究院
3.中国科学院大学 计算机科学与技术学院
4.哈尔滨工业大学(深圳) 机电工程与自动化学院
Recommended Citation
GB/T 7714
刘金文,任卫红,田建东. 融合人群密度的自适应深度多目标跟踪算法[J]. 模式识别与人工智能,2021,34(5):385-397.
APA 刘金文,任卫红,&田建东.(2021).融合人群密度的自适应深度多目标跟踪算法.模式识别与人工智能,34(5),385-397.
MLA 刘金文,et al."融合人群密度的自适应深度多目标跟踪算法".模式识别与人工智能 34.5(2021):385-397.
Files in This Item:
File Name/Size DocType Version Access License
融合人群密度的自适应深度多目标跟踪算法.(8529KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[刘金文]'s Articles
[任卫红]'s Articles
[田建东]'s Articles
Baidu academic
Similar articles in Baidu academic
[刘金文]'s Articles
[任卫红]'s Articles
[田建东]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[刘金文]'s Articles
[任卫红]'s Articles
[田建东]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 融合人群密度的自适应深度多目标跟踪算法.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.