Suppr超能文献

基于视频序列中的粒子滤波器的多行人跟踪算法。

Tracking Algorithm of Multiple Pedestrians Based on Particle Filters in Video Sequences.

机构信息

School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266000, China.

出版信息

Comput Intell Neurosci. 2016;2016:8163878. doi: 10.1155/2016/8163878. Epub 2016 Oct 25.

Abstract

Pedestrian tracking is a critical problem in the field of computer vision. Particle filters have been proven to be very useful in pedestrian tracking for nonlinear and non-Gaussian estimation problems. However, pedestrian tracking in complex environment is still facing many problems due to changes of pedestrian postures and scale, moving background, mutual occlusion, and presence of pedestrian. To surmount these difficulties, this paper presents tracking algorithm of multiple pedestrians based on particle filters in video sequences. The algorithm acquires confidence value of the object and the background through extracting a priori knowledge thus to achieve multipedestrian detection; it adopts color and texture features into particle filter to get better observation results and then automatically adjusts weight value of each feature according to current tracking environment. During the process of tracking, the algorithm processes severe occlusion condition to prevent drift and loss phenomena caused by object occlusion and associates detection results with particle state to propose discriminated method for object disappearance and emergence thus to achieve robust tracking of multiple pedestrians. Experimental verification and analysis in video sequences demonstrate that proposed algorithm improves the tracking performance and has better tracking results.

摘要

行人跟踪是计算机视觉领域的一个关键问题。粒子滤波器已被证明在非线性和非高斯估计问题的行人跟踪中非常有用。然而,由于行人姿态和尺度的变化、运动背景、相互遮挡和行人的存在,复杂环境中的行人跟踪仍然面临许多问题。为了克服这些困难,本文提出了一种基于视频序列中粒子滤波器的多行人跟踪算法。该算法通过提取先验知识来获取目标和背景的置信值,从而实现多行人检测;它将颜色和纹理特征引入粒子滤波器,以获得更好的观测结果,然后根据当前跟踪环境自动调整每个特征的权重值。在跟踪过程中,该算法处理严重的遮挡情况,以防止由于物体遮挡而导致的漂移和丢失现象,并将检测结果与粒子状态相关联,提出了一种用于区分物体消失和出现的方法,从而实现了多行人的鲁棒跟踪。在视频序列中的实验验证和分析表明,所提出的算法提高了跟踪性能,具有更好的跟踪结果。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c1fe/5101411/6396d3736fe0/CIN2016-8163878.001.jpg

相似文献

1
Tracking Algorithm of Multiple Pedestrians Based on Particle Filters in Video Sequences.
Comput Intell Neurosci. 2016;2016:8163878. doi: 10.1155/2016/8163878. Epub 2016 Oct 25.
2
A Boosted Multi-Task Model for Pedestrian Detection With Occlusion Handling.
IEEE Trans Image Process. 2015 Dec;24(12):5619-29. doi: 10.1109/TIP.2015.2483376. Epub 2015 Sep 28.
3
Nonlinear dynamic model for visual object tracking on Grassmann manifolds with partial occlusion handling.
IEEE Trans Cybern. 2013 Dec;43(6):2005-19. doi: 10.1109/TSMCB.2013.2237900.
4
Robust multiperson tracking from a mobile platform.
IEEE Trans Pattern Anal Mach Intell. 2009 Oct;31(10):1831-46. doi: 10.1109/TPAMI.2009.109.
6
Tracking pedestrians using local spatio-temporal motion patterns in extremely crowded scenes.
IEEE Trans Pattern Anal Mach Intell. 2012 May;34(5):987-1002. doi: 10.1109/TPAMI.2011.173.
7
Video analysis of Hammersmith lateral tilting examination using Kalman filter guided multi-path tracking.
Med Biol Eng Comput. 2014 Sep;52(9):759-72. doi: 10.1007/s11517-014-1178-2. Epub 2014 Aug 6.
8
An anti-occlusion optimization algorithm for multiple pedestrian tracking.
PLoS One. 2024 Jan 31;19(1):e0291538. doi: 10.1371/journal.pone.0291538. eCollection 2024.
9
Tracking Multiple Video Targets with an Improved GM-PHD Tracker.
Sensors (Basel). 2015 Dec 3;15(12):30240-60. doi: 10.3390/s151229794.
10
Research on Athlete Detection Method Based on Visual Image and Artificial Intelligence System.
Comput Intell Neurosci. 2022 Sep 29;2022:2418367. doi: 10.1155/2022/2418367. eCollection 2022.

本文引用的文献

1
Robust superpixel tracking.
IEEE Trans Image Process. 2014 Apr;23(4):1639-51. doi: 10.1109/TIP.2014.2300823.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验