[1]马皇特,贺永杰,王春梅,等.基于无人机视觉的人体检测跟踪技术研究[J].计算机技术与发展,2018,28(10):115-118.[doi:10.3969/ j. issn.1673-629X.2018.10.024]
 MA Huang-te,HE Yong-jie,WANG Chun-mei,et al.Research on Human Detection and Tracking Technology Based on UAV Vision[J].,2018,28(10):115-118.[doi:10.3969/ j. issn.1673-629X.2018.10.024]
点击复制

基于无人机视觉的人体检测跟踪技术研究()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年10期
页码:
115-118
栏目:
智能、算法、系统工程
出版日期:
2018-10-10

文章信息/Info

Title:
Research on Human Detection and Tracking Technology Based on UAV Vision
文章编号:
1673-629X(2018)10-0115-04
作者:
马皇特贺永杰王春梅禹密柱王江安
长安大学 信息工程学院,陕西 西安 710064
Author(s):
MA Huang-teHE Yong-jieWANG Chun-meiYU Mi-zhuWANG Jiang-an
School of Information Engineering,Chang’an University,Xi’an 710064,China
关键词:
移动平台人体检测人体跟踪模板匹配实时
Keywords:
mobile platformhuman detectionhuman trackingtemplate matchingreal-time
分类号:
TP391
DOI:
10.3969/ j. issn.1673-629X.2018.10.024
文献标志码:
A
摘要:
由于运动人体的随意性、姿态的多样性、人体服饰的差异性,加之可能存在的遮挡等问题,使人体检测存在着一定的难度和挑战。 针对固定摄像机监控系统对移动行人检测的局限性问题,对基于空中移动平台小型四旋翼无人机的目标人体检测和跟踪进行了研究。 在人体检测方面,利用主成分分析法(PCA)降维后的方向梯度直方图(HOG)特征,由于人体的头肩部在行人运动过程中具有良好的不变性,结合头部和肩部的模板匹配算法,提高了人体检测的准确性。 在人体跟踪方面,采用连续自适应的均值漂移算法(CamShift)进行跟踪,当人体被完全遮挡时,容易出现在跟踪过程中丢失目标的情况。 利用连续自适应的均值漂移算法与粒子滤波算法相结合,提高了算法的跟踪效果。 实验结果表明,人体检测和跟踪具有良好的效果,并且能够满足实时的要求。
Abstract:
Due to the diversity of human movement posture,the different clothes,and the problem of occlusion,there is a certain difficulty and challenge on human body detection. Aiming at the limitations of the fixed camera monitoring system for moving pedestrian detection,we carry on the research on the detection and tracking of the target human body of the small four-rotor unmanned aerial vehicle (UAV) under the air moving platform. In the human body detection,we use the HOG feature after dimension reduction by PCA to improve the accuracy of human detection in combination with the head and shoulders template matching algorithm because of the better invariance for the human head and shoulders during the pedestrian movement. In the human tracking,we adopt CamShift algorithm for tracking. But when the human body is completely blocked,it is easy to appear in the tracking process to lose the target situation. And the CamShift algorithm combined with particle filter algorithm can improve the tracking effect of the algorithm. The experiment shows that the human body detection and tracking algorithm has excellent detection and tracking effect,and can meet the real-time requirements.

相似文献/References:

[1]徐志成 焦阳 朱怀宏.一种基于Windows Mobile的医疗辅助系统[J].计算机技术与发展,2006,(01):147.
 XU Zhi-cheng,JIAO Yang,ZHU Huai-hong.Windows Mobile Based Medical Treatment System[J].,2006,(10):147.
[2]张虎 方贤勇 吴忠标.基于多尺度细胞局部二值模式的人体检测[J].计算机技术与发展,2012,(07):52.
 ZHANG Hu,FANG Xian-yong,WU Zhong-biao.Human Detection Based on Multi-scale Cell Structured Local Binary Pattern[J].,2012,(10):52.
[3]宋燕燕,曹效业,周灵. 移动增强现实技术在互动展示中的应用研究[J].计算机技术与发展,2016,26(09):83.
 SONG Yan-yan,CAO Xiao-ye,ZHOU Ling. Research on Application of Mobile AR Technology in Product Interaction Exhibition[J].,2016,26(10):83.
[4]戴彦群.智慧管网系统的设计与实现[J].计算机技术与发展,2019,29(11):206.[doi:10. 3969 / j. issn. 1673-629X. 2019. 11. 041]
 DAI Yan-qun.Design and Implementation of Smart Pipe Network System[J].,2019,29(10):206.[doi:10. 3969 / j. issn. 1673-629X. 2019. 11. 041]
[5]王 蓉,吕祖盛,孙 嘉,等.基于人像分割的智能搜救无人机系统设计[J].计算机技术与发展,2020,30(08):147.[doi:10. 3969 / j. issn. 1673-629X. 2020. 08. 025]
 WANG Rong,LYU Zu-sheng,SUN Jia,et al.Design of Intelligent Rescue UAV System Based on Portrait Segmentation[J].,2020,30(10):147.[doi:10. 3969 / j. issn. 1673-629X. 2020. 08. 025]
[6]于 翔,周 波.基于多模态融合的室内人体跟踪技术研究[J].计算机技术与发展,2023,33(02):38.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 006]
 YU Xiang,ZHOU Bo.Research on Indoor Human Tracking Technology Based on Multi-modal Fusion[J].,2023,33(10):38.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 006]

更新日期/Last Update: 2018-10-10