[1]蔡志兆,吕建勋.基于Kinect的运动检测平台设计与实现[J].应用科技,2019,46(03):64-69.[doi:10.11991/yykj.201807011]
 CAI Zhizhao,LYU Jianxun.Design and implementation of motion detection platform based on Kinect[J].Applied science and technology,2019,46(03):64-69.[doi:10.11991/yykj.201807011]
点击复制

基于Kinect的运动检测平台设计与实现(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第46卷
期数:
2019年03期
页码:
64-69
栏目:
自动化技术
出版日期:
2019-04-29

文章信息/Info

Title:
Design and implementation of motion detection platform based on Kinect
作者:
蔡志兆 吕建勋
北京航空航天大学 自动化科学与电气工程学院, 北京 100191
Author(s):
CAI Zhizhao LYU Jianxun
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China
关键词:
运动检测Kinect传感器运动检测平台深度信息彩色信息边界检测单应性矩阵光流
Keywords:
motion detectionKinect sensormotion detection platformdepth informationcolor informationboundary detectionhomography matrixoptical flow
分类号:
TP391
DOI:
10.11991/yykj.201807011
文献标志码:
A
摘要:
现有的运动检测算法易受光照、阴影、复杂背景等因素影响,检测结果准确性欠佳,具有一定的局限性。基于此,设计了一种基于Kinect传感器的运动检测方法,可以完成室内场景的刚体运动检测。所设计的运动检测平台基于结合传感器所采集的深度信息和彩色信息,提升物体边界检测精度,提出基于单应性矩阵的刚体运动的密集光流估计方法。实验结果表明,基于Kinect的运动检测平台具有很好的检测效果,证明了运动平台的有效性。
Abstract:
Existing motion detection algorithms are susceptible to illumination, shadows, complex background and other factors, and the accuracy of the detection results is poor, which has certain limitations. Based on this, a Kinect sensor based motion detection method is designed, which can detect the rigid motion of indoor scenes. Based on the depth and color information collected by the sensor, the motion detection platform is designed to improve the detection precision of the object boundary. Finally, the dense optical flow estimation of rigid body motion based on the homography matrix is proposed. The experimental results show that the Kinect-based motion detection platform has a good detection effect, which proves effectiveness of the motion platform.

参考文献/References:

[1] 陆晨皓. 基于RGB-D的人体运动目标检测及其应用[D]. 成都:电子科技大学, 2015.
[2] LIU Fan, TANG Jinhui, ZHAO Ruizhen, et al. Abnormal behavior recognition system for ATM monitoring by RGB-D camera[C]//Proceedings of the 20th ACM International Conference on Multimedia. Nara, Japan:ACM, 2012:1295-1296.
[3] PARRA-DOMINGUEZ G S, TAATI B, MIHAILIDIS A. 3D human motion analysis to detect abnormal events on stairs[C]//Proceedings of the 20122nd International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission. Zurich, Switzerland:IEEE, 2012:97-103.
[4] 戴路, 张洁. 基于Kinect的体感交互式儿童安全教育平台设计[J]. 软件导刊, 2018, 17(8):144-148
[5] 贾浩东. 基于ROS平台的机器人目标识别系统的设计[J]. 电子测试, 2018(2):49-50, 59
[6] 赵运鹏, 张金学, 周文杰, 等. OpenCV视觉应用设计[J]. 福建电脑, 2018, 34(6):147-148
[7] 孙凯乐, 郭显久, 张烜, 等. 基于改进Canny算法的边缘检测[J]. 电脑编程技巧与维护, 2018(6):165-168, 173
[8] HAGGUI O, TADONKI C, LACASSAGNE L, et al. Harris corner detection on a NUMA manycore[J]. Future generation computer systems, 2018, 88:442-452.
[9] 陈伟杰, 孙作雷. 基于LK光流法的单目视觉里程计[J]. 微型机与应用, 2017, 36(21):45-47, 50
[10] 陈至坤, 李燊, 杜哲民. 基于光流法的移动机器人避障平衡策略的改进[J]. 华北理工大学学报(自然科学版), 2018, 40(2):88-92
[11] 商磊, 张宇, 李平. 基于密集光流的步态识别[J]. 大连理工大学学报, 2016, 56(2):214-220
[12] 林成忠, 张为, 王鑫, 等. 基于稠密光流和边缘特征的烟雾检测算法[J]. 计算机工程与科学, 2018, 40(7):1213-1220

相似文献/References:

[1]张宗彬.改进的混合高斯模型的运动对象分割算法[J].应用科技,2010,37(05):33.[doi:10.3969/j.issn.1009-671X.2010.05.008]
 ZHANG Zong-bin.A moving objects segmentation algorithm based on improved GMM[J].Applied science and technology,2010,37(03):33.[doi:10.3969/j.issn.1009-671X.2010.05.008]
[2]王祖龙,谢红.视频图像火焰区域分割算法[J].应用科技,2011,38(07):16.[doi:doi:10.3969/j.issn.1009-671X.2011.07.04]
 WANG Zulong,XIE Hong.Flame segmentation algorithm based on video image[J].Applied science and technology,2011,38(03):16.[doi:doi:10.3969/j.issn.1009-671X.2011.07.04]

备注/Memo

备注/Memo:
收稿日期:2018-07-31。
作者简介:蔡志兆,女,硕士研究生;吕建勋,男,讲师
通讯作者:蔡志兆,E-mail:czz_918@yeah.net
更新日期/Last Update: 2019-04-29