《计算机应用研究》|Application Research of Computers

结合区域HOF和字典学习的人体行为识别方法

Human activity recognition method combined with region HOF and dictionary learning

免费全文下载 (已被下载 次)  
获取PDF全文
作者 王剑,李春雨,李跃新
机构 1.常熟理工学院 计算机科学与工程学院,江苏 常熟 215500;2.安阳工学院 计算机科学与信息工程学院,河南 安阳 455000;3.湖北大学 计算机与信息工程学院,武汉 430064
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)09-2863-04
DOI 10.3969/j.issn.1001-3695.2017.09.066
摘要 为辅助老人看护,提出一种基于视频的人体行为识别方法。采用AMBER方法检测视频中的运动目标,粗定位行为感兴趣区域;提取行为感兴趣区域各像素点的光流,构建归一化的光流方向直方图(histograms of oriented optical flow,HOF),用于描述人体行为;采用在线字典学习方法进行训练和测试,在训练阶段寻找最优的字典和稀疏矩阵,在测试阶段依据稀疏性分类不同特征。在国际上通用的ADL人体行为数据库中的仿真实验结果表明,采用本方法进行人体行为识别的识别率高,且不同人体行为之间的分类混淆率低。
关键词 行为识别;老人看护;光流方向直方图;字典学习;运动检测
基金项目 江苏省高校自然科学研究项目(12KJB520001)
湖北省重大科技支持项目(2014BAA089)
本文URL http://www.arocmag.com/article/01-2017-09-066.html
英文标题 Human activity recognition method combined with region HOF and dictionary learning
作者英文名 Wang Jian, Li Chunyu, Li Yuexin
机构英文名 1.SchoolofComputerScience&Engineering,ChangshuInstituteofTechnology,ChangshuJiangsu215500,China;2.CollegeofComputerScience&InformationEngineering,AnyangInstituteofTechnology,AnyangHenan455000,China;3.SchoolofComputerScience&InformationEngineering,HubeiUniversity,Wuhan430064,China
英文摘要 As a secondary care for the elderly, this paper proposed a new human activity recognition method based on video. First, it used AMBER method for detecting the moving objects in video, and located the activity region of interest roughly. Then, it extracted optical flow of each pixel in the activity region of interest, and built normalized histograms of oriented optical flow (HOF), which was used to describe human activities. Finally, it used online dictionary learning method for training and testing, to find the best dictionaries and sparse matrices during training phase, and classified different features according to sparsity during testing phase. The results of experiment on the international human activity dataset show that, recognize human activity by using the new method can achieve high recognition rate, and low category confusion rate between different human activities.
英文关键词 activity recognition; elderly care; histograms of oriented optical flow; dictionary learning; motion detection
参考文献 查看稿件参考文献
  [1] 张斌彪. 老人远程看护系统的设计和实现[D] . 长春:吉林大学, 2015.
[2] Courtemanche F, Ameur E, Dufresne A, et al. Activity recognition using eye-gaze movements and traditional interactions[J] . Interacting with Computers, 2011, 23(3):202-213.
[3] Anguita D, Ghio A, Oneto L, et al. Energy efficient smartphone-based activity recognition using fixed-point arithmetic[J] . Journal of Universal Computerence, 2013, 19(9):1295-1314.
[4] Gebre B G, Wittenburg P, Heskes T, et al. Motion history images for online speaker/signer diarization[C] //Proc of IEEE International Conference on Acoustics, Speech and Signal Processing. 2014:1537-1541.
[5] Glodek M, Bigalke L, Schels M, et al. Incorporating uncertainty in a layered HMM architecture for human activity recognition[C] // Proc of Joint ACM Workshop on Human Gesture and Behavior Understan-ding. New York:ACM Press, 2011:33-34.
[6] Hu Ninghang, Englebienne G, Krose B. A two-layered approach to recognize high-level human activities[C] //Proc of IEEE International Symposium on Robot and Human Interactive Communication. 2014:243-248.
[7] Zhang Xudong, Yang Jing, Hu Liangmei, et al. Human activity re-cognition using multi-layered motion history images with time-of-fligh(TOF) camera[J] . Journal of Electronics & Information Technology, 2014, 36(5):1139-1144.
[8] Aggarwal J K, Ryoo M S. Human activity analysis:a review[J] . ACM Computing Surveys, 2011, 43(3):194-218.
[9] 冯家更, 肖俊. 视点无关的行为识别综述[J] . 中国图象图形学报, 2013, 18(2):157-168.
[10] 单言虎, 张彰, 黄凯奇. 人的视觉行为识别研究回顾、现状及展望[J] . 计算机研究与发展, 2016, 53(1):93-112.
[11] 李瑞峰, 王亮亮, 王珂. 人体动作行为识别研究综述[J] . 模式识别与人工智能, 2014, 27(1):35-48.
[12] Messing R, Pal C, Kautz H. Activity recognition using the velocity histories of tracked keypoints[C] //Proc of IEEE International Conference on Computer Vision. 2009:104-111.
[13] Wang Jiang, Chen Zhuoyuan, Wu Ying. Action recognition with multiscale spatio-temporal contexts[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. 2011:3185-3192.
[14] Matikainen P, Hebert M, Sukthankar R. Representing pairwise spatial and temporal relations for action recognition[C] // Proc of the 11th European Conference on Computer Vision, Part I. Berlin:Sprin-ger-Verlag, 2010:508-521.
[15] Yuan Fei, Xia Guisong, Sahbi H, et al. Mid-level features and spatio-temporal context for activity recognition[J] . Pattern Recognition, 2012, 45(12):4182-4191.
[16] Wang Bin, Dudek P. AMBER:adapting multi-resolution background extractor[C] //Proc of IEEE International Conference on Image Processing. 2013:3417-3421.
[17] Hsu F C, Gubbi J, Palaniswami M. Human head detection using histograms of oriented optical flow in low quality videos with occlusion[C] //Proc of International Conference on Signal Processing and Communication Systems. 2013:1-6.
[18] Nusrat S, Remus B. Optimal filter estimation for Lucas-Kanade optical flow[J] . Sensors, 2012, 12(9):12694-12709.
[19] Sadeghi M, Babaie-Zadeh M, Jutten C. Dictionary learning for sparse representation:a novel approach[J] . IEEE Signal Processing Letters, 2013, 20(12):1195-1198.
收稿日期 2016/6/3
修回日期 2016/7/20
页码 2863-2866
中图分类号 TP391.41
文献标志码 A