1. 毕业设计(论文)的内容和要求
(一)课题简介课题为实践课题,要求学生根据公共场合人体特定行为识别的需求,在了解视频监控系统的组成、原理与实现的基础上,实现视频动作检测与识别系统的接口和界面程序设计。
设计开发监控系统,实时检测并显示监控场景内的人体行为,并对出现或可能出现的室内人体特定动作(如械斗、用拳头打人、踢人、打耳光、争吵、强行拉拽、跌倒、抽搐、爬行、摔砸东西、敲打、抛物、点火、攀爬、翻越栏杆,选择其中的3-5种即可)进行识别。
课题需熟悉基于Python语言处理程序的设计,实现对人体特定动作的分割与展示,并进行动作识别。
2. 参考文献
[1].夏良正,数字图像处理(第二版),南京:东南大学出版社,2004.[2].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):35-47.[3]. 王志瑞,闫彩良.图像特征提取方法的综述[J].吉首大学学报,2011,32(5):44-47[4].王亮,胡卫明,谭铁牛.人运动的视觉分析综述[J].计算机学报,2002,25(3):225-237.[5]. S Xie, C Sun, Rethinking spatiotemporal feature learning: Speed-accuracy tradeoffs in video classification, European Conference on Computer Vision, 2018, pp. 305-321[6] Joao Carreira, Andrew Zisserman; Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6299-6308. [7]Vishwakarma, S., Agrawal, A. A survey on activity recognition and behavior understanding in video surveillance. Vis Comput 29, 9831009 (2013) [8]. Christoph Feichtenhofer, Axel Pinz, Andrew Zisserman; Convolutional Two-stream Network Fusion for Video Action Recognition. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1933-1941.[9]. J. Wang, W. Wang and W. Gao, "Multiscale Deep Alternative Neural Network for Large-Scale Video Classification," in IEEE Transactions on Multimedia, vol. 20, no. 10, pp. 2578-2592, Oct. 2018. doi: 10.1109/TMM.2018.2855081.
以上是毕业论文任务书,课题毕业论文、开题报告、外文翻译、程序设计、图纸设计等资料可联系客服协助查找。