吴庆甜,郭会文,吴新宇,贺涛.基于巡逻机器人的实时跑动检测系统[J].集成技术,2017,6(3):50-58
基于巡逻机器人的实时跑动检测系统
Real-Time Running Detection from a Patrol Robot
  
DOI:
中文关键词:  跑动检测;实时系统;巡逻机器人;光流
英文关键词:running detection; real-time detection; patrol robot; optical flow
基金项目:
作者单位
吴庆甜 中国科学院大学深圳先进技术学院 深圳 518055;中国科学院深圳先进技术研究院 深圳 518055 
郭会文 中国科学院大学深圳先进技术学院 深圳 518055;中国科学院深圳先进技术研究院 深圳 518055 
吴新宇 中国科学院大学深圳先进技术学院 深圳 518055;中国科学院深圳先进技术研究院 深圳 518055 
贺涛 五邑大学信息工程学院 江门 529020 
摘要点击次数: 130
全文下载次数: 119
中文摘要:
      文章提出了一种基于巡逻机器人系统的快速运动人体目标检测方法,采用卷积神经网络作为运动人体目标检测器,在不同摄像头视角和背景条件下,采集了不同姿态的跑动目标正负样本图像,完成 了卷积神经网络的训练。为区分前景目标的运动和机器人造成的背景运动,采用了光流特征来描述目标的运动情况并提取出感兴趣区域;为提高跑动目标的检测准确率,将跑动人物的表面特征和运动特征结合起来形成双流数据通道,并输入到卷积神经网络中进行识别。实验结果表明,该系统在室外环境下能够实现 85% 的跑动人体目标检测准确率,并达到 20 帧/秒检测速度。
英文摘要:
      In this paper, a real-time running targets detection method was investigated based on a patrol robot system. The convolutional neural network method was used as the classifier. Running targets with various poses under different camera viewpoints and backgrounds were collected for the training of the neural network. To discriminate the foreground target and the changing background caused by the robot motion, an optical flowbased method was applied. Optical flow of two successive frames taken by on-board camera was used to extract region of interest. To boost the detection efficiency and accuracy, both appearance and motion information of the target are used as input of the convolutional neural network. Experimental results show that under real outdoor scenarios, the detection accuracy can reach 85% with a running efficiency of 20 frames per second.
查看全文  查看/发表评论  下载PDF阅读器
关闭
微信关注二维码 用微信扫一扫

美女

美女图片

美女

美女图片