计算机应用 ›› 2019, Vol. 39 ›› Issue (8): 2475-2479.DOI: 10.11772/j.issn.1001-9081.2019010232

• 应用前沿、交叉与综合 • 上一篇    下一篇

基于MobileNet的移动端城管案件目标识别算法

杨辉华1,2, 张天宇3, 李灵巧1,2, 潘细朋2   

  1. 1. 桂林电子科技大学 计算机与信息安全学院, 广西 桂林 541004;
    2. 北京邮电大学 自动化学院, 北京 100876;
    3. 桂林电子科技大学 电子工程与自动化学院, 广西 桂林 541004
  • 收稿日期:2019-02-13 修回日期:2019-03-15 出版日期:2019-08-10 发布日期:2019-04-15
  • 通讯作者: 张天宇
  • 作者简介:杨辉华(1972-),男,湖南常德人,教授,博士生导师,博士,主要研究方向:智能信息处理、机器学习;张天宇(1992-),男,江苏南京人,硕士研究生,主要研究方向:机器学习、模式识别;李灵巧(1985-),男,四川达州人,博士研究生,主要研究方向:机器学习;潘细朋(1985-),男,江西宜春人,博士研究生,主要研究方向:机器学习、计算机视觉。
  • 基金资助:
    国家自然科学基金资助项目(61471191,61501233,61071163)。

Target recognition algorithm for urban management cases by mobile devices based on MobileNet

YANG Huihua1,2, ZHANG Tianyu3, LI Lingqiao1,2, PAN Xipeng2   

  1. 1. School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin Guangxi 541004, China;
    2. School of Automation, Beijing University of Posts and Telecommunications, Beijing 100876, China;
    3. School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin Guangxi 541004, China
  • Received:2019-02-13 Revised:2019-03-15 Online:2019-08-10 Published:2019-04-15
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61471191, 61501233,61071163).

摘要: 针对目前大量安装的固定监控摄像头存在监控死角,以及移动设备硬件性能较低等问题,提出一种可在较低性能的IOS移动设备上运行的城市管理案件目标识别算法。首先,在MobileNet中增加新的超参数,优化输入输出图像的通道数与每个通道所产生的特征图数量;随后,将改进后的MobileNet与SSD目标识别框架相结合构成一种新的识别算法,并移植到IOS移动端设备上;最后,该算法利用移动端设备自带的摄像头拍摄案发现场视频,实现对8种特定城管案件目标的准确检测。该算法检测结果的平均精度均值(mAP)与原型YOLO和原型SSD相比,分别提升了15.5个百分点和10.4个百分点。实验结果表明,所提算法可以在低性能IOS移动设备上流畅运行,减少了监控死角,为城管队员加速案件分类与处理提供了技术支撑。

关键词: 智慧城管, 目标识别, MobileNet, 移动设备, 视频监控

Abstract: For the monitoring dead angles of fixed surveillance cameras installed in large quantities and low hardware performance of mobile devices, an urban management case target recognition algorithm that can run on IOS mobile devices with low performance was proposed. Firstly, the number of channels of input and output images and the number of feature maps generated by each channel were optimized by adding new hyperparameters to MobileNet. Secondly, a new recognition algorithm was formed by combining the improved MobileNet with the SSD recognition framework and was transplanted to the IOS mobile devices. Finally, the accurate detection of the common 8 specific urban management case targets was achieved by the proposed algorithm, in which the camera provided by the mobile device was used to capture the scene video. The mean Average Precision (mAP) of the proposed algorithm was 15.5 percentage points and 10.4 percentage points higher than that of the prototype YOLO and the prototype SSD, respectively. Experimental results show that the proposed algorithm can run smoothly on low-performance IOS mobile devices, reduce the dead angles of monitoring, and provide technical support for urban management team to speed up the classification and processing of cases.

Key words: intelligent urban management, target recognition, MobileNet, mobile device, video surveillance

中图分类号: