基于多通信机制与机器视觉的智慧小区视频监控系统
|
摘要
为了有效监控小区内的车辆速度,实现保障小区业主人身安全和促进城市小区健康发展,本文设计了一套基于多通信机制与机器视觉的智慧小区视频监控系统。首先,将基于Socket的网口通信与基于RS232的串口通信实施融合,连接测速摄像头与中心服务器,构建起智慧小区车辆视频监控系统的硬件平台。然后,结合高斯模型、Harris角点定位与RANSAC匹配优化方法,设计了车辆速度检测算子,实现车辆有无判断和车辆速度计算。在Visiual Studio平台开发系统,并对所提智慧小区视频监控系统进行了测试,结果表明:本文提出的智慧小区视频监控系统,在车速检测和系统智能性方面,都优于传统小区视频监控系统。
In order to effectively monitor the vehicle speed in the residential area, and realize the purpose of ensuring the personal safety in the residential area, as well as promote the healthy development of the urban residential area, this paper designs a smart residential area video monitoring system based on multi-communication mechanism and machine vision. Firstly, integrating socket-based network communication with RS232-based serial communication, connecting speed measuring camera and central server, the hardware foundation of vehicle video surveillance system of intelligent community is constructed. Then, combining the Gaussian model, Harris corner location and Ransac corner matching method, the vehicle speed detection operator is designed to realize the vehicle judgment and vehicle speed calculation. The system is developed on Visual studio platform, and the video surveillance system of intelligent community is tested, the output results show that this intelligent video surveillance system is superior to the traditional video surveillance system in speed detection and system intelligence.
In order to effectively monitor the vehicle speed in the residential area, and realize the purpose of ensuring the personal safety in the residential area, as well as promote the healthy development of the urban residential area, this paper designs a smart residential area video monitoring system based on multi-communication mechanism and machine vision. Firstly, integrating socket-based network communication with RS232-based serial communication, connecting speed measuring camera and central server, the hardware foundation of vehicle video surveillance system of intelligent community is constructed. Then, combining the Gaussian model, Harris corner location and Ransac corner matching method, the vehicle speed detection operator is designed to realize the vehicle judgment and vehicle speed calculation. The system is developed on Visual studio platform, and the video surveillance system of intelligent community is tested, the output results show that this intelligent video surveillance system is superior to the traditional video surveillance system in speed detection and system intelligence.
引文
[1]李娟.基于GPS的高速公路车速全程监控方法研究[J].测绘工程,2018,6(2):63-67.
[2]徐骏骅.基于边缘检测与模式识别的车脸识别算法[J].控制工程,2018,2(6):126-129.
[3]朱善玮.基于Haar-like和AdaBoost的车脸检测[J].电子科技,2018,11(5):58-63.
[4]黄山.基于无线数据通信及微机接口的单片机教学平台的研究[D].广州:华南理工大学,2018:52-54.
[5]陆翔莺.基于PCA算法的车脸识别系统研究[J].通讯世界,2018,27(3):1042-1045.
[6]马平华,徐晓光,夏雯娟.基于改进型Camshift和卡尔曼滤波器的车辆跟踪算法[J].井冈山大学学报:自然科学版,2015,36(5):60-65.
[7]张立亭,黄晓浪,鹿琳琳.基于灰度差分与模板的Harris角点检测快速算法[J].仪器仪表学报,2018,39(2):218-224.
[8]Wang Z C,Li R,Shao Z H.Adaptive Harris corner detection algorithm based on iterative threshold[J].Modern Physics Letters B,2017,31(15):1750181-1750189.
[9]刘三毛.基于RGB-D的室内场景SLAM方法研究[D].长沙:湖南工业大学,2017:21-39.
[10]Cheng L,Li M C,Liu Y X.Remote sensing image matching by integrating affine invariant feature extraction and RANSAC[J].Computers and Electrical Engineering,2012,38(4):1023-1032.
[2]徐骏骅.基于边缘检测与模式识别的车脸识别算法[J].控制工程,2018,2(6):126-129.
[3]朱善玮.基于Haar-like和AdaBoost的车脸检测[J].电子科技,2018,11(5):58-63.
[4]黄山.基于无线数据通信及微机接口的单片机教学平台的研究[D].广州:华南理工大学,2018:52-54.
[5]陆翔莺.基于PCA算法的车脸识别系统研究[J].通讯世界,2018,27(3):1042-1045.
[6]马平华,徐晓光,夏雯娟.基于改进型Camshift和卡尔曼滤波器的车辆跟踪算法[J].井冈山大学学报:自然科学版,2015,36(5):60-65.
[7]张立亭,黄晓浪,鹿琳琳.基于灰度差分与模板的Harris角点检测快速算法[J].仪器仪表学报,2018,39(2):218-224.
[8]Wang Z C,Li R,Shao Z H.Adaptive Harris corner detection algorithm based on iterative threshold[J].Modern Physics Letters B,2017,31(15):1750181-1750189.
[9]刘三毛.基于RGB-D的室内场景SLAM方法研究[D].长沙:湖南工业大学,2017:21-39.
[10]Cheng L,Li M C,Liu Y X.Remote sensing image matching by integrating affine invariant feature extraction and RANSAC[J].Computers and Electrical Engineering,2012,38(4):1023-1032.