The invention relates to the technical field of traffic detection, in particular to a deep learning non-motorized vehicle lane driving detection method based on an embedded terminal, which comprises the following steps: step 1, establishing a plurality of camera monitoring identification systems; step 2, creating an image set, and storing the image set into a basic database of each monitoring identification system; 3, comparing parameters; 4, storing the image frames of the illegal motor vehicle in sequence, and creating a new sub-image set; and step 5, uploading the data to a central database, integrating the central database, and expanding the central database. Whether a motor vehicle is on a non-motorized vehicle lane or not and whether the non-motorized vehicle runs forwards or backwards or not are marked and recorded, vehicles violating rules for multiple times are mainly marked, a central database is expanded, and the problem that due to the fact that most motor vehicle lanes andnon-motor vehicle lanes are parallel, the number of parameters of basic data is small, detection precision is not enough frequently, the detection speed is not high enough, and missed judgment is caused is solved.
本发明涉及交通检测技术领域,尤其为一种基于嵌入式终端的深度学习非机动车道行驶检测方法,包括:步骤一:建立多个摄像头监控识别系统;步骤二:创建图像集,图像集保存至各自监控识别系统的基础数据库内;步骤三:参数对比;步骤四:将违规机动车辆的图像帧按顺序保存并创建一个新的子图片集;步骤五:上传中央数据库,中央数据库进行整合,扩充中央数据库。本发明通过对机动车辆是否在非机动车道上和非机动车辆正行逆行进行标记记录,对多次违规的车辆进行重点标记,扩大中央数据库,解决了由于机动车道和非机动车道多是并行,致使基础数据的参数较少,时常导致检测精度不够,且检测速度不够快,导致漏判的情况发生。
Deep learning non-motorized vehicle lane driving detection method based on embedded terminal
一种基于嵌入式终端的深度学习非机动车道行驶检测方法
2020-09-08
Patent
Electronic Resource
Chinese
Non-motorized vehicle lane illegal parking prevention system
European Patent Office | 2021
|Energy-saving non-motorized vehicle lane anti-retrograde-running device
European Patent Office | 2020
|Tunnel non-motorized vehicle lane groove cover plate mounting device
European Patent Office | 2022
|Deep learning retrograde motion detection method based on embedded terminal
European Patent Office | 2021
|Automatic driving vehicle lane changing method based on double-layer deep reinforcement learning
European Patent Office | 2023
|