摘要
针对目前市面上的清洁车容易因为驾驶员的疏忽造成清扫盘与路沿的碰撞,加速清扫盘的损坏,洒水作业容易波及路人,贴地工作的吸盘容易与减速带碰撞造成损失,不能自动根据垃圾量调节清扫功率等问题,提出了一种清洁车智能监测和控制系统;该系统采用超声测距模块避免碰撞,运用YOLOv4算法检测行人和减速带,使用VGG16网络进行垃圾量化进而调节清扫功率,通过CAN通信模块实现对清洁车设备的实时控制;该系统采用多线程实现多任务算法之间的协调与通信;行车实验表明,该系统的整体运行速度为每秒6~7帧,满足实时性;路沿距离检测及避障算法准确率为96%,垃圾量化算法准确率为90%,行人和减速带算法准确率为96.25%,准确率较高,能够有效提高清扫效率,降低设备损耗,提高行车安全。
Aiming at the problem that the cleaning vehicle on market is easy to collide with the roadside due to the negligence of driver,the cleaning plate is easy to accelerate the damage,the watering operation is easy to affect passers,the suction cup working close to the ground is easy to collide with the deceleration belt,resulting in losses,and the cleaning power can not be automatically adjusted according to the amount of garbage,an intelligent monitoring and control system for the cleaning vehicle is proposed.The system uses ultrasonic ranging module to avoid collision,YOLOv4 algorithm is used to detect pedestrians and speed bumps,VGG16 network is used to quantify garbage and adjust cleaning power,and the real-time control of cleaning vehicle equipment is realized through Controller Area Network(CAN)communication module.The system realizes the coordination and communication between multitasking algorithms through multithreading.The driving experiment shows that the overall running speed of the system is 6-7 frames per second,which meets the real-time performance.The accuracy of roadside distance detection and obstacle avoidance algorithm is up to 96%,the accuracy of garbage quantification algorithm is up to 90%,and the accuracy of pedestrian and deceleration belt algorithm is up to 96.25%.The accuracy of the system is relatively high,which can effectively improve the cleaning efficiency,reduce the loss of equipment and improve the safety of driving.
作者
熊文军
赵山虎
李世博
杨建华
范孝波
孙洪良
陈军
XIONG Wenjun;ZHAO Shanhu;LI Shibo;YANG Jianhua;FAN Xiaobo;SUN Hongliang;CHEN Jun(School of Automation,Northwestern Polytechnical University,Xi'an 710000,China;Special Vehicle Research Institute,Jiangsu Yueda Special Car Co.,Ltd.,Yancheng 224000,China)
出处
《计算机测量与控制》
2022年第5期109-114,共6页
Computer Measurement &Control
基金
西北工业大学横向项目(2019ME090021)。
作者简介
熊文军(1995-),男,云南大理人,硕士生,主要从事图像处理方向的研究;杨建华(1967-),女,山西长治人,博士生导师,教授,主要从事新型传感器、集成测试技术与工业图像处理方向的研究。
