基于机器视觉的烟仓机器人路径识别与控制
|
摘要
仓库中醇化的烟叶因含有水分,在微生物作用下会发生霉变。为降低烟叶霉变检测的劳动强度,提高烟叶检测效率,我们基于机器视觉研发了一款搭载FLIR C3红外热成像检测仪的烟仓机器人。本研究主要介绍了烟仓机器人软硬件控制系统的设计,并对机器人行进路径的识别与控制进行研究。烟仓机器人的硬件控制系统采用32位ARM处理器STM32F103ZET6,利用OV2640传感器进行图像的采集与传输;软件控制系统基于Microsoft Visual Studio 2010开发环境,调用OpenCV等图像处理函数,实现图像分割、边缘检测及路径识别与规划。路径识别采用基于机器视觉的方法,利用高斯滤波去除图像中的噪音、干扰,经阈值化处理后采用Canny算子进行图像边缘检测处理,通过Hough变换,提取出车道的边缘线及车道中心线,根据车道中心线的角度偏差和像素偏差制定控制策略,从而实现烟仓机器人的自控行走,实际运行试验结果表明,该系统能够很好地实现路径识别和运动控制。本研究可为无线通讯和路径识别控制类机器人的相关设计研究提供参考。
The alcoholized tobacco leaves in the warehouse could mildew due to the presence of water. In order to reduce the labor intensity of tobacco leaf mold detection and improve the detection efficiency, we developed a cigarette warehouse robot equipped with FLIR C3 infrared thermal imaging detector based on machine vision. In this paper,the design of the software and hardware control system of the smoke bin robot was introduced, and the identification and control of the robot travel path were studied. The hardware control system adopted 32-bit ARM processor STM32 F103 ZET6, and used OV2640 sensor to collect and transmit images. The software control system was developed based on the Microsoft Visual Studio 2010 development environment, and called the image processing functions such as OpenCV to realize image segmentation, edge detection and path recognition and planning. Path recognition adopted a machine vision-based method, which used Gaussian filtering to remove noise and interference in the image. After thresholding, the Canny operator was used to detect the image edge, and the edge line and center line of the lane were extracted by Hough transform. According to the angular deviation of the lane centerline and the pixel deviation to develop a control strategy, the smoke bin robot achieved the self-controlled walking. The actual operation test results showed that the system could realize path recognition and motion control. This study could provide reference for the related design research of wireless communication and path recognition control robots.
The alcoholized tobacco leaves in the warehouse could mildew due to the presence of water. In order to reduce the labor intensity of tobacco leaf mold detection and improve the detection efficiency, we developed a cigarette warehouse robot equipped with FLIR C3 infrared thermal imaging detector based on machine vision. In this paper,the design of the software and hardware control system of the smoke bin robot was introduced, and the identification and control of the robot travel path were studied. The hardware control system adopted 32-bit ARM processor STM32 F103 ZET6, and used OV2640 sensor to collect and transmit images. The software control system was developed based on the Microsoft Visual Studio 2010 development environment, and called the image processing functions such as OpenCV to realize image segmentation, edge detection and path recognition and planning. Path recognition adopted a machine vision-based method, which used Gaussian filtering to remove noise and interference in the image. After thresholding, the Canny operator was used to detect the image edge, and the edge line and center line of the lane were extracted by Hough transform. According to the angular deviation of the lane centerline and the pixel deviation to develop a control strategy, the smoke bin robot achieved the self-controlled walking. The actual operation test results showed that the system could realize path recognition and motion control. This study could provide reference for the related design research of wireless communication and path recognition control robots.
引文
[1] David K. Muller Stored Product[M]. USA, 1998: 97-103.
[2] 金闻博.卷烟储运学(校内教材)[M] .合肥:中国科学技术大学,1998:25-40.
[3] Zou X J, Zou H X,Lu J, et al. Virtual manipulator-based binocular stereo vision positioning system and errors modeling [J]. Machine Vision and Aplications, 2012, 23(1):43-46.
[4] Atiya S, Hager G. Real-time vision-based robot localization [C]// Proceedings. IEEE International Conference on Robotics and Automation, 1991.
[5] 杨为民,李天石,贾鸿社,等.农业机械机器视觉导航研究[J]. 农业工程学报,2004,20(1): 160-165.
[6] 张磊,王书茂,陈兵旗,等.基于机器视觉的麦田边界检测[J].农业机械学报,2007,38(2):111-114.
[7] 张成涛,谭彧,吴刚,等.基于达芬奇平台的联合收获机视觉导航系统路径识别[J].农业机械学报,2012,43(增刊):271-276.
[8] 董靖川,张朝,温洋,等. 基于STM32的低碳避障实验小车电控设计[J].实验技术与管理, 2017,34(12): 45-49.
[9] 王辉,于立君,董泽全,等.基于STM32的循迹平衡小车实验教学平台研究[J].实验技术与管理,2017,34(5):136-139.
[10] 高杰.基于WIFI的无线视频监控硬件电路设计[J].电子测试,2017(1):22-23.
[11] 马捷,鄂金龙.基于近场通信的WiFi传输连接方案[J].计算机工程,2013(6):1-6.
[12] Thomas Valerrian Pasca Santhappa, Sumanta Patro,Bheemarjuna Reddy Tamma.Network coordination function for uplink traffic steering in tightly coupled LTE Wi-Fi networks[J]. Computer Networks,2017,127:296-316.
[13] Qi Hui, Li Qi. Implementation of LWIP TCP/IP protocol stack based on S1C33E07[M]//Wu Y W.Software Engineering and Knowledge Engineering: Theory and Practice.Springer Berlin-Heidelberg,2012:635-642.
[14] 龚正,沈建新. WIFI镜头机无线图像采集系统[J].计算机系统应用,2016,25(4):263-267.
[15] Ding X L, Zhao Q, Li Y B, et al. A real-time and effective object recognition and localization method[J].Applied Mechanics and Materials, 2014, 3372(615):82-87.
[16] 林开颜,吴军辉, 徐立鸿, 等.彩色图像分割方法综述[J].中国图象图形学报,2005,10(1):1-10.
[17] 丁文,李勃,陈启美.Canny色彩边缘检测及分类新方法[J].北京邮电大学学报,2012,35(1):115-119.
[18] 樊可霞,周一军,涂煊,等.基于OpenCV的社保卡号码识别算法的研究[J].信息技术,2014(3):175-178.
[19] 聂瑞柱.基于视觉的AGV路径跟踪技术研究[D].青岛:青岛科技大学,2015.
[20] 李天剑,王会香,黄民.基于机器视觉的仓储机器人控制方法研究[J].北京信息科技大学学报(自然科学版),2015,30(6):12-17.
[2] 金闻博.卷烟储运学(校内教材)[M] .合肥:中国科学技术大学,1998:25-40.
[3] Zou X J, Zou H X,Lu J, et al. Virtual manipulator-based binocular stereo vision positioning system and errors modeling [J]. Machine Vision and Aplications, 2012, 23(1):43-46.
[4] Atiya S, Hager G. Real-time vision-based robot localization [C]// Proceedings. IEEE International Conference on Robotics and Automation, 1991.
[5] 杨为民,李天石,贾鸿社,等.农业机械机器视觉导航研究[J]. 农业工程学报,2004,20(1): 160-165.
[6] 张磊,王书茂,陈兵旗,等.基于机器视觉的麦田边界检测[J].农业机械学报,2007,38(2):111-114.
[7] 张成涛,谭彧,吴刚,等.基于达芬奇平台的联合收获机视觉导航系统路径识别[J].农业机械学报,2012,43(增刊):271-276.
[8] 董靖川,张朝,温洋,等. 基于STM32的低碳避障实验小车电控设计[J].实验技术与管理, 2017,34(12): 45-49.
[9] 王辉,于立君,董泽全,等.基于STM32的循迹平衡小车实验教学平台研究[J].实验技术与管理,2017,34(5):136-139.
[10] 高杰.基于WIFI的无线视频监控硬件电路设计[J].电子测试,2017(1):22-23.
[11] 马捷,鄂金龙.基于近场通信的WiFi传输连接方案[J].计算机工程,2013(6):1-6.
[12] Thomas Valerrian Pasca Santhappa, Sumanta Patro,Bheemarjuna Reddy Tamma.Network coordination function for uplink traffic steering in tightly coupled LTE Wi-Fi networks[J]. Computer Networks,2017,127:296-316.
[13] Qi Hui, Li Qi. Implementation of LWIP TCP/IP protocol stack based on S1C33E07[M]//Wu Y W.Software Engineering and Knowledge Engineering: Theory and Practice.Springer Berlin-Heidelberg,2012:635-642.
[14] 龚正,沈建新. WIFI镜头机无线图像采集系统[J].计算机系统应用,2016,25(4):263-267.
[15] Ding X L, Zhao Q, Li Y B, et al. A real-time and effective object recognition and localization method[J].Applied Mechanics and Materials, 2014, 3372(615):82-87.
[16] 林开颜,吴军辉, 徐立鸿, 等.彩色图像分割方法综述[J].中国图象图形学报,2005,10(1):1-10.
[17] 丁文,李勃,陈启美.Canny色彩边缘检测及分类新方法[J].北京邮电大学学报,2012,35(1):115-119.
[18] 樊可霞,周一军,涂煊,等.基于OpenCV的社保卡号码识别算法的研究[J].信息技术,2014(3):175-178.
[19] 聂瑞柱.基于视觉的AGV路径跟踪技术研究[D].青岛:青岛科技大学,2015.
[20] 李天剑,王会香,黄民.基于机器视觉的仓储机器人控制方法研究[J].北京信息科技大学学报(自然科学版),2015,30(6):12-17.