基于单目线结构光的智能仓库车辆识别系统

为了实现钢铁企业智能仓库的车辆识别,提出通过基于机器视觉技术的智能仓库车辆识别方案。将面阵CCD相机及线结构光布置在车辆停车位上方拍摄车辆及结构光图像,首先通过张正友标定法及光平面空间原理完成相机与光平面标定;其次使用图像预处理算法及骨架法提取结构光光条中心线;然后通过引入车上、车下点的判别标准,精准识别车上边缘点,并引入车辆高度变量,得到车上边缘点由图像坐标向世界坐标的转化模型;最后根据车上3个边缘点坐标计算车辆位置信息,完成智能库区车辆方位识别。研究结果表明,所构建的测量系统及算法可以获取仓库车辆位置信息,通过标准件精度验证试验可知系统测量结果精确度较高,能够准确实时反映仓库车辆位置信息,这为智能仓库车辆位置检测提供了有效测量手段。

Intelligent warehouse vehicle detection system based on monocular structured light

In order to realize the vehicle detection of intelligent warehouse in iron and steel enterprise, a vehicle detection scheme of intelligent warehouse based on machine vision technology was proposed. The area array CCD camera and linear structured light were arranged above the vehicle parking space to capture the vehicle and structured light image. Firstly, the camera and light plane were calibrated by ZHANG Zheng-you calibration method and light plane space principle. Secondly, the image preprocessing algorithm and skeleton method were used to extract the center line of structured light strip. Thirdly, edge points on the vehicle were accurately identified by introducing the discrimination criteria of the point on and off the vehicle, and the vehicle height variable was introduced to obtain the transformation model of the edge point on the vehicle from the image coordinate to the world coordinate. Finally, the vehicle position information was calculated according to the coordinate of three edge points on the vehicle to complete the vehicle orientation recognition in the intelligent reservoir area. The research results show that the proposed measurement system and algorithm can obtain the location information of warehouse vehicles. Through the accuracy verification experiment of standard parts, the measurement results of the system have high accuracy and can accurately reflect the location information of warehouse vehicles in real time, which provides an effective measurement method for vehicle location detection in intelligent warehouse.