为实现自动高效获取农作物的生长图像，设计了1种适用于旱田作物的高通量履带式小车图像采集系统。系统采用磁导引传感器和磁条实现小车在田间按路径自动行走；采用履带式小车底盘结构以保证系统在田间复杂环境下能稳定运行；在小车支架两侧分别安装俯视和侧视相机，可同时采集2个作物行的俯视图和侧视图，以提高工作效率；运用无线通信技术远程监控小车运行情况；系统顶端安装太阳能电池板，为小车在运行时补充电能。以盆栽玉米植株为研究对象，用该系统采集了玉米幼苗期到抽穗期的植株图像，结果表明，该系统运行稳定可靠，在旱田以0.1 m/s速度作直线行驶时，绝对误差小于2 cm，最小转弯半径为0.5 m，连续采集模式下单个相机采集效率为30张/min，能满足实际需求。
A high throughput crawler car image acquisition suitable for dry field crops is designed to realize the growth image of crops automatically and efficiently. The system uses magnetic guidance sensor and magnetic stripe to realize the automatic walking of the car in the field according to the path,adopts crawler car chassis structure to ensure the stable operation of the system in the complex environment of the field. The overlooking and sideview cameras on both sides of the trolley bracket are installed to improve the work efficiency. The system uses wireless communication technology to monitor the operation of small cars remotely and the solar panel is installed at the top of the system to supply electric energy for small cars at run time. The images of maize plants from seedling period to tasseling stage were collected by this system. The results showed that the system was stable and reliable with the absolute error less than 2 cm in approximate straight line at 0.1 m/s speed and the minimum turning radius of 0.5 m. Single camera acquisition efficiency is 30 sheets per minute in continuous acquisition mode which can meet the actual needs. The system will provide a novel method for crop breeders to screen crop traits in the field.