Welcome to Smart Agriculture 中文

Smart Agriculture ›› 2020, Vol. 2 ›› Issue (4): 89-102.doi: 10.12133/j.smartag.2020.2.4.202010-SA002

• Special Issue--Agricultural Robot and Smart Equipment • Previous Articles     Next Articles

Visual Navigation System for Wheel-Type Grain Combine Harvester

DING Youchun1,2(), WANG Xuping1,2, PENG Jingye1,2, XIA Zhongzhou1,2   

  1. 1.College of Engineering, Huazhong Agricultural University, Wuhan 430070, China
    2.Key Laboratory of Agricultural Equipment in Mid-lower Yangtze River, Ministry of Agriculture and Rural Affairs, Wuhan 430070, China
  • Received:2020-10-14 Revised:2020-12-08 Online:2020-12-30
  • Supported by:
    National Key Research and Development Program of China (2017YFD0700400); Hubei Province Key Research and Development Program Project (2020BAB097)

Abstract:

Due to the short harvest period after grain ripening, the heavy of harvest tasks, the complicated operation of the combined harvester and the high driver's labor intensity, it is difficult to maintain the consistency of high cutting rate and cutting width of combined harvester. Based on computer vision, the combined harvester navigation method is being used to realize real-time control of the cut width of the combine harvester. To improve the working quality and efficiency of the wheel grain combine harvest, visual navigation control system was built in this research, it was composed of industrial camera, rear wheel angle measurement device, electro-hydraulic steering valve set, control box and notebook computer, etc. The industrial camera was mounted on the light frame of the front left turn of the combine harvester to capture the image information of the front field view of the harvester. The rear wheel angle measurement device was installed on the steering wheel bridge of the harvester, and the change and position of the rear wheel angle were fed back in real time. The steering cylinder was directly driven bypass connection way outside the electro-hydraulic steering valve set to make the rear wheel of the harvester turning. The control box integrated data acquisition card, power supply module, power amplifier, etc., for steering wheel control and steering wheel angle information measurement. As the main controller of the system, the notebook computer run the visual navigation software for image processing and deviation correction control, realized the automatic navigation process control of the combined harvester. Combined with OpenCV, a target path detection algorithm was designed to identify the boundary of harvested and non harvested paddy fields. After preprocessing, secondary edge segmentation and line detection, the forward-looking target path of visual navigation operation of combine harvester was obtained, and field dynamic calibration was carried out according to the relative position information of forward-looking path to obtain the full range harvesting status of combine harvester. A visual navigation tracking control method based on the front viewpoints was proposed in this research, through rectifying control implemented to maintain full cutting length at the same time prevent the leakage cut of crops, with full cut deviation, the front viewpoints pixel deviation and real-time steering rear corner as visual navigation controller input. The output steering wheel voltage was controlled according to the rectifying strategy. The results of paddy field experiments showed that the navigation system could basically realize the reliable acquisition of the position and the stable implementation of the target linear path tracking control. Under the condition that the field illumination conforming to the normal operation of human eyes, the detection accuracies of the image processing algorithm were higher than 96.28%, and the detection times of a single frame were less than 50 ms. Under the conditions that the nominal cutting width of the harvester was 2.56 m, the average full cutting width rate of visual navigation was 94.16%. Compared with the boundary of the first row, the straightness accuracy of the second row was increased by 44.92%. The research could provide technical support for the combine harvester to automatically navigate the operation of full cutting width.

Key words: visual navigation, combine harvester, tracking control, image processing, cutting length rate, front viewpoint

CLC Number: