Abstract
This paper presents a new method of agriculture robot ground navigation reference point ranging based on binocular system. This method is applicable to the camera installation position at any angle and height, calibrating the agricultural robot binocular with the improve BP neural network and then the left and right image coordinates of the reference point can be obtained with the improved SIFT feature matching and the trained BP neural network saved during calibration is output, and then the world coordinates of the navigation reference point corresponding to the agricultural robot are output, and finally the horizontally straight line distance between the reference point and the robot body can be obtained. Experimental results show that in a certain field of view, the total time of field navigation reference point ranging is 55ms with the accuracy up to 99%, able to meet the operational requirements of the agricultural robot in most cases.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
