Research on Position Estimation Method of Intelligent Forklift Based on Binocular Vision

This paper proposes a method for calculating the relative angle of intelligent forklift and shelf based on binocular vision for intelligent warehousing system. This paper completes the calibration, stereo rectification, stereo matching and three-dimensional reconstruction of the binocular system. It deduces the binocular vision model in detail, and converts the calculation to the image pixel coordinate system, and directly performs the three-dimensional reconstruction from the pixel coordinate system. Project part of the point cloud on the shelf vertically to the ground, and then use the RANSAC algorithm to fit a straight line. According to the slope of the fitted straight line, the angle of the shelf plane relative to the camera imaging plane is calculated to obtain the relative angle of the shelf and the forklift. Experimental results show that the proposed algorithm is feasible and has high accuracy. And this algorithm can meet the requirements of calculating the relative angle of forklift and shelf.