Harvester visual navigation method and system based on improved Segnet image segmentation

The invention discloses a harvester visual navigation method and system based on improved Segnet image segmentation. The method comprises the following steps: (1) collecting a to-be-segmented field crop image for preprocessing; (2) performing semantic segmentation on the obtained field crop image by using an improved Segnet model to generate a target feature map, wherein the improved Segnet model refers to the fact that a ShuffleNetV2 network is used as an encoder part in the Segnet model; (3) acquiring boundary pixel points and position information of a target in the feature map by using an edge detection algorithm; and (4) taking the obtained boundary pixel points and position information as the input of a cumulative probability Hough transform (PPHT) algorithm, and enabling the cumulative probability Hough transform (PPHT) algorithm to finally output a straight line segment as a target straight line path for navigation by adjusting a threshold parameter, a minLinelength parameter and a maxLineGap parameter