Object extraction for the vision system of eggplant picking robot

Object extraction for the vision system of eggplant picking robot is put forward to improve the real time of the vision system. The characteristic of eggplant fruit is found by means of experiment and statistics of the color features of the eggplant fruit in growing environment and their surroundings. The EXG color factor is most available to segment the image of eggplants. The threshold segmentation method is completed based on the brightness. The residua are got rid of preferably by template operation and morphologic operation. Rotation direction search method is used to contour tracing the eggplant fruit image edges. According to the requirements for the vision system of fruit-vegetable picking robot, such features are extracted as the contour, area, circumscribed rectangle and cut out point of the fruit target. In is shown by the experiments that the segmentation efficiency is greater than 84% respectively and the average time used is 0.11s, meeting the requirements of picking robot for the vision system.