Target Identification Method Based on Pixel Difference for Eggplant Picking Robot

摘要：

A target identification method based on pixel difference for eggplant fruit picking robot is put forward to improve the reliability and 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 image segmentation is completed through calculating each RGB value of every pixel. The residua and noise are got rid of preferably by morphologic operation and median filter. The outline is drawn by using search direction rotationmethod. 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 85％ respectively and the average time used is 0.11s, meeting the requirements of picking robot for the vision system.

关键词： eggplant picking robot image processing image segmentation feature extraction

作者: Jian Song Changlin Liu

作者单位: College of Machinery, Weifang University, Weifang, Shandong, China College of Engineering, China Agricultural University, Haidian, Beijing, China

会议类型: 国际会议

会议名称: 2010 International Conference on Circuit and Signal Processing(2010年电路与信号处理国际会议 ICCSP 2010)

会议地点: 上海

会议语种:英文

页码: 401-403

在线出版日期: 2010-12-25（万方平台首次上网日期，不代表论文的发表时间）