Apple Nighttime Images Enhancement Algorithm for Harvesting Robot

作者:Lv Xingqin*; Xu Bo; Ji Wei; Tong Gang; Zhao Dean
来源:Chinese Intelligent Systems Conference (CISC), 2015 to 2015.
DOI:10.1007/978-3-662-48386-2_10

摘要

In order to enhance the applicability and efficiency of harvesting robot to ensure that people can timely pick ripe fruit, the robot need to have an ability of continuous recognition and harvest at night. For some disadvantages of night vision images, Retinex algorithm for image enhancement based on bilateral filter is presented. Bilateral filter which has a function of edge preservation is adopted to improve the smooth, evaluate the illumination and remove unfavorable illumination effects from the original image. Then the reflectance of the image from above that contains just the characteristics of the object itself can be obtained. Finally, apple nighttime image enhancement is implemented. The experimental results show that the above method can more accurately evaluate the illumination of high-contrast edge regions, to suppress noise, enhance image contrast and improve overall visual effects of the image.

全文