Visual Row Detection Using Pixel-Based Algorithm and Stereo Camera for Cotton-Picking Robot

Precision farming still depends heavily on RTK-GPS to navigate along the rows of the farms. However, GPS cannot be the only method to navigate the farm for robots to work as a “swarm” on the same farm; they may require visual systems to navigate and avoid collisions. Also, plant growth and canopy changes are not accommodated. Hence, the visual system remains a complementary method to add to the efficiency of the GPS system. In this study, optical detection of the cotton rows is investigated and demonstrated. The stereo camera is used to detect the row depth, and then, the pixel-based algorithm is used to calculate and determine the highest pick and lowest picks of the cotton rows by assuming the normal distribution of the high and low pixels. Using perspective transform and pixel-based sliding window algorithm, it detects the left and right row. Then, the system determines the Bayesian score of the detection and calculates the center of the rows for smooth navigation of the cotton-picking robot.