Adaptive segmentation algorithm of landing zone under change of scale

The acquired aerial image is susceptible to illumination and scale changes when UAV is searching for a suitable landing zone based on vision. The main purpose of the aerial image segmentation is to identify the landing zone which is roomy enough for UAV to land and has the same object types (such as land, lakes, etc). Therefore, the segmentation algorithm not only has the capability of clustering but also has the capability of segmenting the different type objects. According to the characteristics of the aerial image and the needs of the segmentation task, an adaptive segmentation algorithm of landing zone under the change of scale is proposed. First, the needed minimum pixel is calculated for UAV landing according to the current height of UAV, the size of the landing area and the ground resolution of the image. Second, the Mean Shift algorithm is employed for image coarse segmentation, and the bandwidth of the kernel function in Mean Shift is calculated according to the minimum pixel gotten in previous step in combination with the threshold in maximum between-cluster variance. Third, the edge of the coarse segmentation image is drawn by using the Canny operator and the final segmentation result is gotten. Finally, the aerial images at different scenarios and scales preliminarily that selected with Google Earth are employed in segmentation experiments. Experimental results demonstrates that the proposed algorithm can meet the mission requirements for accurate segmentation and it is robust to illumination and scale change.