Enhanced Harris Hawk Optimized Image Segmentation Model for Unmanned Aerial Vehicle Remote Sensing Scene Segmentation
摘要
To give a better approach for unmanned aerial vehicle (UAV) remote sensing image (RSS) segmentation and recognition, a threshold image segmentation (TIS) method based on an enhanced Harris hawks optimization (HHO) is proposed. To improve the optimization performance of the algorithm, directional crossover (DC) and directional variation (DV) are introduced into HHO and XMHHO is proposed. The segmentation model XMHHO-TIS is proposed using histogram and threshold segmentation methods and based on the improved XMHHO for threshold search. The comparative experiment results and analysis demonstrate that the proposed model is superior to seven other similar models in terms of segmentation quality.