A UA-net based Salient Object Detection Method for UAV

Lingfeng Chen, Gan Liu, Ying Tan, Zhe Sun, Hangli Ge, Feng Duan, Chi Zhu

Abstract: Object detection is one of the hot research issues for the Unmanned Aerial Vehicle (UAV). The main problem of object detection is the inaccuracy of object’s location. Most of the current studies focus on classifying and locating objects, while ignore the influence of pixel-level object detection. By utilizing the Salient Object Detection (SOD) method, we may improve the accuracy of object’s location. In this work, we refer to the structure of U-net, and present a network structure called UA-net. In order to improve the result of small image processing, we use not only the commonly used bilinear interpolation method, but also try several other image interpolation methods. After trained and tested by PedCut2013_Segmentation dataset, the result shows that the UA-net can produce nice saliency map of pedestrians, and different interpolation methods have different quality evaluated by evaluation methods. After testing by UAV’s collected images, the saliency map can also be nice SOD results. These results show that UA-net is an applicable SOD structure for UAV to carry out the pedestrian recognition task.