Object Detection Deployed on UAVs for Oblique Images by Fusing IMU Information

Object detection is a very challenging task due to the serious object scale diversity. There is an obvious scale distribution in the oblique images captured by the unmanned aerial vehicles (UAVs): the objects at the top of the image are smaller in scale, while the objects at the bottom of the image are larger in scale. Based on this prior information, we propose an object detector with the divide-and-conquer strategy. First, we estimate the object scale using inertial measurement unit (IMU) information. Then the small objects at the top of image are detected by shallow networks with small receptive field and the big objects at the bottom of image are detected by deep networks with big receptive field. Compared with YOLOv5, our method improves the accuracy by 4.6% on mean of average precision (mAP) metric and improves the speed by 79%. Our method can also be performed in real-time on an NVIDIA XAVIER NX with about 30 frames/s. The code is made available on GitHub (<uri>https://github.com/bitshenwenxiao/UAVYOLO</uri>).