LWUAVDet: A Lightweight UAV Object Detection Network on Edge Devices

Real-time object detection on unmanned aerial vehicles (UAVs) poses a challenging issue due to the limited computing resources of edge devices. To address this problem, we propose a novel lightweight object detection network named LWUAVDet for real-time UAV applications. The detector comprises three core components: E-FPN, PixED Head, and Aux Head. Firstly, we develop an extended and refined topology in the Neck layer, called E-FPN, to enhance the multi-scale representation of each stage and alleviate the aliasing effect caused by the repetitive feature fusion of the Neck. Secondly, we propose a pixel encoder and decoder for dimension exchange between space and channel to achieve flexible and effective feature extraction in the Head layer, named PixED Head. Furthermore, Aux Head for the auxiliary task merely using the Head layer is presented for online distillation to enhance feature representation. Specially, in Aux Head, we introduce the weighted sum of Focal Loss and complete intersection over union loss for the cost matrix of the sample assigner to alleviate category imbalance and aspect ratio imbalance of the UAV data. The performance of our LWUAVDet is validated experimentally on the NVIDIA Jetson Xavier NX and Jetson Nano GPU devices. Extensive experiments demonstrate that the LWUAVDet models achieve a better trade-off between accuracy and latency on VisDrone, UAVDT, and VOC2012 datasets compared to state-of-the-art lightweight models.