面向无人机平台的轻量化目标检测网络

Lightweight target detection network for UAV platforms

针对无人机端目标检测中存在图像尺度变化大、目标尺寸小和无人机机载嵌入式计算资源有限的问题,提出一种应用于无人机平台轻量化的目标检测网络。该网络以YOLOv5作为基准模型,首先增加检测分支以处理尺度变化的问题;然后提出基于归一化Wasserstein距离与传统IOU混合的小目标检测度量方法,用于解决小目标检测精度低的问题;随后提出FasterNet与C3融合的C3_FN轻量化网络结构,降低网络计算量,使其更适合无人机平台使用。最后将算法分别在仿真平台与嵌入式平台上利用无人机目标检测数据集VisDrone进行性能测试。仿真平台上的测试结果表明,本文提出的网络相较于基准网络在mAP0.5指标上提升了6.6%,mAP0.5-0.95指标上提升了4.8%,推理时间仅需45.9 ms,对比其他主流的无人机目标检测网络具有更好的检测效果。在嵌入式设备NVIDIA Jetson Nano上的测试结果表明,本文算法能够在有限的硬件资源下获得高精度接近实时的检测性能。

A lightweight target detection network for application to unmanned aerial vehicle(UAV)plat-forms was proposed for solving the problems of large image-scale variation,small target size,and limited embedded computing resources on UAVs in UAV-side target detection.The network used YOLOv5 as the benchmark model.First,detection branches were used to solve the problem of scale variation.Then,a small-target detection metric based on a mixture of normalized Wasserstein distance and traditional IOU was used for solving the problem of inaccurate small-target detection.In addition,a C3_FN lightweight network structure combining FasterNet and C3 was employed to reduce the computational burden of the network and make it more suitable for UAV platforms.The performance of the algorithms was tested on a simulation platform and an embedded platform using the UAV target detection dataset VisDrone.The sim-ulation platform test results indicate that the proposed network achieves improvements of 6.6%and 4.8%in the mAP0.5 and mAP0.5-0.95 metrics,respectively,compared with a benchmark network,and the inference time is only 45.9 ms.The detection results are superior to those of mainstream UAV target detection net-works.The test results for the embedded device(NVIDIA Jetson Nano)indicate that the proposed algo-rithm can achieve high accuracy and near real-time detection performance with limited hardware resources.