This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Inspired by FCOS, a lighter and more efficient decoupled head is proposed, and its inference speed can be improved with little loss of precision. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS COCO2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia Jetson AGX Xavier. We also designed lighter models with less parameters for edge computing devices with lower computing power, which also show better performances. Our source code, hyper-parameters and model weights are all available at https://github.com/LSH9832/edgeyolo.
翻译:本文提出一个高效、低复杂和无锚的物体探测器,其依据是最新的YOLO框架,可在边缘计算平台上实时实施。我们开发了一个强化的数据增强方法,以便在培训期间有效抑制过度装配,并设计一个混合随机损失功能,以提高小物体的探测准确性。在FCOS的启发下,提出了一个较轻和更有效的脱钩头板,其推导速度可以提高,精确度则少得多。我们的基线模型可以在MS CO2017数据集中达到50.6% AP50:95和69.8% AP50的精确度,在VisDrone2019-DET数据集中达到26.4% AP50和44.8% AP50的精确度。在Nvidia Jetson AgX Xavier的边缘计算机设备上,我们还设计了较轻的模型,其参数较少,其计算能力也显示更好的性能。我们的源代码、超参数和模型重量都在 https://github.HLS/HLS.