Liu Haiying, Sun Fengqian, Gu Jason, Deng Lixia
School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, China.
School of Electrical and Computer Engineering, Dalhousie University, Halifax, NS B3H 4R2, Canada.
Sensors (Basel). 2022 Aug 4;22(15):5817. doi: 10.3390/s22155817.
In the research of computer vision, a very challenging problem is the detection of small objects. The existing detection algorithms often focus on detecting full-scale objects, without making proprietary optimization for detecting small-size objects. For small objects dense scenes, not only the accuracy is low, but also there is a certain waste of computing resources. An improved detection algorithm was proposed for small objects based on YOLOv5. By reasonably clipping the feature map output of the large object detection layer, the computing resources required by the model were significantly reduced and the model becomes more lightweight. An improved feature fusion method (PB-FPN) for small object detection based on PANet and BiFPN was proposed, which effectively increased the detection ability for small object of the algorithm. By introducing the spatial pyramid pooling (SPP) in the backbone network into the feature fusion network and connecting with the model prediction head, the performance of the algorithm was effectively enhanced. The experiments demonstrated that the improved algorithm has very good results in detection accuracy and real-time ability. Compared with the classical YOLOv5, the mAP@0.5 and mAP@0.5:0.95 of SF-YOLOv5 were increased by 1.6% and 0.8%, respectively, the number of parameters of the network were reduced by 68.2%, computational resources (FLOPs) were reduced by 12.7%, and the inferring time of the mode was reduced by 6.9%.
在计算机视觉研究中，一个极具挑战性的问题是小目标检测。现有的检测算法通常专注于检测全尺寸目标，而没有针对小尺寸目标进行专门优化。对于小目标密集场景，不仅准确率低，而且存在一定的计算资源浪费。提出了一种基于YOLOv5的小目标改进检测算法。通过合理裁剪大目标检测层输出的特征图，显著减少了模型所需的计算资源，使模型变得更轻量级。提出了一种基于PANet和BiFPN的用于小目标检测的改进特征融合方法（PB-FPN），有效提高了算法对小目标的检测能力。通过将骨干网络中的空间金字塔池化（SPP）引入特征融合网络并与模型预测头连接，有效提升了算法性能。实验表明，改进后的算法在检测准确率和实时性方面都有很好的效果。与经典的YOLOv5相比，SF-YOLOv5的mAP@0.5和mAP@0.5:0.95分别提高了1.6%和0.8%，网络参数数量减少了68.2%，计算资源（FLOPs）减少了12.7%，模型推理时间减少了6.9%。
