Zhang Jie, Zhang Hongyan, Liu Bowen, Qu Guang, Wang Fengxian, Zhang Huanlong, Shi Xiaoping
College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China.
Department of navigation, Airforce communication NCO Academy, DaLian 116000, China.
Heliyon. 2023 Jul 3;9(7):e17730. doi: 10.1016/j.heliyon.2023.e17730. eCollection 2023 Jul.
As we all know, YOLOv4 can achieve excellent detection performance in object detection and has been effectively applied in many fields. However, the inconsistency of scale features affects the prediction accuracy of the path aggregation network (PANet) in YOLOv4 for small objects, resulting in low detection accuracy. This paper presents YOLOv4, which uses an adaptive recursive path aggregation network (AR-PANet) to improve the detection accuracy of small objects. First, the output characteristics of the PANet are fed back into the backbone network by using a recursive structure to enrich the characteristic information of the object. Second, an adaptive approach is developed to eliminate conflicting information in multi-scale feature space, thereby enhancing scale invariance and promoting feature extraction accuracy for small objects. Finally, the CBAM is used to map the multi-scale features obtained from the AR-PANet to independent channels and spatial dimensions to achieve feature refinement, thus improving the detection accuracy of small objects. Experimental results show that our proposed method can effectively improve the accuracy of small object detection in multiple datasets, addressing this challenging problem with impressive results. Thus, our proposed approach has great potential and valuable applications in the fields of remote sensing and intelligent transportation.
众所周知，YOLOv4在目标检测中能实现出色的检测性能，并已在许多领域得到有效应用。然而，尺度特征的不一致性影响了YOLOv4中路径聚合网络（PANet）对小目标的预测精度，导致检测准确率较低。本文提出了YOLOv4，它使用自适应递归路径聚合网络（AR-PANet）来提高小目标的检测精度。首先，通过递归结构将PANet的输出特征反馈到主干网络中，以丰富目标的特征信息。其次，开发了一种自适应方法来消除多尺度特征空间中的冲突信息，从而增强尺度不变性并提高小目标的特征提取精度。最后，使用CBAM将从AR-PANet获得的多尺度特征映射到独立的通道和空间维度以实现特征细化，从而提高小目标的检测精度。实验结果表明，我们提出的方法可以有效提高多个数据集中小目标检测的准确率，以令人印象深刻的结果解决了这个具有挑战性的问题。因此，我们提出的方法在遥感和智能交通领域具有巨大的潜力和有价值的应用。
