DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection
DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection
复制标题
DOI：
10.1016/j.ins.2020.02.067
复制
发表时间：
2020-06-01
影响因子：
8.1
通讯作者：
Wang, Rutong
中科院分区：
文献类型：
--
作者：
Huang, Zhanchao;Wang, Jianlin;Wang, Rutong
虽然YOLOv2方法的目标检测速度非常快，但由于其骨干网性能不高，多尺度区域特征利用不足，限制了YOLOv2方法的检测精度。为此，本文提出了一种基于密集连接（DC）和空间金字塔池（SPP）的YOLO （DC-SPP-YOLO）方法，以提高YOLOv2的目标检测精度。具体来说，YOLOv2的骨干网采用卷积层的密集连接，加强了特征提取，缓解了梯度消失问题。此外，引入改进的空间金字塔池化方法对多尺度区域特征进行池化和拼接，使网络能够更全面地学习目标特征。基于MSE（均方误差）损失和交叉熵损失组成的新损失函数，建立并训练了DC-SPP-YOLO模型。实验结果表明，在PASCAL VOC数据集和UA-DETRAC数据集上，DC-SPP-YOLO的mAP （mean Average Precision）高于YOLOv2。验证了所提出的DC-SPP-YOLO方法的有效性。(C) 2020爱思唯尔公司版权所有。
Although the YOLOv2 method is extremely fast on object detection, its detection accuracy is restricted due to the low performance of its backbone network and the under-utilization of multi-scale region features. Therefore, a dense connection (DC) and spatial pyramid pooling (SPP) based YOLO (DC-SPP-YOLO) method is proposed in this paper for ameliorating the object detection accuracy of YOLOv2. Specifically, the backbone network of YOLOv2 adopts the dense connection of convolution layers, which strengthen the feature extraction and alleviate the vanishing-gradient problem. Moreover, an improved spatial pyramid pooling is introduced to pool and concatenate the multi-scale region features, so that the network learns the object features more comprehensively. The DC-SPP-YOLO model is established and trained based on a new loss function composed of MSE (mean square error) loss and cross-entropy loss. The experimental results indicate that the mAP (mean Average Precision) of DC-SPP-YOLO is higher than that of YOLOv2 on the PASCAL VOC datasets and the UA-DETRAC datasets. The effectiveness of DC-SPP-YOLO method proposed is demonstrated. (C) 2020 Elsevier Inc. All rights reserved.