期刊
IEEE ACCESS
卷 8, 期 -, 页码 24344-24357出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.2971026
关键词
DenseNet; feature fusion; multi-scale object detection; SSD
资金
- National Natural Science Foundation of China [61373116]
- Ministry of Industry and Information Technology Communication Soft Science Project [2018-R-26]
- Shaanxi Provincial Social Science Foundation [2016N008]
- Shaanxi Provincial Department of Education Science Research Program Foundation [18JK0697]
- Xi'an Social Science Planning Foundation [17X63]
- Xi'an University of Posts and Telecommunications Graduate Innovation Foundation [CXJJLY2018066]
- Xi'an University of Posts and Telecommunications Science and Technology Project [19-B-281]
In view of the lack of feature complementarity between the feature layers of Single Shot MultiBox Detector (SSD) and the weak detection ability of SSD for small objects, we propose an improved SSD object detection algorithm based on Dense Convolutional Network (DenseNet) and feature fusion, which is called DF-SSD. On the basis of SSD, we design the feature extraction network DenseNet-S-32-1 with reference to the dense connection of DenseNet, and replace the original backbone network VGG-16 of SSD with DenseNet-S-32-1 to enhance the feature extraction ability of the model. In the part of multi-scale detection, a fusion mechanism of multi-scale feature layers is introduced to organically combine low-level visual features and high-level semantic features in the network structure. Finally, a residual block is established before the object prediction to further improve the model performance. We train the DF-SSD model from scratch. The experimental results show that our model DF-SSD with 300 x 300 input achieves 81.4% mAP, 79.0% mAP, and 29.5% mAP on PASCAL VOC 2007, VOC 2012, and MS COCO datasets, respectively. Compared with SSD, the detection accuracy of DF-SSD on VOC 2007 is improved by 3.1% mAP. DF-SSD requires only 1/2 parameters to SSD and 1/9 parameters to Faster RCNN. We inject more semantic information into DF-SSD, which makes it have advanced detection effect on small objects and objects with specific relationships.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据