-
- ZHANG Yanyan
- Department of Electronic and Information Engineer, Nanjing University of Information Science & Technology
-
- SHEN Meiling
- Department of Electronic and Information Engineer, Nanjing University of Information Science & Technology
-
- YANG Wensheng
- Department of Electronic and Information Engineer, Nanjing University of Information Science & Technology
抄録
<p>We propose a target detection network (RMF-Net) based on the multi-scale strategy to solve the problems of large differences in the detection scale and mutual occlusion, which result in inaccurate locations. A multi-layer feature fusion module and multi-expansion dilated convolution pyramid module were designed based on the ResNet-101 residual network. The ability of the network to express the multi-scale features of the target could be improved by combining the shallow and deep features of the target and expanding the receptive field of the network. Moreover, RoI Align pooling was introduced to reduce the low accuracy of the anchor frame caused by multiple quantizations for improved positioning accuracy. Finally, an AD-IoU loss function was designed, which can adaptively optimise the distance between the prediction box and real box by comprehensively considering the overlap rate, centre distance, and aspect ratio between the boxes and can improve the detection accuracy of the occlusion target. Ablation experiments on the RMF-Net model verified the effectiveness of each factor in improving the network detection accuracy. Comparative experiments were conducted on the Pascal VOC2007 and Pascal VOC2012 datasets with various target detection algorithms based on convolutional neural networks. The results demonstrated that RMF-Net exhibited strong scale adaptability at different occlusion rates. The detection accuracy reached 80.4% and 78.5% respectively.</p>
収録刊行物
-
- IEICE Transactions on Communications
-
IEICE Transactions on Communications E105.B (5), 675-683, 2022-05-01
一般社団法人 電子情報通信学会
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390291932689766400
-
- NII論文ID
- 130008124244
-
- ISSN
- 17451345
- 09168516
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可