Improved Faster R-CNN for Multi-Scale Object Detection

被引：0
作者：
Li X. [1 ]
Fu C. [1 ]
Li X. [1 ]
Wang Z. [1 ]
机构：
[1] College of Information, Liaoning University, Shenyang
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2019年 / 31卷 / 07期
关键词：
Convolutional neural network; Deep learning; Multi-scale learning; Object detection;
D O I：
10.3724/SP.J.1089.2019.17283
中图分类号：
学科分类号：
摘要：
For multi-scale object detection, the detection methods based on single-level feature extraction suffered from the low detection quality because of the loss or distortion of feature for small-scale objects, or the redundancy of feature for large-scale objects. We propose a multi-scale object detection method based on Faster R-CNN. The method extracts the multi-scale features with the policy of multi-level feature extraction, configures statistically the size and the aspect ratio of the anchor, and adopts a multi-channel region strategy to generate multi-scale proposals. Extensive experiments on the PASCAL VOC dataset show that the quality of our method, with 9.7% of the log-average miss rate and 75.2% of the mean average precision, performs better than the traditional detection methods. © 2019, Beijing China Science Journal Publishing Co. Ltd. All right reserved.
引用
收藏
页码：1095 / 1101
页数：6
相关论文
共 24 条
  • [1] Li J., Zhou X., Chan S., Et al., A novel video target tracking method based on adaptive convolutional neural network feature, Journal of Computer-Aided Design & Computer Graphics, 30, 2, pp. 273-281, (2018)
  • [2] Sang J., Guo P., Xiang Z., Et al., Vehicle detection based on faster-RCNN, Journal of Chongqing University, 40, 7, pp. 32-36, (2017)
  • [3] Mao Y., Research on object detection technology of robotic vision systems, (2017)
  • [4] Cai H., Zhao Z., Han L., Et al., Multiple target detection algorithm based on SSD networks, Journal of Mechanical & Electrical Engineering, 34, 6, pp. 685-688, (2017)
  • [5] Rui T., Fei J., Zhou Y., Et al., Pedestrian detection based on deep convolutional neural network, Computer Engineering and Applications, 52, 13, pp. 162-166, (2016)
  • [6] Xie L., Ji G., Peng Q., Et al., Application of preprocessing convolutional neural network in pedestrian detection, Journal of Frontiers of Computer Science and Technology, 12, 5, pp. 708-718, (2018)
  • [7] Zhang D., Li L., Face detection system based on PCANet-RF, Computer Technology and Development, 26, 2, pp. 31-34, (2016)
  • [8] Wei Z., Wen C., Xie K., Et al., Real-time face detection for mobile devices with optical flow estimation, Journal of Computer Applications, 38, 4, pp. 1146-1150, (2018)
  • [9] Girshick R., Donahue J., Darrelland T., Et al., Rich feature hierarchies for accurate object detection and semantic segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2014)
  • [10] He K.M., Zhang X.Y., Ren S.Q., Et al., Spatial pyramid pooling in deep convolutional networks for visual recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 9, pp. 1904-1916, (2015)
123