SSD image target detection algorithm based on self-attention

被引：0
|
作者：
Chu Y. [1 ]
Huang Y. [1 ]
Zhang X. [1 ]
Liu H. [1 ]
机构：
[1] School of Computer Science and Technology, Anhui University of Technology, Ma'anshan
来源：
| 1600年 / Huazhong University of Science and Technology卷 / 48期
关键词：
Convolutional neural network; detection; Hard hat wear; Object detection; Self-attention; Single shot multibox detector (SSD);
D O I：
10.13245/j.hust.200912
中图分类号：
学科分类号：
摘要：
Aiming at supervising employees to wear safety helmets, a neural network was trained based on deep learning method, the single shot multibox detector (SSD) target detection framework and self-attention mechanism were used to train the neural network.By adjusting the parameters of the original SSD target detection framework, the self-attention module was added to the SSD target detection framework.The mutual influence between pixels in the feature map could be calculated, so as to improve the algorithm's attention to target detection and expand the receptive field of convolutional neural network, and the accuracy of target detection was improved.Experimental results show that the improved algorithm has good adaptability to small target detection and occlusion between targets, and the detection accuracy is significantly improved compared with other detection algorithms. © 2020, Editorial Board of Journal of Huazhong University of Science and Technology. All right reserved.
引用
收藏
页码：70 / 75
页数：5
相关论文
共 17 条
  • [1] 10
  • [2] RUBAIYAT A H M, TOMA T T, KALANTARI-KHANDANI M, Et al., Automatic detection of helmet uses for construction safety, Proc of International Confer-ence on Web Intelligence Workshops, pp. 135-142, (2017)
  • [3] 3
  • [4] 40, 3, pp. 365-370, (2014)
  • [5] DALAL N, TRIGGS B., Histograms of oriented gradients for human detection, Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 886-893, (2005)
  • [6] GIRSHICK R, DONAHUE J, DARRELL T, Et al., Rich feature hierarchies for accurate object detection and se-mantic segmentation, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2013)
  • [7] GIRSHICK R., FastR-CNN, Proc of the IEEE Inter-national Conference on Computer Vision, pp. 1440-1448, (2015)
  • [8] REN S, HE K, GIRSHICK R, Et al., Faster R-CNN: towards real-time object detection with region proposal networks, Advances in Neural Information Proc-essing Systems, pp. 91-99, (2015)
  • [9] REDMON J, DIVVALA S, GIRSHICK R, Et al., You only look once: unified, real-time object detection, Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, (2016)
  • [10] LIU W, ANGUELOV D, ERHAN D, Et al., SSD: single shot multibox detector, Proc of the 14th European Conference on Computer Vision, pp. 21-37, (2016)
12