Object detection method of multi-view SSD based on deep learning

被引：0
|
作者：
Tang C. [1 ,2 ,3 ]
Ling Y. [1 ,2 ,3 ]
Zheng K. [4 ]
Yang X. [1 ,3 ]
Zheng C. [1 ,2 ,3 ]
Yang H. [1 ,2 ,3 ]
Jin W. [1 ,2 ,3 ]
机构：
[1] National University of Defense Technology, Hefei
[2] Key Laboratory of Infrared and Low Temperature Plasma of Anhui Province, Hefei
[3] State Key Laboratory of Pulsed Power Laser Technology, Hefei
[4] 31101 Troops of PLA, Nanjing
来源：
Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering | 2018年 / 47卷 / 01期
关键词：
Deep learning; Multi-view SSD; Object detection; Small object;
D O I：
10.3788/IRLA201847.0126003
中图分类号：
学科分类号：
摘要：
The object detection method of multi-view Single Shot multibox Detector(SSD) based on deep learning was proposed. Firstly, the model and the working principle of classical SSD were expounded. According to the concept of convolution receptive field and the mapping relationship between the feature map and the original image, the sizes of covolution receptive field in different levels and the scales of the default boxes mapped to the original image were analyzed to find the reason why the classical SSD was not good at small object detection. Based on this, the multi-view SSD model was put forward, and the model architecture and its working principle were deeply expounded. Then, through the test in a dataset of 106 images for small object detection, the detection performance of multi-view SSD and classical SSD were evaluated and compared in object retrieval ability and object detection precision. Experimental results show that with the confidence threshold of 0.4, the multi-view SSD is 0.729 in Average F-measure(AF) and 0.644 in mean Average Precision(mAP), and has respectively raised 0.169 and 0.131 compared to the classical SSD in the two evaluation indexes, thus verifying the effectiveness of the proposed method. © 2018, Editorial Board of Journal of Infrared and Laser Engineering. All right reserved.
引用
收藏
相关论文
共 25 条
  • [1] Erhan D., Szegedy C., Toshev A., Et al., Scalable object detection using deep neural networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2147-2154, (2014)
  • [2] Borji A., Cheng M.M., Jiang H., Et al., Salient object detection: A benchmark, IEEE Transactions on Image Processing, 24, 12, pp. 5706-5722, (2015)
  • [3] Luo H., Xu L., Hui B., Et al., Status and prospect of target tracking based on deep learning, Infrared and Laser Engineering, 46, 5, (2017)
  • [4] He S., Yang S., Shao X., Et al., Ship target detection on the sea surface based on natural measure feature of image block, Infrared and Laser Engineering, 40, 9, pp. 1812-1817, (2011)
  • [5] Merlin P.M., Farber D.J., A parallel mechanism for detecting curves in pictures, IEEE Transactions on Computers, 100, 1, pp. 96-98, (1975)
  • [6] Singla N., Motion detection based on frame difference method, International Journal of Information & Computation Technology, 4, 15, pp. 1559-1565, (2014)
  • [7] Lee D.S., Effective Gaussian mixture learning for video background subtraction, IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, 5, pp. 827-832, (2005)
  • [8] Horn B.K.P., Schunck B.G., Determining optical flow, Artificial Intelligence, 17, 1-3, pp. 185-203, (1981)
  • [9] Viola P., Jones M., Rapid object detection using a boosted cascade of simple features, IEE Conference on Computer Vision and Pattern Recognition, 1, (2003)
  • [10] Felzenszwalb P.F., Girshick R.B., McAllester D., Et al., Object detection with discriminatively trained part-based models, IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, 9, pp. 1627-1645, (2010)
123