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

Tang Cong; Ling Yongshun; Zheng Kedong; Yang Xing; Zheng Chao; Yang Hua; Jin Wei

doi:10.3788/IRLA201847.0126003

Volume 47 Issue 1

Jan. 2018

Turn off MathJax

Article Contents

Article Navigation > Infrared and Laser Engineering > 2018 > 47(1): 126003-0126003(9)

Tang Cong, Ling Yongshun, Zheng Kedong, Yang Xing, Zheng Chao, Yang Hua, Jin Wei. Object detection method of multi-view SSD based on deep learning[J]. Infrared and Laser Engineering, 2018, 47(1): 126003-0126003(9). doi: 10.3788/IRLA201847.0126003

Citation:

Tang Cong, Ling Yongshun, Zheng Kedong, Yang Xing, Zheng Chao, Yang Hua, Jin Wei. Object detection method of multi-view SSD based on deep learning[J]. Infrared and Laser Engineering, 2018, 47(1): 126003-0126003(9). doi: 10.3788/IRLA201847.0126003

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

doi: 10.3788/IRLA201847.0126003

Tang Cong^1,2,3,
Ling Yongshun^1,2,3,
Zheng Kedong⁴,
Yang Xing^1,3,
Zheng Chao^1,2,3,
Yang Hua^1,2,3,
Jin Wei^1,2,3

1.
National University of Defense Technology,Hefei 230037,China;
2.
Key Laboratory of Infrared and Low Temperature Plasma of Anhui Province,Hefei 230037,China;
3.
State Key Laboratory of Pulsed Power Laser Technology,Hefei 230037,China;
4.
31101 Troops of PLA,Nanjing 210018,China

Received Date: 2017-06-11
Rev Recd Date: 2017-08-12
Publish Date: 2018-01-25

Abstract

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.
- deep learning,
- multi-view SSD,
- object detection,
- small object

References

[1]	Borji A, Cheng M M, Jiang H, et al. Salient object detection:A benchmark[J]. IEEE Transactions on Image Processing, 2015, 24(12):5706-5722.
[2]	Erhan D, Szegedy C, Toshev A, et al. Scalable object detection using deep neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014:2147-2154.
[3]	Luo Haibo, Xu Lingyun, Hui Bin, et al. Status and prospect of target tracking based on deep learning[J]. Infrared and Laser Engineering, 2017, 46(5):0502002. (in Chinese)
[4]	He Sihua, Yang Shaoqing, Shao Xiaofang, et al. Ship target detection on the sea surface based on natural measure feature of image block[J]. Infrared and Laser Engineering, 2011, 40(9):1812-1817. (in Chinese)
[5]	Merlin P M, Farber D J. A parallel mechanism for detecting curves in pictures[J]. IEEE Transactions on Computers, 1975, 100(1):96-98.
[6]	Singla N. Motion detection based on frame difference method[J]. International Journal of Information Computation Technology, 2014, 4(15):1559-1565.
[7]	Lee D S. Effective Gaussian mixture learning for video background subtraction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(5):827-832.
[8]	Horn B K P, Schunck B G. Determining optical flow[J]. Artificial Intelligence, 1981, 17(1-3):185-203.
[9]	Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C]//IEE Conference on Computer Vision and Pattern Recognition, 2003, 1:I-511-I-518.
[10]	Felzenszwalb P F, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9):1627-1645.
[11]	Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[12]	Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, IEEE, 2005, 1:886-893.
[13]	Panning A, Al-Hamadi A K, Niese R, et al. Facial expression recognition based on Haar-like feature detection[J]. Pattern Recognition Image Analysis, 2008, 18(3):447-452.
[14]	Burges C J C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(2):121-167.
[15]	Zhu J, Zou H, Rosset S, et al. Multi-class adaboost[J]. Statistics and its Interface, 2009, 2(3):349-360.
[16]	Kong T, Yao A, Chen Y, et al. HyperNet:towards accurate region proposal generation and joint object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:845-853.
[17]	Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014:580-587.
[18]	He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//European Conference on Computer Vision, 2014:346-361.
[19]	Girshick R. Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015:1440-1448.
[20]	Ren S, He K, Girshick R, et al. Faster r-cnn:Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015:91-99.
[21]	Li Y, He K, Sun J. R-fcn:Object detection via region-based fully convolutional networks[C]//Advances in Neural Information Processing Systems, 2016:379-387.
[22]	Redmon J, Divvala S, Girshick R, et al. You only look once:Unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:779-788.
[23]	Liu W, Anguelov D, Erhan D, et al. SSD:Single shot multibox detector[C]//European Conference on Computer Vision, 2016:21-37.
[24]	Cai Z, Fan Q, Feris R S, et al. A unified multi-scale deep convolutional neural network for fast object detection[C]//European Conference on Computer Vision, 2016:354-370.
[25]	Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C]//ICLR, 2015.

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Get Citation

PDF

XML

Article Metrics

Article views(1402) PDF downloads(610) Cited by()

Proportional views

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

1. National University of Defense Technology,Hefei 230037,China;

2. Key Laboratory of Infrared and Low Temperature Plasma of Anhui Province,Hefei 230037,China;

3. State Key Laboratory of Pulsed Power Laser Technology,Hefei 230037,China;

4. 31101 Troops of PLA,Nanjing 210018,China

Received Date: 2017-06-11

Rev Recd Date: 2017-08-12

Publish Date: 2018-01-25

Key words:

Abstract: 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.

HTML

Reference (25)

[1]	Borji A, Cheng M M, Jiang H, et al. Salient object detection:A benchmark[J]. IEEE Transactions on Image Processing, 2015, 24(12):5706-5722.
[2]	Erhan D, Szegedy C, Toshev A, et al. Scalable object detection using deep neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014:2147-2154.
[3]	Luo Haibo, Xu Lingyun, Hui Bin, et al. Status and prospect of target tracking based on deep learning[J]. Infrared and Laser Engineering, 2017, 46(5):0502002. (in Chinese)
[4]	He Sihua, Yang Shaoqing, Shao Xiaofang, et al. Ship target detection on the sea surface based on natural measure feature of image block[J]. Infrared and Laser Engineering, 2011, 40(9):1812-1817. (in Chinese)
[5]	Merlin P M, Farber D J. A parallel mechanism for detecting curves in pictures[J]. IEEE Transactions on Computers, 1975, 100(1):96-98.
[6]	Singla N. Motion detection based on frame difference method[J]. International Journal of Information Computation Technology, 2014, 4(15):1559-1565.
[7]	Lee D S. Effective Gaussian mixture learning for video background subtraction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(5):827-832.
[8]	Horn B K P, Schunck B G. Determining optical flow[J]. Artificial Intelligence, 1981, 17(1-3):185-203.
[9]	Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C]//IEE Conference on Computer Vision and Pattern Recognition, 2003, 1:I-511-I-518.
[10]	Felzenszwalb P F, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9):1627-1645.
[11]	Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[12]	Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, IEEE, 2005, 1:886-893.
[13]	Panning A, Al-Hamadi A K, Niese R, et al. Facial expression recognition based on Haar-like feature detection[J]. Pattern Recognition Image Analysis, 2008, 18(3):447-452.
[14]	Burges C J C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(2):121-167.
[15]	Zhu J, Zou H, Rosset S, et al. Multi-class adaboost[J]. Statistics and its Interface, 2009, 2(3):349-360.
[16]	Kong T, Yao A, Chen Y, et al. HyperNet:towards accurate region proposal generation and joint object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:845-853.
[17]	Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014:580-587.
[18]	He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//European Conference on Computer Vision, 2014:346-361.
[19]	Girshick R. Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015:1440-1448.
[20]	Ren S, He K, Girshick R, et al. Faster r-cnn:Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015:91-99.
[21]	Li Y, He K, Sun J. R-fcn:Object detection via region-based fully convolutional networks[C]//Advances in Neural Information Processing Systems, 2016:379-387.
[22]	Redmon J, Divvala S, Girshick R, et al. You only look once:Unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:779-788.
[23]	Liu W, Anguelov D, Erhan D, et al. SSD:Single shot multibox detector[C]//European Conference on Computer Vision, 2016:21-37.
[24]	Cai Z, Fan Q, Feris R S, et al. A unified multi-scale deep convolutional neural network for fast object detection[C]//European Conference on Computer Vision, 2016:354-370.
[25]	Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C]//ICLR, 2015.

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

doi: 10.3788/IRLA201847.0126003

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views