Method based on Separation Confidence Computation and Scale Synthesis Optimization for Real-Time Target Detection in Streetscape Videos

doi:10.23940/ijpe.19.06.p5.15381547

Int J Performability Eng ›› 2019, Vol. 15 ›› Issue (6): 1538-1547.doi: 10.23940/ijpe.19.06.p5.15381547

Previous Articles Next Articles

Method based on Separation Confidence Computation and Scale Synthesis Optimization for Real-Time Target Detection in Streetscape Videos

Jianmin Liu^a,b,*, Minhua Yang^b, and Jianmei Tan^a

a School of Information and Statistics, Guangxi University of Finance and Economics, Nanning, 530003, China
b School of Geosciences and Info-Physics, Central South University, Changsha, 410000, China

Submitted on ;
Contact: * E-mail address: jianminliu2007@163.com
About author:Jianmin Liu received his B.S. degree from the University of Hunan, his M.S. degree from the University of Xiamen, and his Ph.D. from Central South University. His research interests include data mining and machine learning;Minhua Yang received his Ph.D. from China Agricultural University. He is currently a professor at Central South University;Jianmei Tan received her M.S. degree from the University of Technology of Changsha.
Supported by:
This work was supported by the Ph.D. Research Foundation of Guangxi University of Finance and Economics, Key Research Projects of Hunan Provincial Department of Education (No. 17A108), and Guangxi Natural Science Foundation.

Abstract

Abstract: This study proposes a method for the real-time detection and recognition of targets in streetscape videos. The proposed method is based on separation confidence computation and scale synthesis optimization. First, on the basis of generalization in transfer learning, we combine a fine-tuning method suitable for non-convex optimization and adaptive moment estimation in high-dimensional space. Then, we dynamically adjust the learning rates of parameters on the basis of first and second gradient moment estimations. We establish the framework and implementation steps of the proposed method by organically combining regular term super-parameter generalization and hard-example mining technology. We use the proposed method to detect and recognize targets in streetscape videos with high frame rates and high definition. Furthermore, we experimentally demonstrate that the accuracy and robustness of our proposed method are superior to those of conventional methods.

Key words: object detection, separation confidence computation, scale synthesis optimization, transfer learning, streetscape videos

Jianmin Liu, Minhua Yang, and Jianmei Tan. Method based on Separation Confidence Computation and Scale Synthesis Optimization for Real-Time Target Detection in Streetscape Videos [J]. Int J Performability Eng, 2019, 15(6): 1538-1547.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

[1] S. Wu, D. Chen,X. Wang, “Moving Target Detection based on Improved Three Frame Difference and Visual Background Extractor,” in Proceedings of 2017 10^th International Congress on Image and Signal Processing, Biomedical Engineering and Informatics, IEEE, 2017
[2] X. Shen, Z. Song,H. Fan, “Data Level Moving Target Detection Algorithm based on Bernoulli Random Finite Set,” Iet Signal Processing, Vol. 12, No. 6, 2018
[3] A. Krizhevsky, I. Sutskever,G. E. Hinton, “Imagenet Classification with Deep Convolutional Neural Networks,” inProceedings of the 25^th International Conference on Neural Information Processing Systems, pp. 1097-1105, 2012
[4] K. He, X. Zhang,S. Ren, “Deep Residual Learning for Image Recognition,” inProceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
[5] S. Christian, T. Alexander,E. Dumitru, “Deep Neural Networks for Object Detection,” inProceedings of Conference on Neural Information Processing Systems, pp. 2553-2561, 2013
[6] R. Girshick, J. Donahue,T. Darrell, “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” arXiv Preprint arXiv:1311.2524v3, 2014
[7] R. Girshick, “Fast R-CNN,” arXiv Preprint arXiv:1504.08083, 2015
[8] K. R.He and R. Girshick, “Faster R-Cnn: Towards Real-Time Object Detection with Region Proposal Networks,” in Proceedings of the 28^th International Conference on Neural Information Processing Systems, Vol. 1, pp. 91-99, 2016
[9] J. Redmon, S. Divvala,R. Girshick, “You Only Look Once: Unified, Real-Time Object Detection,” arXiv Preprint arXiv:1506. 02640, 2016
[10] C. Szegedy, W. Liu,Y. Jia, “Going Deeper with Convolutions,” inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-9, 2015
[11] J. Li, H. C. Wong,S. L. Lo, “Multiple Object Detection by Deformable Part-based Model and R-CNN,” IEEE Signal Processing Letters, Vol. 1, No. 1, pp. 99, 2018
[12] P. Dong and W. Wang, “Better, Region Proposals for Pedestrian Detection with R-CNN,” inProceedings of Conference on Visual Communications and Image Processing, pp. 1-4, IEEE, 2017
[13] J. R. R.Uijlings, K. Sande, and T. Gevers, “Selective Search for Object Recognition,” International Journal of Computer Vision, Vol. 104, No. 2, pp. 154-171, 2013
[14] J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” arXiv Preprint arXiv:1612.08242, 2016
[15] W. Liu, D. Anguelov,D. Erhan, “SSD: Single Shot MultiBox Detector,” in Proceedings of European Conference on Computer Vision, Springer, Cham, pp. 21-37, 2016
[16] M. Zhu, “Recall, Precision and Average Precision,” Department of Statistics and Actuarial Science, University of Waterloo, Waterloo, pp. 2-30, 2004
[17] A. Neubeck and G. L. Van, “Efficient Non-Maximum Suppression,” inProceedings of ICPR 2006 18th International Conference on Pattern Recognition, pp. 850-855, IEEE, 2006
[18] S. J.Pan and Q. Yang, “A Survey on Transfer Learning,” IEEE Transactions on Knowledge & Data Engineering, Vol. 22, No. 10, pp. 1345-1359, 2010
[19] A. Shrivastava, A. Gupta,R. Girshick, “Training Region-based Object Detectors with Online Hard Example Mining,” inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 761-769, 2016
[20] “The Pascal Visual Object Classes Challenge 2012 (voc2012) Results (2012),” (http://www.pascal-network.org /challenges/VOC/, last accessed on January 1, 2019
[21] A. Geiger, P. Lenz, and R. Urtasun, “Are We Ready for Autonomous Driving the Kitti Vision Benchmark Suite,” in Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3354-3361, 2012
[22] “Udacity. Public Driving Dataset,”(https://www.udacity.com/self-driving-car, last accessed on January 10, 2019)
[23] O. Russakovsky, J. Deng,H. Su, “Imagenet Large Scale Visual Recognition Challenge,” International Journal of Computer Vision, Vol. 115, No. 3, pp. 211-252, 2015

Method based on Separation Confidence Computation and Scale Synthesis Optimization for Real-Time Target Detection in Streetscape Videos

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 10

Recommended 0

[1]	Aashita Rajput, Muskan Yadav, Sachin Yadav, Megha Chhabra, and Arun Prakash Agarwal. Patch-Based Breast Cancer Histopathological Image Classification using Deep Learning [J]. Int J Performability Eng, 2023, 19(9): 607-623.
[2]	Saumya Kumar, Puneet Goswami, and Shivani Batra. Enriched Diagnosis of Osteoporosis using Deep Learning Models [J]. Int J Performability Eng, 2023, 19(12): 824-833.
[3]	Weiguo Pan, Feng Pan, and En Fu. Dual Model-based Traffic Light and Sign Detection using Prior Information [J]. Int J Performability Eng, 2020, 16(8): 1203-1214.
[4]	Tao Wei, Xuezhuan Zhao, Lishen Pei and Lingling Li. A Co-Saliency Object Detection Model for Video Sequences [J]. Int J Performability Eng, 2020, 16(11): 1793-1802.
[5]	Qinggang Wu and Xueming Zhai. Remote Sensing Object Detection via an Improved YOLO Network [J]. Int J Performability Eng, 2020, 16(11): 1803-1813.
[6]	Weiguo Pan, En Fu, Bingxin Xu, Songyin Dai, and Feng Pan. Traffic Sign Detection via Efficient ROI Detector and Deep Convolution Neural Network [J]. Int J Performability Eng, 2020, 16(10): 1566-1578.
[7]	Yu Wang, Shuai Yang, and René Vinicio Sánchez. Wind Turbine Gearbox Fault Diagnosis using SAE-BP Transfer Neural Network [J]. Int J Performability Eng, 2019, 15(9): 2504-2514.
[8]	Aili Wang, Ying Wang, Xiaoying Song, and Yuji Iwahori. Remote Sensing Image Super-Resolution Reconstruction based on Generative Adversarial Network [J]. Int J Performability Eng, 2019, 15(7): 1783-1791.
[9]	Lan Wu and Xiaolei Han. Novel Steganalysis Method for Unknown Embedding Rates using Transfer and Multi-Task Learning [J]. Int J Performability Eng, 2019, 15(12): 3139-3150.
[10]	Baojun Zhang. Moving Target Detection and Trackingbased on Camshift Algorithm and KalmanFilter in Sport Video [J]. Int J Performability Eng, 2019, 15(1): 288-397.