A Tracking-by-Detection System for Pedestrian Tracking Using Deep Learning Technique and Color Information
1
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Pedestrian tracking is a particular object tracking problem and an important component in various visionbasedapplications, such as autonomous cars and surveillance systems. Following several years of development,pedestrian tracking in videos remains challenging, owing to the diversity of object appearances and surroundingenvironments. In this research, we proposed a tracking-by-detection system for pedestrian tracking, whichincorporates a convolutional neural network (CNN) and color information. Pedestrians in video frames arelocalized using a CNN-based algorithm, and then detected pedestrians are assigned to their correspondingtracklets based on similarities between color distributions. The experimental results show that our system isable to overcome various difficulties to produce highly accurate tracking results.
Abstract
Pedestrian tracking is a particular object tracking problem and an important component in various visionbasedapplications, such as autonomous cars and surveillance systems. Following several years of development,pedestrian tracking in videos remains challenging, owing to the diversity of object appearances and surroundingenvironments. In this research, we proposed a tracking-by-detection system for pedestrian tracking, whichincorporates a convolutional neural network (CNN) and color information. Pedestrians in video frames arelocalized using a CNN-based algorithm, and then detected pedestrians are assigned to their correspondingtracklets based on similarities between color distributions. The experimental results show that our system isable to overcome various difficulties to produce highly accurate tracking results.
참고문헌 (20)
- C. Sutheerakul, "Application of unmanned aerial vehicles to pedestrian traffic monitoring and management for shopping streets", Transportation Research Procedia, 25, pp.1717~1734 (2017)
- K. V. Sriram, "Human detection and tracking in video surveillance system", Proceedings of 2016 IEEE International Conference on Computational Intelligence and Computing Research, pp.1~3 (2016)
- F. Li, "Fast pedestrian detection and dynamic tracking for intelligent vehicles within V2V cooperative environment", IET Image Processing, 11(10), pp.833~840 (2017)
- A. W. M. Smeulders, "Visual tracking : an experimental survey", IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(7), pp.1442~1468 (2014)
- A. Yilmaz, "Object tracking: a survey", ACM Computing Survey, 38(4) (2006)
- A. Dehghan, "Pedestrian and Evacuation Dynamics 2012", pp.3~19 (2014), Springer
- J. Zhu, "Computer Vision – ECCV 2018", pp.366~382 (2018), Springer
- Y. Jiang, "Online pedestrian tracking with multi-stage re-identification", Proceedings of 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, pp.1~6 (2017)
- Ning Yu, "Deep Learning in Genomic and Medical Image Data Analysis: Challenges and Approaches", JIPS(Journal of Information Processing Systems), 13(2), pp.204~214 (2017), 한국정보처리학회[DOI]
- Xin Feng, "Infrared and Visible Image Fusion Based on NSCT and Deep Learning", JIPS(Journal of Information Processing Systems), 14(6), pp.1405~1419 (2018), 한국정보처리학회[DOI]
- Zilong Jiang, "A CTR Prediction Approach for Text Advertising Based on the SAE-LR Deep Neural Network", JIPS(Journal of Information Processing Systems), 13(5), pp.1052~1070 (2017), 한국정보처리학회
- S. D. You, "Comparative study of singing voice detection based on deep neural networks and ensemble learning", Human-centric Computing and Information Sciences, 8(1) (2018)
- S. Ren, "Faster R-CNN : towards real-time object detection with region proposal networks", IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), pp.1137~1149 (2017)
- K. He, "Deep residual learning for image recognition", Proceedings of 2016IEEE Conference on Computer Vision and Pattern Recognition, pp.770~778 (2016)
- J. Huang, "Speed", accuracy trade-offs for modern convolutional object detectors, 2017, 3296~3297
- E. Bochinski, "High-speed tracking-by-detection without using image information", Proceedings of 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, pp.1~6 (2017)
- M. T. N. Truong, "Parallel implementation of color-based particle filter for object tracking in embedded systems", Human-centric Computing and Information Sciences, 7 (2017)
- "Tracking Dataset" (2017)[URL]
- M. Kristan, "The sixth visual object tracking vot2018 challenge results", Proceedings of the 14th European Conference on Computer Vision (ECCV), pp.3~53 (2018)
- "Motchallenge 2015: towards a benchmark for multi-target tracking" (2015)[URL]