CNN기반의 SVM을 이용한 효율적인 입수자 검출 알고리즘
Efficient Swimmer Detection Algorithm using CNN-based SVM
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
In this paper, we propose a CNN-based swimmer detection algorithm. Every year, water safety accidents have been occurred frequently, and accordingly, intelligent video surveillance systems are being developed to prevent accidents. Intelligent video surveillance system is a real-time system that detects objects which users want to do. It classifies or detects objects in real-time using algorithms such as GMM (Gaussian Mixture Model), HOG (Histogram of Oriented Gradients), and SVM (Support Vector Machine). However, HOG has a problem that it cannot accurately detect the swimmer in a complex and dynamic environment such as a beach. In other words, there are many false positives that detect swimmers as waves and false negatives that detect waves as swimmers. To solve this problem, in this paper, we propose a swimmer detection algorithm using CNN (Convolutional Neural Network), specialized for small object sizes, in order to detect dynamic objects and swimmers more accurately and efficiently in complex environment. The proposed CNN sets the size of the input image and the size of the filter used in the convolution operation according to the size of objects. In addition, the aspect ratio of the input is adjusted according to the ratio of detected objects. As a result, experimental results show that the proposed CNN-based swimmer detection method performs better than conventional techniques.
Abstract
In this paper, we propose a CNN-based swimmer detection algorithm. Every year, water safety accidents have been occurred frequently, and accordingly, intelligent video surveillance systems are being developed to prevent accidents. Intelligent video surveillance system is a real-time system that detects objects which users want to do. It classifies or detects objects in real-time using algorithms such as GMM (Gaussian Mixture Model), HOG (Histogram of Oriented Gradients), and SVM (Support Vector Machine). However, HOG has a problem that it cannot accurately detect the swimmer in a complex and dynamic environment such as a beach. In other words, there are many false positives that detect swimmers as waves and false negatives that detect waves as swimmers. To solve this problem, in this paper, we propose a swimmer detection algorithm using CNN (Convolutional Neural Network), specialized for small object sizes, in order to detect dynamic objects and swimmers more accurately and efficiently in complex environment. The proposed CNN sets the size of the input image and the size of the filter used in the convolution operation according to the size of objects. In addition, the aspect ratio of the input is adjusted according to the ratio of detected objects. As a result, experimental results show that the proposed CNN-based swimmer detection method performs better than conventional techniques.
참고문헌 (21)
- 2016 Ministary of Public Safety and Security Statistics Annual Report, "Ministary of Public Safety and Security", 49~53 (2016)
- YuJung Choi, "Object Detecting and Tracking Algorithm In The Environment of Complex Beach", Korean Institute of Information Scientists and Engineers Academic Publications, 2016(12), pp.1123~1125 (2016)
- Z. Zivkovic, "Improved Adaptive Gaussian Mixture Model for Background Subtraction", Pattern Recognition, 2, pp.28~31 (2004)
- N. Dalal, "Histogram of Oriented Gradients for Human Detection", Proc. of the Int’l Conf. on Computer Vision and Pattern Recognition, pp.886~893 (2005)
- C. Burges, "A Tutorial on Support Vector Machines for Pattern Recognition", Data Mining and Knowledge Discovery, 2(Issue 2), pp.121~167 (1998)
- Y. Bengio, "Learning Deep Architectures for AI", Foundations and Trends in Machine Learning, 2(1), pp.1~127 (2009)
- Y. Tang, "Deep Learning using Linear Support Vector Machines", ArXiv preprint arXiv:1306.0239, ~ (2013)
- S. Paisitkriangkrai, "Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning", IEEE Trans. on Pattern Analysis and Machine Intelligence, 38(Issue 6), pp.1243~1257 (2016)
- H. Jiang, "Face Detection with the Faster R-CNN", Proc. of the Int’l Conf. on Automatic Face and Gesture Recognition, pp.650~657 (2017)
- 장지웅, "일반 CCTV 기반 차량 번호판 인식 시스템", 전자공학회논문지, 54(8), pp.89~96 (2017), 대한전자공학회
- S. Krig, "Computer Vision Metrics", pp.187~246 (2016)
- P. Viola, "Rapid Object Detection Using a Boosted Cascade of Simple Features", Proc. of the Int’l Conf. on Computer Vision and Pattern Recognition, pp.1~9 (2001)
- P. Felzenszwalb, "A Discriminatively Trained, Multiscale, Deformable Part Model", Proc. of the Int’l Conf. on Computer Vision and Pattern Recognition, pp.1~8 (2008)
- J. Redmon, "YOLO9000: Better, Faster, Stronger", Computer Vision and Pattern Recognition (2016)
- R. Girshick, "Fast R-CNN", Proc. of the IEEE Int’l Conf. on Computer Vision, pp.1440~1448 (2015)
- S. Ren, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks", Proc. of the Int’l Conf. on Advances in Neural Information Processing Systems, pp.91~99 (2015)
- F. J. Huang, "Large-Scale Learning with SVM and Convolutional for Generic Object Categorization", Proc. of the Int’l Conf. on Computer Vision and Pattern Recognition, pp.284~291 (2006)
- J. F. Henriques, "High-Speed Tracking with Kernelized Correlation Filters", IEEE Trans. on Pattern Analysis and Machine Intelligence, 37(Issue 3), pp.583~596 (2015)
- V. Nair, "Rectified Linear Units Improve Restricted Boltzmann Machines", Proc. of the 27th Int’l Conf. on Machine Learning, pp.807~814 (2010)
- K. Diederik, "Adam: A Method for Stochastic Optimization", ArXiv preprint arXiv:1412.6980, ~ (2014)
- J. Deng, "ImageNet: A Large-Scale Hierarchical Image Database", Proc. of the Int’l Conf. on Computer Vision and Pattern Recognition, pp.248~255 (2009)