Doney Alex
ABSTRACT
Detecting people from a top view video feed is comparatively a more difficult problem than pedestrian detection especially on a real time system, as the perceived 2D shape of person from the overhead view is of widely varying nature due to perspective distortions with almost no unique discernible outline shape. Therefore the amount of information available from overhead view is very less. Also, there is a lot of rotational variation of the data from top view. However the advantage of having such a detector is that for a tracking application there would be little occlusion. Hence, this problem is worthy of specialised attention. In recent times there are many deep learning based approaches, but all of them are computationally expensive. We present a method to effectively train a computationally light AdaBoost classifier based detector, which uses the limited amount of information and can give a high accuracy running on a light embedded platform such as Raspberry Pi 3B.
- J. Begard, N. Allezard, and P. Sayd. 2008. Real-time human detection in urban scenes: Local descriptors and classifiers selection with AdaBoost-like algorithms. In 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 1--8.Google Scholar
- Ben Benfold and Ian Reid. 2009. Guiding Visual Surveillance by Tracking Human Attention. In Proc. BMVC. 14.1--14.11.Google ScholarCross Ref
- P. Cerri, L. Gatti, L. Mazzei, F. Pigoni, and H. G. Jung. 2010. Day and night pedestrian detection using cascade AdaBoost system. In 13th International IEEE Conference on Intelligent Transportation Systems. 1843--1848.Google Scholar
- I. Cohen, A. Garg, and T. S. Huang. 2000. Vision-based overhead view person recognition. In Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, Vol. 1. 1119--1124 vol.1. Google ScholarDigital Library
- N. Dalal and B. Triggs. 2005. Histograms of oriented gradients for human detection. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), Vol. 1. 886--893 vol. 1. Google ScholarDigital Library
- Xiaofan Xu Dexmont Pena, Andrew Forembski and David Moloney. 2017. Benchmarking of CNNs for Low-Cost, Low-Power Robotics Applications. (2017). http://juxi.net/workshop/deep-learning-rss-2017/papers/Pena.pdfGoogle Scholar
- P Dollar. {n. d.}. Piotr's Computer Vision Matlab Toolbox (PMT). ({n. d.}).https://github.com/pdollar/toolboxGoogle Scholar
- P. Dollar, R. Appel, S. Belongie, and P. Perona. 2014. Fast Feature Pyramids for Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 8 (Aug 2014), 1532--1545. Google ScholarDigital Library
- Piotr Dollar, Serge Belongie, and Pietro Perona. 2010. The Fastest Pedestrian Detector in the West. In Proc. BMVC. 68.1--11.Google ScholarCross Ref
- Piotr Dollar, Zhuowen Tu, Pietro Perona, and Serge Belongie. 2009. Integral Channel Features. In Proc. BMVC. 91.1--91.11.Google ScholarCross Ref
- P. Dollar, C. Wojek, B. Schiele, and P. Perona. 2009. Pedestrian detection: A benchmark. In 2009 IEEE Conference on Computer Vision and Pattern Recognition. 304--311.Google Scholar
- DT42. 2017. Run Object Detection using Deep Learning on Raspberry Pi 3(1). (2017). https://medium.com/dt42/run-object-detection-using-deep-learning-on-raspberry-pi-3-1-55027eac26c3Google Scholar
- Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. (04-2017).Google Scholar
- Intel. 2017. Intel Movidius Neural Compute Stick. (2017). https://developer.movidius.com/Google Scholar
- Sarthak Jain. 2018. How to easily Detect Objects with Deep Learning on Raspberry Pi. (2018). https://medium.com/nanonets/how-to- easily- detect- objects- with- deep- learning- on-raspberrypi- 225f29635c74Google Scholar
- Rudolph Emil Kalman. 1960. A New Approach to Linear Filtering and Prediction Problems. Transactions of the ASME-Journal of Basic Engineering 82, Series D (1960), 35^5.Google Scholar
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. SSD: Single Shot MultiBox Detector. In Computer Vision - ECCV 2016, Bastian Leibe, Jiri Matas, NicuSebe, and Max Welling (Eds.). Springer International Publishing, Cham, 21--37.Google Scholar
- Carlos A. Luna, Cristina Losada-Gutierrez, David Fuentes-Jimenez, Alvaro Fernandez-Rincon, Manuel Mazo, and Javier Macias-Guarasa. 2017. Robust people detection using depth information from an overhead Time-of-Flight camera. Expert Systems withApplications 71 (2017), 240--256. Google ScholarDigital Library
- James Munkres. 1957. ALGORITHMS FOR THE ASSIGNMENT AND TRANS- PORTATIONPROBLEMS. (1957).Google Scholar
- Vinod Nair, Pierre-Olivier Laprise, and James J. Clark. 2005. An FPGA-based People Detection System. EURASIP J. Appl Signal Process.2005(Jan.2005), 1047--1061. Google ScholarDigital Library
- AznulQalid Md Sabri NouarAlDahoul and Ali Mohammed Mansoor. 2018. RealTime Human Detection for Aerial Captured Video Sequences via Deep Models. (2018).Google Scholar
- O. Ozturk, Toshihiko Yamasaki, and KiyoharuAizawa. 2009. Tracking of humans and estimation of body/head orientation from top-view single camera for visual focus of attention analysis. In 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops. 1020--1027.Google ScholarCross Ref
- YanweiPang, YuanYuan, XuelongLi, and JingPan. 2011. EfficientHOGhuman detection. Signal Processing 91, 4 (2011), 773--781. Google ScholarDigital Library
- J. Redmon, S. Divvala, R. Girshick, and A. Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In 2016 IEEE Conference on Computer Vision andPatternRecognition (CVPR). 779--788.Google Scholar
- Thiago T. Santos and Carlos H. Morimoto. 2011. Multiple camera people detection and tracking using support integration. Pattern Recognition Letters 32, 1 (2011), 47--55. Image Processing, Computer Vision and Pattern Recognition in Latin America. Google ScholarDigital Library
- T. E. Tseng, A. S. Liu, P. H. Hsiao, C. M. Huang, and L. C. Fu. 2014. Real-time people detection and tracking for indoor surveillance using multiple top-view depth cameras. In 2014IEEE/RSJInternational Conference on IntelligentRobots and Systems. 4077--4082.Google Scholar
- TimvanOosterhout, SanderBakkes, andBenKrAfise. 2011. HEAD DETECTION IN STEREO DATA FOR PEOPLE COUNTING AND SEGMENTATION. InProceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011). INSTICC, SciTePress, 620--625.Google Scholar
- P. Viola and M. Jones. 2001. Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, Vol. 1.1-511-I-518 vol.1.Google Scholar
- ZhognchuanZhangandF. Cohen. 2013. 3D pedestrian tracking based on overhead cameras. In 2013 Seventh International Conference on Distributed Smart Cameras (ICDSC). 1--6.Google Scholar
- Qiang Zhu, Mei-Chen Yeh, Kwang-Ting Cheng, and Shai Avidan. 2006. Fast Human Detection Using a Cascade of Histograms of Oriented Gradients. In Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR '06). IEEE Computer Society, Washington, DC, USA, 1491--1498. Google ScholarDigital Library
Index Terms
- Optimisation of Feature Space for People Detection from TopView on Light Embedded Platform
Recommendations
Top View Person Detection and Counting for Low Compute Embedded Platforms
ICVIP '18: Proceedings of the 2018 2nd International Conference on Video and Image ProcessingIn this paper, we present an optimised approach for the top-view person detection and counting for low compute embedded platform. Earlier methods have used background subtraction for top-view detection which produces inaccurate results due to merging of ...
Learning Optimal Embedded Cascades
The problem of automatic and optimal design of embedded object detector cascades is considered. Two main challenges are identified: optimization of the cascade configuration and optimization of individual cascade stages, so as to achieve the best ...
Credit card fraud detection using ensemble data mining methods
AbstractNowadays, credit card fraud has become one of the most complex and vital issues in the world, even more than the past decades. Widespread use of credit cards is one of the most attractive forms of online transactions in the banking sector. Credit ...
Comments