Automatic Samples Selection Using Histogram of Oriented Gradients (HOG) Feature Distance
AbstractFinding victims at a disaster site is the primary goal of Search-and-Rescue (SAR) operations. Many technologies created from research for searching disaster victims through aerial imaging. but, most of them are difficult to detect victims at tsunami disaster sites with victims and backgrounds which are look similar. This research collects post-tsunami aerial imaging data from the internet to builds dataset and model for detecting tsunami disaster victims. Datasets are built based on distance differences from features every sample using Histogram-of-Oriented-Gradient (HOG) method. We use the longest distance to collect samples from photo to generate victim and non-victim samples. We claim steps to collect samples by measuring HOG feature distance from all samples. the longest distance between samples will take as a candidate to build the dataset, then classify victim (positives) and non-victim (negatives) samples manually. The dataset of tsunami disaster victims was re-analyzed using cross-validation Leave-One-Out (LOO) with Support-Vector-Machine (SVM) method. The experimental results show the performance of two test photos with 61.70% precision, 77.60% accuracy, 74.36% recall and f-measure 67.44% to distinguish victim (positives) and non-victim (negatives).
R. Bethany, â€œRing of Fire.â€ pp. 1â€“403, 1998.
BRR, â€œACEH DAN NIAS SETAHUN SETELAH TSUNAMI Upaya Pemulihan Dan Langkah Ke Depan,â€ 2005.
I. A. Sulistijono and A. Risnumawan, â€œFrom Concrete to Abstractâ€¯: Multilayer Neural Networks for Disaster Victims Detection.â€
N. Dalal and B. Triggs, â€œHistograms of oriented gradients for human detection,â€ Proc. - 2005 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognition, CVPR 2005, vol. I, pp. 886â€“893, 2005.
T. Kobayashi, A. Hidaka, and T. Kurita, â€œSelection of histograms of oriented gradients features for pedestrian detection,â€ Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 4985 LNCS, no. PART 2, pp. 598â€“607, 2008.
Y. Uzun, M. Balcilar, K. Mahmoodi, F. Davletov, M. F. Amasyali, and S. Yavuz, â€œUsage of HoG (histograms of oriented gradients) features for victim detection at disaster areas,â€ ELECO 2013 - 8th Int. Conf. Electr. Electron. Eng., pp. 4â€“7, 2013.
C. Papageorgiou, â€œA Trainable System for Object Detection in Images and Video Sequences,â€ Int. J. Comput. Vis., vol. 38, no. 1685, pp. 15â€“33, 2000.
M. Andriluka et al., â€œVision based victim detection from unmanned aerial vehicles,â€ IEEE/RSJ 2010 Int. Conf. Intell. Robot. Syst. IROS 2010 - Conf. Proc., pp. 1740â€“1747, 2010.
V. Ferrari, M. Marin-Jimenez, and A. Zisserman, â€œProgressive Search Space Reduction for Human Pose Estimation,â€ IEEE Conf. Comput. Vis. Pattern Recognit., vol. 2, no. figure 1, pp. 1â€“8, 2008.
L. Bourdev, J. Malik, U. C. Berkeley, A. Systems, P. Ave, and S. Jose, â€œPoseletsâ€¯: Body Part Detectors Trained Using 3D Human Pose Annotations,â€ 2009 IEEE 12th Int. Conf. Comput. Vis., pp. 1365--1372, 2009.
P. Felzenszwalb, D. McAllester, and D. Ramanan, â€œA Discriminatively Trained, Multiscaled, Deformable Part Model,â€ Cvpr, pp. 1â€“8, 2008.
S. Carpin, M. Lewis, J. Wang, S. Balakirsky, and C. Scrapper, â€œUSARSim: A robot simulator for research and education,â€ Proc. - IEEE Int. Conf. Robot. Autom., pp. 1400â€“1405, 2007.
W. R. Schwartz, A. Kembhavi, D. Harwood, and L. S. Davis, â€œHuman detection using partial least squares analysis,â€ Comput. Vision, 2009 IEEE 12th Int. Conf., p. 1, 2009.
A. Bar-hillel, D. Levi, E. Krupka, and C. Goldberg, â€œLNCS 6314 - Part-Based Feature Synthesis for Human Detection,â€ Eur. Conf., pp. 127â€“142, 2010.
P. DollÃ¡r, Z. Tu, H. Tao, and S. Belongie, â€œFeature mining for image classification,â€ Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., no. July, 2007.
P. DollÃ¡r, Z. Tu, P. Perona, and S. Belongie, â€œIntegral Channel Features,â€ BMVC 2009 London Engl., pp. 1â€“11, 2009.
P. Dollar, S. Belongie, and P. Perona, â€œThe Fastest Pedestrian Detector in the West,â€ Proceedings Br. Mach. Vis. Conf. 2010, p. 68.1-68.11, 2010.
S. Walk and N. Majer, â€œ[Poster]New Features and Insights for Pedestrian Detection,â€ Training, pp. 8â€“8.
C. Wojek and B. Schiele, â€œA performance evaluation of single and multi-feature people detection,â€ Jt. Pattern Recognit. Symp., pp. 82â€“91, 2008.
A. Satpathy, X. Jiang, and H. L. Eng, â€œHuman detection by quadratic classification on subspace of extended histogram of gradients,â€ IEEE Trans. Image Process., vol. 23, no. 1, pp. 287â€“297, 2014.
P. DollÃ¡r, C. Wojek, B. Schiele, and P. Perona, â€œPedestrian detection: An evaluation of the state of the art,â€ IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 4, pp. 743â€“761, 2012.
S. Munder and D. M. Gavrila, â€œAn experimental study on pedestrian classification,â€ IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 11, pp. 1863â€“1868, 2006.
D. S. Bolme, Y. M. Lui, B. a. Draper, and J. R. Beveridge, â€œSimple real-time human detection using a single correlation filter,â€ 2009 Twelfth IEEE Int. Work. Perform. Eval. Track. Surveill., pp. 1â€“8, 2009.
D. S. Bolme, B. A. Draper, and J. R. Beveridge, â€œAverage of synthetic exact filters,â€ 2009 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work. CVPR Work. 2009, pp. 2105â€“2112, 2009.
S. Soo, â€œObject detection using Haar-cascade Classifier,â€ vol. 2, no. 3, pp. 1â€“12, 2014.
Copyright (c) 2018 EMITTER International Journal of Engineering Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The copyright to this article is transferred to Politeknik Elektronika Negeri Surabaya(PENS) if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to PENS. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment. The copyright transfer form can be downloaded here .
The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.
Plagiarism screening will be conducted by EMITTER Journal Editorial Board using iThenticate Plagiarism Checker and CrossCheck plagiarism screening service. Author should download and signing declaration of plagiarism form here and resubmit it with copyright transfer form via online submission.