CONCURRENT SELF-ORGANIZING MAPS FOR PEDESTRIAN DETECTION IN THERMAL IMAGERY

被引：0

作者：

Ciotec, Adrian-Dumitru ^{[1
]}

Neagoe, Victor-Emil ^{[1
]}

Barar, Andrei-Petru ^{[1
]}

机构：

[1] Univ Politehn Bucuresti, Fac Elect Telecommun & Informat Technol, Bucharest, Romania

来源：

UNIVERSITY POLITEHNICA OF BUCHAREST SCIENTIFIC BULLETIN SERIES C-ELECTRICAL ENGINEERING AND COMPUTER SCIENCE | 2013年 / 75卷 / 04期

关键词：

pedestrian detection; thermal imagery; night vision; concurrent selforganizing maps (CSOM); histogram of oriented gradients (HOG);

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The paper presents an original approach for pedestrian detection in thermal imagery using Histogram of Oriented Gradients (HOG) for feature extraction and the neural network classifier called Concurrent Self-Organizing Maps (CSOM), previously introduced by first author. The proposed algorithm has the following main stages: (a) detection of the regions of interest (ROI); (b) feature selection using the Histogram of Oriented Gradients (HOG; (c) classification using a CSOM classifier with several neural modules for each class; (d) decision fusion of the SOM modules into the two final classes: pedestrians and non-pedestrians. For training and testing the proposed algorithm, we have used the OTCBVS - OSU Thermal Pedestrian Database provided by the Ohio State University. After optimizing HOG descriptors parameters we obtains the False Positive Error Rate (FPER) of 1.79%, the False Negative Error Rate (FNER) of 0.49% and the Total Success Rate (TSR) of 98.48 %.

引用

页码：45 / 56

页数：12

共 50 条

[1] Concurrent self-organizing maps for classification of multispectral satellite imagery
Neagoe, VE
Ropot, AD
6TH WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL XIV, PROCEEDINGS: IMAGE, ACOUSTIC, SPEECH AND SIGNAL PROCESSING III, 2002, : 126 - 131
[2] Using self-organizing maps for anomaly detection in hyperspectral imagery
Penn, BS
2002 IEEE AEROSPACE CONFERENCE PROCEEDINGS, VOLS 1-7, 2002, : 1531 - 1535
[3] Concurrent Self-Organizing Maps for pattern classification
Neagoe, VE
Ropot, AD
FIRST IEEE INTERNATIONAL CONFERENCE ON COGNITIVE INFORMATICS, PROCEEDINGS, 2002, : 304 - 312
[4] Self-organizing maps for outlier detection
Munoz, A
Muruzabal, J
NEUROCOMPUTING, 1998, 18 (1-3) : 33 - 60
[5] A new method of pipeline detection in sonar imagery using self-organizing maps
Puttipipatkajorn, A
Jouvencel, B
Salgado-Jimenez, T
IROS 2003: PROCEEDINGS OF THE 2003 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, 2003, : 541 - 546
[6] Novelty detection using Self-Organizing Maps
Ypma, A
Duin, RPW
PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 1322 - 1325
[7] Concurrent Self-Organizing Maps for Supervised/Unsupervised Change Detection in Remote Sensing Images
Neagoe, Victor-Emil
Stoica, Radu-Mihai
Ciurea, Alexandru-Ioan
Bruzzone, Lorenzo
Bovolo, Francesca
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2014, 7 (08) : 3525 - 3533
[8] Using self-organizing maps to identify patterns in satellite imagery
Richardson, AJ
Risien, C
Shillington, FA
PROGRESS IN OCEANOGRAPHY, 2003, 59 (2-3) : 223 - 239
[9] Self-Organizing Maps approach to object localization in sonar imagery
Amornrit, P
Jouvencel, B
PROCEEDINGS OF THE 11TH INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS 2003, VOL 1-3, 2003, : 1172 - 1177
[10] Concurrent self-organizing maps for multispectral facial image recognition
Neagoe, Victor-Emil
Mugioiu, Alexandru-Cristian
Tudoran, Cristian-Tudor
2007 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN IMAGE AND SIGNAL PROCESSING, 2007, : 330 - 335

← 1 2 3 4 5 →