Real-Time Implementation of Human Detection in Thermal Imagery Based on CNN

다국어 초록 (Multilingual Abstract)

In this paper, an effective human detection method in thermal imaging is proposed using background modeling and convolution neural network(CNN). For real-time implementation, the background modeling is done by modified running Gaussian average and the CNN-based human classification is performed for only detected foreground objects. To enhance human detection accuracy, morphological operators and ellipse testing are adopted to extract Region of Interest. Also, three CNN models with different input sizes and voting method are trained using our own dataset. For real-time system, the whole system is implemented in C++ and it process more than 30 fps with high accuracy.

참고문헌 (Reference)

1 정재영, "배경 모델 갱신을 통한 코드북 기반의 전배경 분할" 한국디지털콘텐츠학회 17 (17): 375-381, 2016

2 D. C. D. Oliveira, "Towards Real-Time People Recognition on Aerial Imagery Using Convolutional Neural Networks" 27-34, 2016

3 C. H. Setjo, "Thermal image human detection using Haar-cascade classifier" 1-6, 2017

4 J. Li, "Robust pedestrian detection in thermal infrared imagery using the wavelet transform" 53 (53): 267-273, 2010

5 X. Zhao, "Robust pedestrian detection in thermal infrared imagery using a shape distribution histogram feature and modified sparse representation classification" 48 (48): 1947-1960, 2015

6 J. H. Lee, "Robust Pedestrian Detection by Combining Visible and Thermal Infrared Cameras" 15 : 10580-10615, 2015

7 F. Yin, "Realtime ghost removal for foreground segmentation methods" 2008

8 S. V. Tathe, "Real-time human detection and tracking" 1-5, 2013

9 S. V. Tathe, "Real-time human detection and tracking" 2013

10 Y. Sun, "Real-time and fast RGB-D based people detection and tracking for service robots" 1514-1519, 2016

11 C. Wren, "Pfinder : Real-time tracking of the human body" 19 (19): 780-785, 1997

12 M. Mueller, "Persistent Aerial Tracking system for UAVs" 1562-1569, 2016

13 N. K. Negied, "Pedestrians’ detection in thermal bands –Critical survey" 2 (2): 141-148, 2015

14 V. John, "Pedestrian detection in thermal images using adaptive fuzzy C-means clustering and convolutional neural networks" 246-249, 2015

15 A. Lakshmi, "Pedestrian detection in thermal images : An automated scale based region extraction with curvelet space validation" 76 : 421-438, 2016

16 B. Qi, "Pedestrian detection from thermal images : A sparse representation based approach" 76 : 157-167, 2016

17 H. Fukui, "Pedestrian detection based on deep convolutional neural network with ensemble inference network" 223-228, 2015

18 T. Kim, "Pedestrian detection at night time in FIR domain : Comprehensive study about temperature and brightness and new benchmark" 79 : 44-54, 2018

19 P. Dollar, "Pedestrian Detection : An Evaluation of the State of the Art" 34 (34): 743-761, 2012

20 Y. L. Hou, "Multispectral pedestrian detection based on deep convolutional neural networks" 1-4, 2017

21 K. Lenac, "Moving objects detection using a thermal Camera and IMU on a vehicle" 212-219, 2015

22 Tan Dat Trinh, "Improved Running Gaussian Average for Background Subtraction in Thermal Imagery" 한국정보기술학회 15 (15): 101-117, 2017

23 J. Schmidhuber, "Deep learning in neural networks : An overview" 61 : 85-117, 2015

24 Y. LeCun, "Deep Learning" 521 : 436-444, 2015

25 J. H. Kim, "Convolutional Neural Network-Based Human Detection in Nighttime Images Using Visible Light Camera Sensors" 17 (17): 1-26, 2017

26 T. Bouwmans, "Background modeling using mixture of Gaussians for foreground detection-a survey" 1 (1): 219-237, 2008

27 F. S. Leira, "Automatic detection, classification and tracking of objects in the ocean surface from UAVs using a thermal camera" 1-10, 2015

28 R. Soundrapandiyan, "Adaptive Pedestrian Detection in Infrared Images Using Background Subtraction and Local Thresholding" 58 : 706-713, 2015

29 M. H. Hung, "A fast algorithm of temporal median filter for background subtraction" 5 (5): 33-40, 2014

30 A. Sobral, "A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos" 122 : 4-21, 2014

31 N. Ogale, "A Survey of Techniques for Human Detection from Video" University of Maryland 2006