Intensity Weighted Histogram Equalization Method for Night Vision
AbstractThis paper explores the possibility of utilizing histogram equalization on images captured in poor lighting conditions in order to expand their histogram dynamic range, enhancing their contrast and effectively provide night vision for such images. Then, some drawbacks of standard histogram equalization for dark images, caused mainly due to the clustering of pixels around the lowest intensities are exposed, and Enhanced Intensity Weighted Histogram Equalization is presented as a solution to obtain more realistic night vision images by incorporating the normalized weight of each pixel intensity into the calculations and spreading the histogram values to fill in the gaps, reducing noisy high frequency changes. This technology can be applied to new capture devices that detect the lack of illumination and engage Enhanced Intensity Weighted Histogram Equalization to provide low light capture, useful for surveillance, driving, medical imaging, and even space exploration.
(1) A. Waxman, D. Fay, P. Ilardi, D. Savoye, R. Biehl, D. Grau, "Sensor Fused Night Vision: Assessing Image Quality in the Lab and in the Field," 9th International Conference on Information Fusion, 2006, pp. 1-8.
(2) C. K. Teo, "Digital Enhancement of Night Vision and Thermal Images," Thesis, Naval Postgraduate School. Monterey, California, USA. 2003.
(3) D. Fay, P. Ilardi, N. Sheldon, D. Grau, R. Biehl, A. Waxman, "Real-time image fusion and target learning & detection on a laptop attached processor," International Conference on Information Fusion, 2005, pp. 499-506.
(4) F. Schule, R. Schweiger, K. Dietmayer, "Augmenting Night Vision Video Images with Longer Distance Road Course Information," Intelligent Vehicles Symposium (IV), 2013 IEEE, pp. 1233-1238.
(5) International Telecommunications Union. (2015). BT.601: Studio encoding parameters of digital television for standard 4:3 and wide screen 16:9 aspect ratios [Online]. Available: http://www.itu.int/rec/R-REC-BT.601-7-201103-I/en
(6) M. Serfling, O. Loehlein, R. Schweiger, K. Dietmayer, "Camera and Imaging Radar Feature Level Sensorfusion for Night Vision Pedestrian Recognition," Intelligent Vehicles Symposium, 2009 IEEE, pp. 597-603.
(7) N. Sapkota, "Real Time Digital Night Vision Using Nonlinear Contrast Enhancement," MS Thesis. UNLV Theses/Dissertations/Professional Papers/Capstones. 2013.
(8) R. C. Gonzalez and R. E. Woods, "Histogram Equalization," in Digital Image Processing, 3rd ed., UP, India: Prentice Hall, 2007, pp. 122–128.
(9) S. D. Chen and R. Ramli, "Contrast Enhancement using Recursive
Mean-Separate Histogram Equalization for Scalable Brightness Preservation," IEEE Trans. Consumer Electronics. vol. 49, no. 4, pp. 1301-1309, 2003.
(10) Y.T. Kim, "Contrast Enhancement Using Brightness Preserving Bi-Histogram Equalization," IEEE Trans. Consumer Electronics, vol. 43, no. 1, pp. 1-8, Feb. 1997.
(11) Z. Yu, W. Xiqin, and P. Yingning, "New image enhancement algorithm for night vision," ICIP 99. Proceedings. 1999 International Conference on Image Processing, vol. 1, pp. 201-203, 1999.