Istrazivanja i projektovanja za privreduJournal of Applied Engineering Science


DOI: 10.5937/jaes18-24786
This is an open access article distributed under the CC BY-NC-ND 4.0 terms and conditions. 
Creative Commons License

Volume 18 article 692 pages: 301 - 304

Mihaela Bukljas*
University of Zagreb, Faculty of Transport and Traffic science, Zagreb, Croatia

Ivan Pavic
University of Split , Faculty of Maritime Studies, Split, Croatia

Pero Vidan
University of Split , Faculty of Maritime Studies, Split, Croatia

Srdjan Vuksa
University of Split , Faculty of Maritime Studies, Split, Croatia

Aerial images taken during terrain mapping can be affected with a foggy weather. In this paper we proposed new fog detection method and image rejection using single neuron. Fog detection is based on statistical data collected by converting color image to grayscale image and then applying gamma correction factor. With this statistical data, training dataset is created for single neuron. Neuron is simple two input neuron with sigmoid activation function. We establish connection with single neuron and statistical data so it can recognize is there presence of fog in aerial image.

View article

1.Robert A. Houze, Jr. “Cloud Dynamics”, Academic Press, In. 1250 Sixth Avenue, San Diego, California 92101-4311 p. xiii, 1994.

2. S. Waharte and N. Trigoni, “Supporting search and rescue operations with UAVs,” in Proceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems, 2010.

3. Wang F. Wang W. “Road extraction using modifi ed dark channel prior and neighborhood FCM in foggy aerial images”, Springer Science+Bussines Media, LLC, part of Springer Nature 2018.

4. Negru M. Nedveschi S. “Image Based Fog Detection and Visibility Estimation for Driving Assistance Systems” 2013 IEEE 9th International Conference on Intelligent Computer Communication and Processing (ICCP), 2013.

5. S. G. Narasimhan, S. K. Nayar, “Shedding light on the weather. In Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition (CVPR'03). IEEE Computer Society, Washington, DC, USA, pp. 665-672.

6. Tan, R.T., "Visibility in bad weather from a single image", IEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008, pp.1-8, 23- 28 June 2008.

7. Kaiming He, Jian Sun, Xiaoou Tang, "Single image haze removal using dark channel prior," IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp.1956-1963, 20-25 June 2009.

8. Tarel, J–P., Hauticre, N., Cord, A., Gruyer, D., Halmaoui, H., "Improved visibility of road scene images under heterogeneous fog," Intelligent Vehicles Symposium (IV), 2010 IEEE, pp.478-485, 21-24 June 2010.

9. G. Pagani, W. Wauben, J.W. Noteboom, „Neural network approach for automatic fog detection using surveillance camera images“ Geophysical esearch Abstracts Vol. 20, EGU2018-2988, 2018

10. J. Mao, U. Phommasak, S. Watanabe, H. Shioya, “Detecting Foggy images and Estimating the Haze Degree Factor“, Mao et al., J ComputSciSystBiol 2014.

11. S. Mengyun, X. Fengying, Z. Yue, Y. Jihao, “Cloud detection of remote sensing images by deep learning” 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

12. C. Bolun, X. Xiangmin, J. Kui, Q. Chunmei, T. Dacheng, “DehazeNet: An End-to-End System for Single Image Haze Removal”, Computer Vision and Pattern Recognition (cs.CV) 2016.