Human Detection On Foggy Images
Somavarapu Priyanka1, Dommeti Sri Divya Sahithi2, Lella SriTeja3, S.Sunitha4
1Somavarapu Priyanka, Student, B.Tech, IT Depatment,VR Engineering College,Vijayawada, A.P, India.
2Dommeti Sri Divya Sahithi, Student, B.Tech, IT Depatment,VR Engineering College,Vijayawada, A.P, India.
3Lella SriTeja, Student, B.Tech, IT Depatment,VR Engineering College,Vijayawada, A.P, India.
4Mrs.S.Sunitha, Assistant Professor, IT Depatment,VR Engineering College,Vijayawada, A.P, India.
Manuscript received on February 05, 2019. | Revised Manuscript received on February 14, 2019. | Manuscript published on August 30, 2019. | PP: 3637-3640 | Volume-8 Issue-6, August 2019. | Retrieval Number: F9364088619/19©BEIESP | DOI: 10.35940/ijeat.F9364.088619
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper was discussing about the human detection using SVM combining weighted least square-filter (WLS), histograms of oriented gradients (HOG). The combination of HOG and SVM is a powerful approach for human detection, as it uses local strength gradients; it is hard to handle noisy and foggy images. For removing of noise or fog from this type of images, we used weighted least square (WLS) filter, and then HOG and SVM algorithms are used for human detection. Due to deprived weather conditions such as fog and haze, the acquired images will exhibit damaged visibility. This can be occurred because of the presence of the suspended particles and scatter of light between objects and the camera. So the image improvement and renewal methods are used to improve the quality of an image which provide strong image in poor weather condition and can extract features from the images not only when they had illumination variations but also when they are degraded with fog. At last, detected objects can be categorized into predefined groups of humans and other objects by using SVM classifier.
Keywords: HOG and SVM classifier, human detection, WLS filter