
Research on image saliency target detection in fog and haze weather based on improved FT algorithm
Author(s) -
Shanglian Huang
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/772/1/012083
Subject(s) - haze , salient , computer science , algorithm , artificial intelligence , computer vision , remote sensing , meteorology , geography
The increase of air turbidity in fog and haze weather is not conducive to the accurate extraction of image feature information of important salient targets such as vehicles and pedestrians, nor is it conducive for drivers to make correct judgment on the road environment ahead of their vision. Therefore, this paper proposes an improved FT algorithm in fog and haze weather. This algorithm firstly uses the Retinex algorithm to remove fog and haze and restore color of fog and haze weather images, then uses FT algorithm to detect the saliency of the target, and finally completes the simulation based on MATLAB platform. It can be seen from the simulation results that the improved FT algorithm is significantly better than the effect of using the traditional FT algorithm, which means that the improved FT algorithm has a better role in helping drivers to detect road salient targets in fog and haze weather. And this improvement has a strong practical value for reducing the incidence of traffic accidents in fog and haze weather.