Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
An Improved Fog Concentration Detection Method for Waterway Based on FADE
Ist Teil von
2022 Global Conference on Robotics, Artificial Intelligence and Information Technology (GCRAIT), 2022, p.820-824
Ort / Verlag
IEEE
Erscheinungsjahr
2022
Link zum Volltext
Quelle
IEEE Xplore
Beschreibungen/Notizen
.- The frequent occurrence of foggy weather greatly impacts the water transportation system, so it is essential to detect fog concentration. Therefore, we introduce and improve an approach of Fog Aware Density Evaluator (FADE) to specifically detect fog concentration in waterways. First, we test a series of fog-related features on the synthesized foggy waterway images. Second, we propose a novel set of features with the addition of two new ones, namely color value in HSV color space, and gray standard deviation. Finally, based on the feature set, the fog concentration of the image patch and the whole image can be obtained using our proposed method, and the fog concentration distribution map can be derived from the fog concentration of image patches. Experimental results show that the method has higher accuracy than FADE in detecting the whole fog concentration of waterway images.