Detection of Sewage Discharge by Density Peak Search and Differential Expression Analysis
2019
Weiguo Sun, Xudong Zhao and Hong Chen
Nowadays, water pollution is a part of the major environmental problems. Industrial sewage that does not meet the emission standards will pollute the surface water and groundwater when it is discharged into water bodies, causing serious adverse impacts on human beings and environment. In view of industrial sewage privately discharged without properly monitoring, we present a method for detection of sewage discharge using clustering and differential analysis on image sequences derived from satellite photos taken when focusing on a certain place. The proposed method helps to indicate key images containing sewage, make the sewage area and leave evidence for the retrospective incident. Clustering based on the search of fast density peaks is used for detecting images containing sewage. In addition, two sample’s t-test and Fisher linear discriminant analysis are combined to extract the key pixels representing the area of sewage discharge. Experiments were made on 200 images corresponding to a certain area at different times of the day and 25 key frames with areas labelled to be sewage discharge were extracted, which indicated the effectiveness of this method.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Directory of Open Access Journals
Découvrez la collection de ce fournisseur de données dans AGRIS
