A detection method for reservoir waterbodies vector data based on EGADS

Abstract

Abstract Owing to the effects of camera, illumination, extraction algorithm defect, and other reasons, vector data for reservoir waterbodies extracted from remote sensing data may have quality issues, impacting the efficiency of data utilization in areas such as water resource management and reservoir monitoring. To efficiently detect abnormal data from massive vector products of reservoir waterbodies, a semi-automatic detection method for reservoir waterbody vector data is presented. The method has three phases. First, the original reservoir vector data are preprocessed to obtain the time series of the area of reservoir waterbodies. Second, data modeling with time series of reservoir waterbodies area data is done using the extensible generic anomaly detection system (EGADS) plug-in framework and time series modeling is conducted using the Olympic model. Third, data that have quality problems are identified with K σ K\sigma model was used to determine the outliers; thereby, the date of the outliers is detected. Results of accuracy verification show that the sensitivity and specificity of the method were 94.44 and 83.87%, respectively, showing its feasibility for use in anomaly detection in polygonal reservoir waterbody vector data with far greater efficiency than traditional manual inspection.