Spatial and temporal features selection for low-altitude target detection

摘要: Abstract Target detection in plane position indicator (PPI) radar images aims at separating moving targets from complicated background image. Background subtraction is a powerful mechanism for such applications. Since there still much clutter left the foreground image after subtraction, an optimal classification (OCP) should be constructed to distinguish clutters. Due complexity and variability of images, threshold value each OCP selected adaptively corresponding pixel In this paper, novel method proposed improve results with spatial temporal features PPI sequence. Firstly, select thresholds adaptively, new formula developed two statistical models. The statistics model reflect aggregation degree concerned pixels, while those their relative positions. Secondly, further reduce false alarm rate, strategy based on incorporated modify OCP. Our parameter values compared other successful techniques target detection. Quantitative evaluations show that provides better results.