Vehicle detection in aerial surveillance using morphological shared-pixels neural (MSPN) networks

Abstract

Vehicle detection from aerial images is becoming an increasingly important research topic in surveillance, traffic monitoring and military applications. The system described in this paper focuses on automatic vehicle detection in the aerial images. This paper introduces a morphological neural network approach to extract vehicle targets from high resolution aerial images. In the approach the Morphological Shared-Pixels Neural Network (MSPN) is used to classify image pixels on roads into vehicle targets and non-vehicle targets, and a morphological preprocessing algorithm is developed to identify candidate vehicle pixels. The proposed method is going to compare with the existing system Dynamic Bayesian Network(DBN). It is going to be proven that the experimental results in MSPN have a good detection performance. The proposed system is going to record all pixel value of aerial images sequentially and filter out the batch or portion of the several vehicle edges. This method is quite better than existing algorithms in identifying the vehicles automatically in aerial images.