No abstract

The automatic extraction of objects from data and images has been a topic of research for decades. This paper proposes an improved snake model that focuses on automatic feature extraction from colour aerial images and satellite images data. A snake is defined as an energy minimizing spline guided by external constraint forces and influenced by image forces that pull it toward features such as lines or edges. Based on the radiometric and geometric behaviours of feature, the snake model is modified in two areas: the criteria for the selection of initial seeds and the external energy function. The proposed snake model includes a new height similarity energy factor and regional similarity energy. The snake approaching the object contours. Compared with the traditional snake model, this algorithm can converge to the true feature contours more quickly and more stably, especially in feature environments. Examination of the results shows that wetland feature extracted from a dense and complex area using supervised classification shape accuracy, whereas the improved automatic feature extraction method has a good shape and area accuracy.