An improved snake model for automatic extraction of buildings from urban aerial images and LiDAR data

Automatic extraction of objects from images has been a topic of research for decades. The main aim of these researches is to implement a numerical algorithm in order to extract the planar objects such as buildings from high resolution images and altitudinal data. Active contours or snakes have been extensively utilized for handling image segmentation and classification problems. Parametric active contour (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. The snake deforms itself from its initial position into conformity with the nearest dominant feature by minimizing the snake energy. The snake energy consists of two main forces, namely: internal and external forces. The coefficients of internal and external energy in snake models have important effects on extraction accuracy. These coefficients together control the weights of the internal and external energy. The coefficients also control the snake’s tension, rigidity, and attraction, respectively. In traditional methods, these weight coefficients are adjusted according to the user’s emphasis. This paper proposes an algorithm for optimization of these parameters using genetic algorithm. Here, we attempt to present the effectiveness of Genetic Algorithms based on active contour, with fitness evaluation by snake model. Compared with traditional methods, this algorithm can converge to the true coefficients more quicker and more stable, especially in complex urban environments. Experimental results from used dataset have 96% of overall accuracy, 98.9% of overall accuracy and 89.6% of k-Factor.