The author presents an image pyramidal approach for representing and locating moving obstacles in the visual guidance of navigation for mobile robots or autonomous land vehicles. The algorithm is based on the utilization of a structural representation of the image in pyramids. A thresholding and mapping scheme for generating the structural pyramids is described. Obstacles are represented and located in terms of the grid cells in structural pyramids. Orthogonal projections are applied to calculate the velocity and acceleration of the moving objects and predict possible collision.