Abstract: A method and apparatus for classifying objects in images utilize means for selecting portions of those images which contain objects and means for classifying those objects based upon parameters of the selected portions, which parameters are useful for classifying the objects. The selecting means preferably is a shadow and highlight detector, a statistical window detector and a neural network window detector whose output is combined in a combined cuer. The parameters are determined from the greylevels and positions of pixels using one or more modules which perform certain mathematical operations on this data. Such parameters include edge parameters, smoothness, clutter, presence and characteristics of highlights and shadows, and texture. The invention is particularly useful for classifying objects in sonar images as natural or man-made.

Abstract: A method of locating objects in sonar images so that matching algorithms can be used to determine if the same objects appear in two images. Information from the matching algorithms can then be used to upgrade the position of the vehicle and objects recorded in the vehicle's navigation system. Images are improved by normalizing brightness and contrast and then convolving the image with at least one filter. The image is normalized by dividing the image into vertical strips, creating a histogram to represent the grayness values for columns of pixels in each strip and applying an algorithm to each strip to change its grayness value.