Abstract: The photosensitive portion of an image sensor which is used for monitoring a forward view of a vehicle on a roadway is formed that is horizontally elongated with an aspect ratio in a range from 1:1.8 to 1:3.1 adjustable in correspondence with the design speed of the roadway, the minimum radius of curvature R, the maximum longitudinal slope S of the roadway, the braking distance D of the vehicle, and the number of lanes to be imaged. Here, the aspect ratio of the photosensitive portion is set at a ratio within a range from 1:1.8 to 1:3.1 in correspondence with the conditions of the design speed of the roadway and of the number of lanes to be imaged including the lane in which the vehicle is driving.

Abstract: A picture compressing apparatus compresses pictures which are classified into three types of pictures. They are an I picture that is intra-frame coded, a P picture that is forward inter-frame coded, and a B picture that is forward/backward inter-frame coded. An apparatus controlling device checks the ID of existing CPU 2 and the CPU ID of program currently created and determines whether or not they match. When the determined result is No, the apparatus controlling device extracts a compressed code of basic modules and differential modules corresponding to the existing CPU. With reference to a code table 17, a decoder decodes the compressed codes to generate an optimun program for the existing CPU. The picture reproducing apparatus performs the similar process to that of the picture compressing apparatus.

Abstract: A method to provide automatic content-based video indexing from object motion is described. Moving objects in video from a surveillance camera 11 detected in the video sequence using motion segmentation methods by motion segmentor 21. Objects are tracked through segmented data in an object tracker 22. A symbolic representation of the video is generated in the form of an annotated graphics describing the objects and their movement. A motion analyzer 23 analyzes results of object tracking and annotates the graph motion with indices describing several events. The graph is then indexed using a rule based classification scheme to identify events of interest such as appearance/disappearance, deposit/removal, entrance/exit, and motion/rest of objects. Clips of the video identified by spatio-temporal, event, and object-based queries are recalled to view the desired video.