Translator Disclaimer
22 September 1997 Automatic detection of targets using hierarchical spatial/temporal processing
Author Affiliations +
Proceedings Volume 3110, 10th Meeting on Optical Engineering in Israel; (1997)
Event: 10th Meeting on Optical Engineering in Israel, 1997, Jerusalem, Israel
An algorithm for automatic target detection has been developed.An image is processed using a pyramidal structure in a two stage process. Each frame is spatially filtered to identify potential target areas. The temporal behavior of blobs identified is analyzed; targets are declared where blobs exhibit motion consistent with targets of interest. Targets of different sizes are detected at different pyramid levels. A single target will usually be detected at several levels. Integration of information from the various levels is essential. Two data merging approaches were examined. The first projects blobs from each level to the pyramid base. Blobs exhibiting target-like behavior are extracted. The second innovative approach builds tracks on each level. Only blobs jointed to tracks are projected to the base. Tracks are formed on these projections. Targets are declared on tracks that achieve a given quality. This hierarchical approach permits the system to operate with great sensitivity. False detections are eliminated at two stages. Most spurious blobs will not form tracks at the pyramid levels and will not be projected to the base. Tracking at the base eliminates others. Experimental results demonstrate high detection probability and low false alarm rate under a wide variety of conditions.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Eliezer Haber and Yehuda Sylman "Automatic detection of targets using hierarchical spatial/temporal processing", Proc. SPIE 3110, 10th Meeting on Optical Engineering in Israel, (22 September 1997);


Back to Top