Real-time image segmentation is a critical part of an automatic target recognizer (ATR). The segmentation of poorly resolved targets in low contrast thermal video images is a challenging task. Most edge-based segmenters are too susceptible to noise, contrast variation, and target boundary discontinuity. The problem is the lack of a fast (video rate) and robust method of grouping the relevant edge elements together while rejecting the irrelevant ones. The authors have overcome this problem by combining the processing power of a single instruction multiple data (SIMD) computer with a newly developed model-directed segmentation algorithm.
Parallel algorithm for model-directed real-time image segmentation
Ein paralleler Algorithmus für modellgeleitete Realzeit-Bildsegmentierung
Proceedings of SPIE, Real-Time Image Processing II ; 1295 ; 2-7
1990
6 Seiten, 4 Bilder, 8 Quellen
Aufsatz (Konferenz)
Englisch
CNN-based Fisheye Image Real-Time Semantic Segmentation
IEEE | 2018
|British Library Online Contents | 2002
|Real-time image segmentation for visual inspection of pharmaceutical tablets
British Library Online Contents | 2011
|