Automatic Infrared Ship Target Segmentation Based on Structure Tensor and Maximum Histogram Entropy

• Main Authors: Yongsong Li, Zhengzhou Li, Zhiquan Ding, Tianqi Qin, Weiqi Xiong
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Infrared (IR) imaging; ship target segmentation; structure tensor; maximum histogram entropy; modified watershed transform
• Online Access: https://ieeexplore.ieee.org/document/9020065/

The existing infrared (IR) ship target segmentation methods may suffer serious performance degradation in the situation of diverse background clutters and ship targets. To cope with this problem, a novel ship target segmentation method is proposed in this paper. Initially, the IR image is transformed into the map of large eigenvalues of structure tensor (STLE), where the horizon line and ship target boundary can be explicitly characterized. According to the scene context clue, the automatic horizon line detection (AHLD) is proposed to efficiently judge the existence of horizon line and remove sky/land region clutters. Then, based on the intensity distribution of ship target and sea background, the adaptive maximum histogram entropy (AMHE) is presented to accurately perceive the brightness (dark or bright) of ship target, and coarsely segment the bright or dark ship target from sea background. After that, considering the ship target boundary information, the regions-of-interest (ROI) of ship target is located and the ship foreground map (SFM) is developed to address the under-segmentation. Finally, a new Watershed algorithm namely structure tensor and maximum histogram entropy modified Watershed transform (TEWT) is constructed to completely extract the whole ship target. Extensive experiments show that the proposed method outperforms the state-of-the-art methods, especially for IR images with intricate background clutter and heavy noise. Moreover, the proposed method can work stably for ship target with unknown brightness, uneven intensities, low contrast, variable quantities, sizes, and shapes.