A clutter-adaptive target-detection method is proposed to detect small moving targets in midwave infrared maritime scenarios. In particular, we focus our attention on the sea-sky background and targets of interest are ships along the horizontal sea-sky line. In the distant sea-sky background infrared imagery, small targets frequently appear as weak intensity and do not have enough structure information in the vicinity of horizontal sea-sky-line, that is sea-sky region, and the complexity of background clutters has direct impact on the target detection performance. Thus, a fuzzy system constructed by the extracted image-based features is designed for the clutter classification. And then, based on the determined clutter type, low clutter or high clutter, the horizontal sea-sky line can be detected successfully. In the target detection stage, under the guidance of the sea-sky line, a modified multilevel filter method is applied to enhance the target in the sea-sky region. Finally, the recursive segmentation method and the target validation technique are adopted for the target extraction and validation. In the experiments, the target detection performance of proposed method is validated by extensive experiments on infrared images taken in different imaging conditions. It achieves high accuracy with a low false alarm rate.
This paper proposes a robust detection and tracking method that can detect and track ship targets in cluttered forward looking infrared image sequences. The proposed method includes two major steps, target detection and target tracking. Because the target's imaging size will be scaled-up gradually along with the imaging distance being reduced, the target's imaging process is analyzed in detail and the target's imaging size is estimated in real-time. Based on the estimation of the target's imaging size, the targets with different imaging sizes can be treated as small targets by image scaling operation and detected successfully using the improved multilevel filter and iterative segmentation technique. In the tracking stage, the histogram back-projection technique, which has little effect on the movement of the camera, is applied to the mean shift procedure for real-time application. Extensive experiments demonstrate the utility and the performance of the proposed approach.
A clutter suppression algorithm called the rectification filter with indications of bidirectional local binary patterns (BDLBP-RF) is proposed as a resolution to the problem of detecting dim targets in infrared (IR) image sequences. First of all, a local binary pattern (LBP) operator with properties of grayscale and rotation invariance is introduced in the application of clutter suppression. Each pixel in the image is estimated by its spatial neighbor pixels and the corresponding LBPs in prior and posterior frames. The approach proposed is based on a spatiotemporal process, in which interframe and intraframe properties of the IR image sequence are both taken into account. The method is evaluated by the comparative experiments, and the LBP operator's optimum values of radius and number of neighbors are discussed. The results of the experiment prove that BDLBP-RF has excellent performance and stability in clutter suppression under various situations. The target point in images processed by our approach received high signal-to-clutter ratio gain, and the detectability of the target is enhanced.
By the analysis of the IR imaging characteristics of small marine targets in complex sea background, the small marine
targets always appear in the region nearby the sea-sky-line, to improve real-time execution and eliminate the ostensible
alarm, the key step of the small sea target detection is to extract and localize the sea-sky-line. Thus, a reliable method of
sea-sky-line detection in complex sea background is proposed in this paper. Firstly, medium filter and discrete wavelet
transformation (DWT) are adopted to suppress the noise and enhance the contrast; Secondly, the low frequency
subimage (cA)and horizontal detail subimage(cH) produced by DWT are combined to extract potential sea-sky-line in
the IR image; then the validation technique is adopted to distill the veritable sea-sky-line. The experiment result shows
that our method can localize the sea-sky-line precisely, and has strong robustness and higher detection efficiency.
In complex sea background, the ship target in the IR image often appears near the sea-sky region, and the sea-sky region
is appeared as a horizontal or nearly horizontal block region, so the primary step of the IR target detection is to localize
the sea-sky region. According to this characteristic of the target and background in the IR image, a detection algorithm
for IR ship target detection in complex sea background is proposed in this paper. Firstly, the low frequency subimage
and horizontal detail subimage is obtained by the multi-scale analysis of wavelet transform. Secondly, the gray
projection and binary clustering segmentation method are combined to localize the sea-sky-line in the image, the target
potential area, that is, sea-sky-region, is also determined. Finally, the multi-level filter method is adopted to detect the
ship target in the sea-sky region. The experiment result show that this algorithm can effectively reduce the computational
complexity, enhance the real-time execution and possess of high detection probability.