22 April 2019 in IEEE Sensors Journal
We offer a new unsupervised statistically-based algorithm for the detection of underwater objects in synthetic aperture sonar (SAS) imagery due to its high-resolution imagery and because its resolution is independent of the range. In contrast to other methods that do not utilize the statistical model of the shadow region, our algorithm combines highlight detection and shadow detection using a weighted likelihood ratio test, while exploiting the expected spatial distribution of potential objects. We detect highlights by a higher-order-statistics representation of the image, followed by a segmentation process to form a region-of-interest (ROI). Then, while taking into account the sonar elevation and scan angle, for each ROI, we use a support vector machine (SVM) over the statistical features of the pixels within the ROI to detect shadow-related pixels and background pixels. Our algorithm has the benefit of being robust as a result of setting its main parameters in situ. Moreover, we do not require knowledge about the target's shape or size, thereby making our algorithm suitable for all sonar detection applications and sonar types. To test detection performance, using our own autonomous underwater vehicle, we collected 270 sonar images, which we also share with the community. Compared to the results of benchmark schemes, our detection algorithm shows a trade-off between the probability of detection and the false alarm rate (FAR), which is close to the Kullback-Leibler (KL) divergence lower bound.
29 July 2019 in IEEE Transactions on Image Processing
The recent boost in undersea operations has led to the development of high-resolution sonar systems mounted on autonomous vehicles. These vehicles are used to scan the seafloor in search of different objects such as sunken ships, archaeological sites, and submerged mines. An important part of the detection operation is the segmentation of sonar images, where the object’s highlight and shadow are distinguished from the seabed background. In this work, we focus on the automatic segmentation of sonar images. We present our enhanced fuzzybased with Kernel metric (EnFK) algorithm for the segmentation of sonar images which, in an attempt to improve segmentation accuracy, introduces two new fuzzy terms of local spatial and statistical information. Our algorithm includes a preliminary de-noising algorithm which, together with the original image, feeds into the segmentation procedure to avoid trapping to local minima and to improve convergence. The result is a segmentation procedure that specifically suits the intensity inhomogeneity and the complex seabed texture of sonar images. We tested our approach using simulated images, real sonar images, and sonar images that we created in two different sea experiments, using multibeam sonar and synthetic aperture sonar. The results show accurate segmentation performance that is far beyond the stateof-the-art results.
18 September 2020 in IET Radar, Sonar & Navigation
The authors introduce a constant false alarm rate (CFAR) detection algorithm, called K‐CFAR, for automatic detection of underwater objects in sonar imagery. The K‐CFAR adopts the K ‐distribution as a statistical model of the background. An efficient closed‐form estimator for the K ‐distribution parameters is derived by the second‐order approximation of the Polygamma function without involving a numerical iterative solution. A closed‐form expression for the CFAR detection threshold is obtained by exploiting the first‐order Laguerre approximation of the K ‐distribution. Then, to increase the probability of detection, a non‐CFAR refinement to the K‐CFAR, based on the spatial feature of the objects, is proposed. Experimental results obtained from 270 real sonar images of diverse environments demonstrate the superiority of the proposed algorithm compared to the state‐of‐the‐art in terms of receiver operating characteristic curves.
27 November 2023 in IEEE Transactions on Mobile Computing
This article proposes a simultaneous localization and mapping (SLAM) solution that combines inputs from sonar and optical images. Our solution for this navigation problem is solved by matching objects detected by the AUV's camera with objects identified within the SAS image. In particular, upon detecting an object using the AUV's camera, e.g., an underwater structure or even a rock, we rank the similarity of this object to all objects found within the SAS image. Taking a SLAM approach, the decision for the best match, and thus the position of the AUV within the SAS image, is made based not only on the current detected object, but also on similarity ranking previously detected objects while accounting for the AUV's self-measured heading. The solution is handled by a tracking mechanism that considers the possible positions of the objects within the SAS image as problem states, and modeling the state relations using a hidden Markov chain. Experimental results on real sonar and optical images implemented within a simulated environment show high accuracy in matching the location of an AUV within an SAS image in multiple scenarios.
1 February 2022 in IEEE Sensors Journal
This paper proposes a feature characterization method that can discriminate between man-made and natural objects on the seabed using a pair of SAS and optical images. Feature matching methods, like scale-invariant feature transform (SIFT), usually utilize gradient information to detect feature points, whereas contour-based features often use geometrical descriptors such as roughness, circularity, and solidity. However, due to the different characteristics of sonar and optical imagery, current descriptors cannot be directly applied over sonar-optical image pairs. The clarity of the water (muddy water, concentration of particles that scatter light) for optical images, and the stability of the platform, and reflections from seabed for SAS images are important parameters that distort the two images and make it hard to match between the two image sources. This paper proposes a feature characterization method that can identify man-made objects in underwater optic-SAS image pairs. Two new contour-based feature descriptors are introduced. The first is the entropy angle feature , which aims to reflect the entropy of the angles that originate from points on the contour. The second feature is local curve fitting , which characterizes the radial-polar space of the local curve polynomial fitting. The descriptors are designed to characterize man-made objects whose contour is expected to be smoother than natural objects such as rocks. Experimental results on a real, large dataset comprised of 1,519 optic-SAS image pairs, are shown to verify that the proposed method has a high level of classification accuracy and good discrimination between man-made and natural objects.
8 August 2023 in Pattern Recognition