An adaptive image stitching algorithm for an underwater tracking system

Published: 08th May 2020
Views: N/A

Presently most states are allocated to focusing on submerged observation. On the other hand, the acquisition of submerged images is performed in noisy surroundings with low visibility because natural light is not available and if man-made light is used, the observable range is limited [1]. Acoustic cameras can supply very high resolutions (for sonar) and rapid refresh rates [2]. Therefore, sonar systems are broadly employed to obtain images of another underwater items or the seabed. It is not contributory to monitoring items or surroundings submerged through sonar gear alone since the observation angle of high resolution sonar gear is really small that only element of the underwater scene may be discovered, i.e., the horizontal view angle of DIDSON (double-frequency identification sonar) is 28.8[degrees]. So, most sonar equipment is frequently installed in rotational mechanism to obtain scene information that was distinct; as such, sonar pictures are stitched to expand the monitoring horizon of the submerged environment [3]. Hence, image mosaicing technology plays an important role in observation systems that are submerged. There's been much research into optical image stitching; yet, little studies have been devoted to stitching for sonar pictures. Image stitching on an optical picture can be divided into algorithms on the basis of the pixel-level, the frequency power spectrum and attributes [4]. The calculation of the pixel-level algorithm is quick and straightforward, but the mosaicing result isn't ideal if there aren't enough features or when the pictures are particularly noisy. The computation of the frequency power spectrum algorithm is, in addition, not slow and sound correlation interference can be overcome, but it requires a sufficient overlap width. Meanwhile, feature points can quickly be pulled by the feature algorithm, which is appropriate for stitching the images with enough features but the expense of a heavy computation load. In previous studies, many researchers have concentrated on the characteristic algorithm or the frequency power spectrum algorithm individually to mosaic sonar image. In the perspective of present study, the phase correlation method [5-7] is typically the most popular algorithm in the area of the frequency power spectrum algorithm while the SIFT (scale invariant feature transform) [8], QUICK (characteristics from accelerated section evaluation) [9] and ORB (oriented SWIFT and rotated SHORT) [10] and SURF [11-13] algorithms enjoy tremendous popularity in the field of attribute algorithms. The algorithms enable the measurement of scaling, rotation and translation factors between two pictures. The stitching resulting from this algorithm is not bad on paper. But, the precision of the stitching result for sonar images with characteristics that are adequate is for the feature algorithm. The SIFT algorithm continues to be studied for extracting identifying invariant attributes from pictures which may be used to do reliable fitting between different views of an object or scene [8]. Mair et al. [9] have described a new corner detection strategy, called the FAST (characteristics from gifted section test) algorithm. The FAST algorithm simply uses the surrounding pixels advice to get the characteristic points, which will be simple and relatively fast. But, the truth of the stitching result from this algorithm is not better than for the SIFT algorithm.

Report this article Ask About This Article

More to Explore