An adaptive image-stitching algorithm for an underwater tracking system

Published: 08th May 2020
Views: N/A

Presently most countries are allocated to focusing on underwater tracking. On the other hand, the acquisition of underwater images is conducted with low visibility in noisy surroundings because natural light is not available and even if artificial light is applied, the observable range is restricted [1]. Acoustic cameras can provide extremely high resolutions (for sonar) and accelerated refresh rates [2]. Therefore, sonar systems are widely used to obtain pictures of the seabed or other underwater objects. It's not conducive to monitoring items or surroundings submerged through sonar equipment alone since the observation angle of high-resolution sonar gear is so small that only element of the submerged scene may be found, i.e., the horizontal view angle of DIDSON (dual-frequency identification sonar) is 28.8[degrees]. Thus, most sonar equipment is usually installed in rotational mechanism to acquire different scene info; as such, sonar images are stitched to expand the monitoring horizon of the underwater environment [3]. So, image mosaicing technology plays a significant part in underwater observation systems. There has been much research into optical image-stitching; yet, little studies have been dedicated to stitching for sonar images. Image-stitching on an optical picture may be split into algorithms based on the pixel-level, the frequency power spectrum and features [4]. The computation of the pixel-level algorithm is fast and easy, but the mosaicing result is not ideal if there aren't enough attributes or if the images are particularly noisy. The computation of the frequency power spectrum algorithm is also not slow and noise correlation interference could be overcome, but it needs a satisfactory overlap width. Meanwhile, attribute points can simply be taken out by the attribute algorithm, which works for stitching the pictures with enough features but the expense of a heavy calculation load. It isn't suitable to adopt a pixel-level algorithm for stitching sonar images with a great deal of noise. In previous studies, many researchers have concentrated on the frequency power spectrum algorithm or the characteristic algorithm individually to sonar image that was mosaic. Several modified stage correlation algorithms based on the Fourier transform have already been proposed in the literature [57]. The algorithms enable the measurement of rotation translation and scaling variables between two pictures. The stitching resulting from this algorithm is good on paper. On the other hand, the preciseness of the stitching result for sonar images with attributes that are adequate is for the characteristic algorithm. The SIFT algorithm has been analyzed for taking out invariant attributes that were distinctive from pictures which can be utilized to perform reliable fitting between different views of an object or scene [8]. Mair et al. [9] have described a novel corner detection strategy, called the FAST (features from gifted segment evaluation) algorithm. The FAST algorithm only uses the surrounding pixels advice to get the characteristic points, which will be simple and relatively rapid.

Report this article Ask About This Article

More to Explore