An adaptive image stitching algorithm for an underwater tracking system

Published: 08th May 2020
Views: N/A

Currently most nations are devoted to focusing on observation that is submerged. But, the acquisition of submerged images is conducted with low visibility in noisy environments because natural light is unavailable and if artificial light is applied, the visible range is restricted [1]. Acoustic cameras can supply very high resolutions (for sonar) and fast refresh rates [2]. Therefore, sonar systems are broadly used to get pictures of another underwater items or the seabed. It's not contributory to tracking items or surroundings underwater through sonar gear alone since the observation angle of high resolution sonar gear is so small that only section of the submerged scene could be discovered, i.e., the horizontal view angle of DIDSON (dual-frequency identification sonar) is 28.8[degrees]. So, most sonar gear is frequently installed to have scene information that was different; as such, sonar images are stitched to expand the monitoring horizon of the underwater environment [3]. Hence, image mosaicing technology plays an important role in tracking systems that are submerged. There has been much research into optical image-stitching; however, little research has been given to stitching for sonar pictures. Image-stitching on an optical image can be divided into algorithms on the basis of the pixel-level, the frequency power spectrum and features [4]. The computation of the pixel-level algorithm is easy and quick, but the result that is mosaicing is just not perfect if there are not enough features or when the images are particularly noisy. The computation of the frequency power spectrum algorithm is also quick and noise correlation interference can be beat, but it needs a sufficient overlap width. Meanwhile, characteristic points can certainly be pulled by the attribute algorithm, which works for stitching the pictures with enough features but the cost of a significant computation load. Several altered stage correlation algorithms on the basis of the Fourier transform have been proposed in the literature [57]. The algorithms enable the measurement of translation, rotation and scaling factors between two pictures. The stitching resulting from this algorithm is not bad on paper. However, the preciseness of the stitching result for sonar pictures with adequate characteristics is for the characteristic algorithm. The SIFT algorithm has been analyzed for pulling identifying invariant attributes from pictures which can be utilized to perform dependable fitting between different views of an object or scene [8]. Because the SIFT feature points are described -dimensional vectors, the speed of this algorithm is slow. Mair et al. [9] have described a new corner detection strategy, called the FAST (features from accelerated segment test) algorithm. The FAST algorithm only uses the surrounding pixels information to get the attribute points, which can be easy and relatively fast.

Report this article Ask About This Article

More to Explore