Forward-looking sonar image compression by integrating keypoint clustering and morphological skeleton
- PDF / 1,989,798 Bytes
- 15 Pages / 439.642 x 666.49 pts Page_size
- 19 Downloads / 178 Views
Forward-looking sonar image compression by integrating keypoint clustering and morphological skeleton Danilo Avola1,3,4 · Marco Bernardi1,4 · Luigi Cinque1 · Gian Luca Foresti2 · Daniele Pannone1,4 · Chiara Petrioli1,4 Received: 14 April 2020 / Revised: 20 July 2020 / Accepted: 18 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Forward-Looking Sonar (FLS) is one of the most effective devices for underwater exploration which provides high-resolution images that can be used for several tasks in marine research, oceanographic, and deep-sea exploration. The limitation of current underwater acoustic channels does not allow transmitting these images in real-time, therefore image compression is required. Since acoustic images are characterized by speckle noise, an important challenge, in this area, is how to perform the compression while preserving relevant information. In this paper, a novel lossy forward-looking acoustic image compression method based on the combination between keypoint clustering and Morphological Skeleton (MS) is proposed. Keypoints are extracted by using A-KAZE feature extractor, while Density-Based Spatial Clustering of Application with Noise (DBSCAN) is used to find keypoint clusters representing a region-of-interest (ROI). Then, MS is executed to compact the ROI. The rest of the image is down-sampled and quantized through K-Means Clustering and represented via colour indexing. Finally, the information is compressed by using Brotli data compression. The experimental results on real FLS images demonstrate that our method achieves good outcomes in terms of quality metrics and compression ratio. Keywords Forward-Looking sonar · Image compression · Keypoint clustering · Morphological skeleton · Color indexing
1 Introduction In recent years, Autonomous Underwater Vehicles (AUVs) have attracted the interest of scientific, military, and commercial industries. The use of the optical camera has opened the door to several applications as simultaneous localization and mapping (SLAM), surveying, object identification, and others. Notwithstanding its information is very useful for different purposes, the visual quality may be severely affected by scattering and attenuation in Danilo Avola
[email protected]
Extended author information available on the last page of the article.
Multimedia Tools and Applications
challenging conditions like very turbid water or highly-cluttered environments, i.e., areas in which partial occlusions affect the visibility of the scene. Furthermore, an AUV equipped with a single camera can only acquire information at limited distance and angles of view. To get over with the above issues, an AUV is equipped, usually, with sonar sensors. Sonar technology is a widely used solution providing reliable measurements regardless of poor visibility conditions, thus enabling the detection of targets from long distances. There are several types of sonar that have different strengths and weaknesses regard range, field of view, and beam resolut
Data Loading...
