A geometric approach to the segmentation and reconstruction of acoustic three-dimensional data
28 Sep 1998-Vol. 1, pp 582-586
TL;DR: This paper presents a technique for the segmentation of three-dimensional images acquired by an acoustical camera that exploits the geometrical properties embedded in the sparse and noisy 3D information available to group the points which better fit the current quadric surface.
Abstract: This paper presents a technique for the segmentation of three-dimensional (3D) images acquired by an acoustical camera. The proposed algorithm identifies first the most reliable image points likely corresponding to man-made objects, and, second, determines the points belonging to the same surface. Actually, it exploits the geometrical properties embedded in the sparse and noisy 3D information available to group the points which better fit the current quadric surface. This algorithm can be applied for the reconstruction of virtual environments from acoustic data, useful for robotic applications (e.g., vehicle navigation). Results on synthetic and real acoustic images are promising.
Citations
More filters
01 Dec 2000
TL;DR: The state of-the art of the techniques and algorithms for acoustic image generation and processing are established, providing technical details and results for the most promising techniques, and pointing out the potential capabilities of this technology for underwater scene understanding are established.
Abstract: Underwater exploration is becoming more and more important for many applications involving physical, biological, geological, archaeological, and industrial issues. This paper aims at surveying the up-to-date advances in acoustic acquisition systems and data processing techniques, especially focusing on three-dimensional (3-D) short-range imaging for scene reconstruction and understanding. In fact, the advent of smarter and more efficient imaging systems has allowed the generation of good quality high-resolution images and the related design of proper techniques for underwater scene understanding. The term acoustic vision is introduced to generally describe all data processing (especially image processing) methods devoted to the interpretation of a scene. Since acoustics is also used for medical applications, a short overview of the related systems for biomedical acoustic image for motion is provided. The final goal of the paper is to establish the state of-the art of the techniques and algorithms for acoustic image generation and processing, providing technical details and results for the most promising techniques, and pointing out the potential capabilities of this technology for underwater scene understanding.
204 citations
Cites methods from "A geometric approach to the segment..."
...In [137] and [138], a geometric method for the reconstruction and segmentation of acoustic images is proposed that represents a further refinement of the one described in...
[...]
13 Sep 1999
TL;DR: An algorithm devoted to the segmentation of acoustic three-dimensional sparse images providing a virtual representation of the recognized objects in order to support a human operator for the navigation and inspection of underwater environments.
Abstract: In this paper, an algorithm devoted to the segmentation of acoustic three-dimensional sparse images is presented. The goal is the discrimination and the reconstruction of the objects present in an underwater scene. The final aim is to obtain an augmented representation of such images providing a virtual representation of the recognized objects in order to support a human operator for the navigation and inspection of underwater environments.
11 citations
01 Jan 2002
TL;DR: The purpose is to present a brief survey concerning the generation and processing of acoustic images for underwater applications, especially focusing on algorithms for three-dimensional (3-D) imaging.
Abstract: Acoustic imaging is an active research field that aims to study techniques for the formation and processing of images generated by raw signals acquired by an acoustic system [1]. Our purpose is to present a brief survey concerning the generation and processing of acoustic images for underwater applications [2,3], especially focusing on algorithms for three-dimensional (3-D) imaging. Like optical systems, acoustic systems can generate an image by processing the waves backscattered from the objects of a scene. The relative ease of measuring the timeof-flight of an acoustic signal makes it possible to generate not only acoustic 2-D images similar to optical ones but also range estimates that can be used to produce a real 3-D map.
2 citations
07 Jun 1999
TL;DR: The system is composed of several modules devoted to noise filtering, segmentation in pipe-shaped structures, recognition and reconstruction, and backprojected in the acoustic image in order to facilitate its interpretation.
Abstract: In this paper, a system aimed at the augmented representation of underwater scenes is presented. The system operates on three-dimensional acoustic images and is composed of several modules devoted to noise filtering, segmentation in pipe-shaped structures, recognition and reconstruction. Finally, identified objects are backprojected in the acoustic image in order to facilitate its interpretation. The final aim is to obtain an augmented (or virtual) representation of such images providing a useful tool to support a human operator for navigating in and inspecting underwater environments.
1 citations
References
More filters
TL;DR: A piecewise-smooth surface model for image data that possesses surface coherence properties is used to develop an algorithm that simultaneously segments a large class of images into regions of arbitrary shape and approximates image data with bivariate functions so that it is possible to compute a complete, noiseless image reconstruction based on the extracted functions and regions.
Abstract: The solution of the segmentation problem requires a mechanism for partitioning the image array into low-level entities based on a model of the underlying image structure. A piecewise-smooth surface model for image data that possesses surface coherence properties is used to develop an algorithm that simultaneously segments a large class of images into regions of arbitrary shape and approximates image data with bivariate functions so that it is possible to compute a complete, noiseless image reconstruction based on the extracted functions and regions. Surface curvature sign labeling provides an initial coarse image segmentation, which is refined by an iterative region-growing method based on variable-order surface fitting. Experimental results show the algorithm's performance on six range images and three intensity images. >
1,151 citations
Book•
07 Oct 2011
TL;DR: The uncertainty modeling techniques that are developed, and the utility of these techniques in various applications, support the claim that Bayesian modeling is a powerful and practical framework for low-level vision.
Abstract: Over the last decade, many low-level vision algorithms have been devised for extracting depth from one or more intensity images. The output of such algorithms usually contains no indication of the uncertainty associated with the scene reconstruction. In other areas of computer vision and robotics, the need for such error modeling is becoming recognized, both because of the uncertainty inherent in sensing and because of the desire to integrate information from different sensors or viewpoints.
In this thesis, we develop a new Bayesian model for the dense fields that are commonly used in low-level vision. The Bayesian model consists of three components: a prior model, a sensor model, and a posterior model. The prior model captures any a priori information about the structure of the dense field. We construct this model by using the smoothness constraints for regularization to define a Markov Random Field. The sensor model describes the behaviour and noise characteristics of our measurement system. We develop a number of sensor models for both sparse depth measurements and dense flow or intensity measurements. The posterior model combines the information from the prior and sensor models using Bayes' Rule, and can be used as the input to later stages of processing. We show how to compute optimal estimates from the posterior model, and also how to compute the uncertainty (variance) in these estimates.
This thesis applies Bayesian modeling to a number of low-level vision problems. The main application is the on-line extraction of depth from motion. For this application, we use a two-dimensional generalization of the Kalman filter to convert the current posterior model into a prior model for the next estimate. The resulting incremental algorithm provides a dense on-line estimate of depth whose uncertainty and error are reduced over time. Other applications of Bayesian modeling, include the choice of optimal smoothing parameter for interpolation; the determination of observer motion from sparse depth measurements without correspondence; and the construction of multiresolution relative surface representations. The approach to uncertainty modeling which we develop, and the utility of this approach in various applications, support our thesis that Bayesian modeling is a useful and practical framework for low-level vision.
341 citations
TL;DR: Optimal (in the maximum a posteriori probability sense) estimates of the reconstructed range image map and the restored confidence image are obtained by minimizing the energy function using simulated annealing.
Abstract: Describes a probabilistic technique for the coupled reconstruction and restoration of underwater acoustic images. The technique is founded on the physics of the image-formation process. Beamforming, a method widely applied in acoustic imaging, is used to build a range image from backscattered echoes, associated point by point with another type of information representing the reliability (or confidence) of such an image. Unfortunately, this kind of images is plagued by problems due to the nature of the signal and to the related sensing system. In the proposed algorithm, the range and confidence images are modeled as Markov random fields whose associated probability distributions are specified by a single energy function. This function has been designed to fully embed the physics of the acoustic image-formation process by modeling a priori knowledge of the acoustic system, the considered scene, and the noise-affecting measures and also by integrating reliability information to allow the coupled and simultaneous reconstruction and restoration of both images. Optimal (in the maximum a posteriori probability sense) estimates of the reconstructed range image map and the restored confidence image are obtained by minimizing the energy function using simulated annealing. Experimental results show the improvement of the processed images over those obtained by other methods performing separate reconstruction and restoration processes that disregard reliability information.
49 citations
01 Jan 1996
TL;DR: The offshore activities in the North Sea have motivated the development of a 3D acoustic camera, and conventional 2D sonars are not capable of providing a real time view of the volume in front of an underwater vehicle.
Abstract: The offshore activities in the North Sea have motivated the development of a 3D acoustic camera. It is considered important to avoid the use of divers subsea and instead develop advanced remotely controlled machines and sensing devices. Also, water turbidity is high in many areas and the operation of conventional video is often restricted. Furthermore, conventional 2D sonars are not capable of providing a real time view of the volume in front of an underwater vehicle.
45 citations