The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Studying fish recognition has important realistic and theoretical significance to aquaculture and marine biology. Fish recognition is challenging problem because of distortion, overlap and occlusion of digital images. Previous researchers have done a lot of work on fish recognition, but the classification accuracy may be not high enough. Classification and recognition methods based on convolutional...
Generally, underwater hull inspection have been conducted by human divers. It is an extremely dangerous task, and hence, can be a potential application for unmanned underwater vehicles. The operational safety and performance of in-water inspection can be significantly improved by introducing unmanned vehicle systems. This study addresses the development of an hover-capable autonomous underwater vehicle...
Canada's Exclusive Economic Zone in the Northeast Pacific encompasses a rich variety of offshore benthic habitats, from continental shelf, slope and abyssal sediments, to sponge reefs, seamounts, gas hydrates and hydrothermal vents. Knowledge of these remote areas is uneven, derived from mostly uncoordinated surveys and sampling expeditions by surface vessels, exploration with remotely operated vehicles...
In this paper, we present an approach for producing side scan sonar image mosaicking under a robust SLAM scheme. A Pose Graph based SLAM algorithm is used to perform a correction over the sensor trajectory for enabling image registration, using observation constraints extracted from the images. However, due to the operational context, the available odometry data carries a high degree of uncertainty...
The recognition of places by using visual information in underwater environments is important when performing autonomous robotic exploration of the same area at different periods of time. It helps the robot to know its location and take decisions accordingly. However, vision-based recognition of underwater places can be a very challenging task due to the inherent properties of this kind of places...
Nowadays, ocean observatory networks, which gather and provide multidisciplinary, long-term, 3D continuous marine observations at multiple temporal spatial scales, play a more and more important role in ocean investigations. In this paper, we try to develop a portable smart device with online fish detection and tracking strategies by ARM7 microprocessor for ocean observatory networks, combining the...
We propose a general approach towards feature extraction for identifying sonar targets based on their composition and geometry. The key idea is to discover the geometric connections between braid-like features within acoustic color topography that includes magnitude and phase information. Specifically, we characterize each target as a graph of intersecting braided features, detected across the complex-valued...
This paper addresses the heterogeneous data registration problem, which is one of the key features for any scene reconstruction and representation, especially for the underwater environment. In this study, we propose a registration method built around a 2D-to-3D feature-based approach that registers high-resolution side-scan sonar images with bathymetric data (topographic 3D point cloud) obtained...
Finding mines in Sonar imagery is a significant problem with a great deal of relevance for seafaring military and commercial endeavors. Unfortunately, the lack of enormous Sonar image data sets has prevented automatic target recognition (ATR) algorithms from some of the same advances seen in other computer vision fields. Namely, the boom in convolutional neural nets (CNNs) which have been able to...
Mechanical systems operating in noisy environments create a challenging signal processing and monitoring problem especially in real-time. To detect a particular type of subsystem from noisy vibration data, it is necessary to identify signatures or particular features that make it unique. Resonant (modal) frequencies emitted during its normal operation satisfy this constraint. Monitoring structural...
In this paper, we propose a backtracking method of AUV based on optical and acoustic image evaluation. With the proposed method, the vehicle can record useful images on its path, and conduct backtracking efficiently and robustly even in turbid water. At each point during the exploration, AUV chooses better image between optical and acoustic image by feature detection. The chosen image is saved in...
This article develops a geometric framework for detecting targets, in the form of regions of interest, from certain sonar imagery. The main idea is to extract level sets from voxel images and compute local geometric features of the resulting surfaces. Examples include Gaussian and principal curvatures, radial distances, patch areas etc. These features are then compressed into histograms, or estimated...
Mapping of underwater environments is a critical task for a range of activities from monitoring coral reef habitats to surveying submerged archaeological sites. In recent years, optical reconstruction methods developed for terrestrial (in air) applications have increasingly been applied to the underwater environment by the marine science community. However, assumptions such as the brightness constancy...
Reading is one of the main paths to acquire knowledge, either done traditionally on paper media or practiced on electronic devices. Efficiency varies when different reading patterns are involved. It is the objective of this research to classify reading patterns from fixation data using machine learning techniques in an attempt to understand and evaluate the reading and learning process. In our experiment,...
This paper presents a performance comparison of several state-of-the-art visual feature extraction algorithms when applied in a poorly-structured environment as found on the planet Mars. So far, no systematic evaluation of feature extraction algorithms in extraterrestrial environments is available. The algorithms in this paper are evaluated using the Devon Island dataset which is said to have one...
In this paper, we address interesting questions about how feng shui influences house price from a data perspective. First, is feng shui likely to influence house price? Second, how do different feng shui features, e.g., house shape, master bedroom location, and other interior room arrangements, influence the price? Third, can we automatically diagnose the feng shui problems of a house? From a dataset...
Image search engines commonly employ the Bag Of Features (BOF) method to represent each database image with a feature vector and retrieve the best candidate using a measure of similarity to a query image vector. The BOF vector, which specifies the occurrence frequency of features, is used with Soft Assignment (SA) to find the most similar candidates which are further analyzed using geometric information...
With the growth of crowd phenomena in the real world, crowd scene understanding is becoming an important task in anomaly detection and public security. Visual ambiguities and occlusions, high density, low mobility and scene semantics, however, make this problem a great challenge. In this paper, we propose an end-to-end deep architecture, Convolutional DLSTM (ConvDLSTM), for crowd scene understanding...
Artificial Neural Networks are a widely used computing system implemented for a wide variety of tasks and problems. A common application of such networks is classification problems. However, a significant amount of this research focuses on one and two-dimensional information, such as vectorized data and images. There is limited research performed on three-dimensional media such as video clips. This...
The subsequence-matching operation applied to motion capture data searches in long motion sequences to locate their parts that are similar to a query example. An effective and efficient implementation of such operation is valuable to increase reusability and findability of expensively recorded data in the past. This demonstration paper builds on recent advances in the field of motion-data processing...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.