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...
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...
As an important role of oceanographic survey, side-scan sonar image classification has attracted much attention in the past two decades. Due to the special properties of sonar image, traditional approaches are difficult to get good classification accuracy, so their implementation in real world is blocked. In this paper, a novel classification system based on kernel-based extreme learning machine (KELM)...
Underwater scene search turns out to be one of the most challenging topics in the underwater image analysis. In this paper, we present one underwater scene search scheme combined with similarity measure and sparse representation. The color histogram is first adopted to classify the candidate image patches for each kind of the underwater scene. At the same time, the feature similarity (FSIM) considers...
In this paper, we try to develop a general framework of 3D shape reconstruction strategy with extremely rare point cloud extracted for fish ethology research. Particle filter is first taken to focus on fish trajectory tracking from monocular video sequence. The Speeded Up Robust Features (SURF) technique will be adopted to match the same tracking fish across the overlapping view fields with more stable...
In this paper, we propose a novel approach for SSS registration based on modified phase correlation, which is capable of handling low resolution and noise. The modified phase correlation combines threshold segmentation with phase correlation to carry out side-scan sonar (SSS) image registration. Image registration aims to transform images obtained from different views to the same coordinate. Underwater...
Computer vision has become the tool of two-dimensional image recognition and analysis, which mainly means extracting image features. But the problem of robustness and real-time property in complex scenarios makes feature extraction become a challenging task. Visual attention is an important psychological adjustment mechanism in the process of human visual information management, under the guidance...
In this paper, we try to combine Bag-of-Words (BoW) with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) together for one kind of sparse representation in the seafloor visual saliency evaluation. Properties in the water, due to the large amount of acoustic noises, sonar signals are easily polluted and interfered during image collection, and the sonar images usually diverge from...
The fast sonar-based object recognition turns out to be one of the most challenging topics in the underwater signal analysis. In this paper, we try to develop a fast benthic object recognition model via the extreme learning machine (ELM) on the basis of the structured geometrical feature extraction. Geometrical features such as major and minor axis, eccentricity, circularity and so on are employed...
In this paper, a novel approach based on bag-of-words and compressed sensing has been proposed for the sparse representation of the underwater images. Properties in the water, such as the limited range, non-uniform lighting, low contrast, diminished colors, has been taken into consideration for underwater image sparse representation. Our method is a simple and computationally efficient extension of...
In this paper, we present one underwater image stitching model combined with the Scale Invariant Feature Transform (SIFT) and the wavelet fusion. Poor visibility in the sea and the variations in the illumination, viewpoints, etc., have been comprehensively taken into consideration for image matching. Wavelet fusion is then made full use of to undertake the underwater image mosaic. It is shown in the...
With the increasing development of underwater vision sensors, simultaneous localization and mapping (SLAM) based on stereo vision has become a hot topic in the areas of ocean investigation and exploration. In this paper, visual SLAM with a focus on stereo camera system is presented to estimate the motion of autonomous underwater vehicles (AUVs) and build the feature map of surrounding environment...
As one of the dominant techniques for sensing the underwater environments, underwater vision has shown great prospects in ocean investigations and explorations over the last decades. The vision system is usually installed on the platforms of autonomous underwater vehicles (AUVs). Due to the limitation of transmission and storage for underwater signals, it is extremely urgent to explore an efficient...
In this paper, the consistent fish tracking strategies have been present for the underwater surveillance system with multiple static cameras in the overlapping field of views (FOV). The discriminative appearance model has been first introduced to distinguish the swimming fish and the background by the superpixel. The centroid coordinate homographic mapping and the Speeded Up Robust Features (SURF)...
The paper describes a localization system for autonomous underwater vehicles (AUV). It uses a DVL (Doppler velocity log) sensor and AHRS (attitude and heading reference system) sensor to measure AUV's depth, attitude and velocities relative to the bottom. A mechanically scanning imaging sonar (MSIS) is employed to obtain acoustic images of objects in underwater environment. In order to estimate optimally...
Navigation and localization with high precision has been one of most critical issues for the safety and effective completion of missions of autonomous underwater vehicles. Since the underwater environment is extremely complex and the external sensors of what can be used are limited to only sonar, as well as information obtained has too much noise and interference, thus all of the intractable will...
A half face recognition scheme is proposed to reduce effect of variable lighting on face recognition. The scheme includes 3 stages. 1) The face images in training set are divided into the left face images and the right half face images firstly, and then they train the left feature extractor and the right feature extractor after illumination compensation respectively. 2) One half of a probe face image...
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.