共查询到20条相似文献，搜索用时 656 毫秒
1.
2.
The fast update rate and good performance of new generation electronic sector scanning sonars is now allowing practicable use of temporal information for signal processing tasks such as object classification and motion estimation. Problems remain, however, as objects change appearance, merge, maneuver, move in and out of the field of view, and split due to poor segmentation. This paper presents an approach to the segmentation, two-dimensional motion estimation, and subsequent tracking of multiple objects in sequences of sector scan sonar images. Applications such as ROV obstacle avoidance, visual servoing, and underwater surveillance are relevant. Initially, static and moving objects are distinguished in the sonar image sequence using frequency-domain filtering. Optical flow calculations are then performed on moving objects with significant size to obtain magnitude and direction motion estimates. Matches of these motion estimates, and the future positions they predict, are then used as a basis for identifying corresponding objects in adjacent scans. To enhance robustness, a tracking tree is constructed storing multiple possible correspondences and cumulative confidence values obtained from successive compatibility measures. Deferred decision making is then employed to enable best estimates of object tracks to be updated as subsequent scans produce new information. The method is shown to work well, with good tracking performance when objects merge, split, and change shape. The optical flow is demonstrated to give position prediction errors of between 10 and 50 cm (1%-5% of scan range), with no violation of smoothness assumptions using sample rates between 4 and 1 frames/s 相似文献
3.
Daniel S. Le Leannec F. Roux C. Soliman B. Maillard E.P. 《Oceanic Engineering, IEEE Journal of》1998,23(3):245-259
This paper presents a method for the matching of underwater images acquired with acoustic sensors. As a final objective, the system aims at matching data from two-dimensional scenes. The proposed approach carries out a hypothetical reasoning based on objects, represented by shadows and echoes in the sonar images, and their available features. The problem of determining measures which are invariant to changes in sonar settings and noise characteristics is addressed by mapping robust features for sonar images to a qualitative representation. To cope with the viewpoint charging appearance, the method is based on the conservation of objects' relative position from one image to another. We attempt to match geometrical structures formed by the association of three objects. The hypothetical reasoning is conducted in a decision tree framework. A tree node is generated by two objects' association, each one belonging to a respective image. Hypotheses propagation consists of creating new nodes from neighboring associations. The matching solution is determined by the selection of the decision tree's longest branch. Thus, the association mechanism is a depth-first procedure. The proposed method has been applied to real high-resolution side-scan sonar images. The matching process has shown successful and promising results which have been further improved. In particular, the parceled shadows (during the segmentation procedure) problem has been tackled 相似文献
4.
This paper presents an investigation of the robustness of an inter-frame feature measure classifier for underwater sector scan sonar image sequences. In the initial stages the images are of either divers or remotely operated vehicles (ROV's). The inter-frame feature measures are derived from sequences of sonar scans to characterize the behavior of the objects over time. The classifier has been shown to produce error rates of 0%-2% using real nonnoisy images. The investigation looks at the robustness of the classifier with increased noise conditions and changes in the filtering of the images. It also identifies a set of features that are less susceptible to increased noise conditions and changes in the image filters. These features are the mean variance, and the variance of the rate of change in time of the intra-frame feature measures area, perimeter, compactness, maximum dimension and the first and second invariant moments of the objects. It is shown how the performance of the classifier can be improved. Success rates of up to 100% were obtained for a classifier trained under normal noise conditions, signal-to-noise ratio (SNR) around 9.5 dB, and a noisy test sequence of SNR 7.6 dB 相似文献
5.
Canonical correlation analysis is employed as a multiaspect feature extraction method for underwater target classification. The method exploits linear dependence or coherence between two consecutive sonar returns, at different aspect angles. This is accomplished by extracting the dominant canonical correlations between the two sonar returns and using them as features for classifying mine-like objects from nonmine-like objects. The experimental results on a wideband acoustic backscattered data set, which contains sonar returns from several mine-like and nonmine-like objects in two different environmental conditions, show the promise of canonical correlation features for mine-like versus nonmine-like discrimination. The results also reveal that in a fixed bottom condition, canonical correlation features are relatively invariant to changes in aspect angle. 相似文献
6.
This paper presents a neural-network-based system to detect small man-made objects in sequences of sector-scan sonar images created using signals of various pulse lengths. The detection of such objects is considered out to ranges of 150 m by using an experimental sector-scan sonar system mounted on a vessel. The sonar system considered in this investigation has three modes of operation to create images over ranges of 200, 400, and 800 m from the vessel using acoustic pulses of a different duration for each mode. After an initial cleaning operation performed by compensating for the motion of the vessel, the imagery is segmented to extract objects for analysis. A set of 31 features extracted from each object is examined. These features consist of basic object size and contrast features, shape moment-based features, moment invariants, and features extracted from the second-order histogram of each object. Optimal sets of 15 features are then selected for each mode and over all modes using sequential forward selection (SFS) and sequential backward selection (SBS). These features are then used to train neural networks to detect man-made objects in each sonar mode. By the addition of a feature describing the sonar's mode of operation, a neural network is trained to detect man-made objects in any of the three sonar modes. The multimode detector is shown to perform very well when compared with detectors trained specifically for each sonar mode setting. The proposed detector is also shown to perform well when compared to a number of statistical detectors based on the same set of features. The proposed detector achieves a 92.4% probability of detection at a mean false-alarm rate of 10 per image, averaged over all sonar mode settings. 相似文献
7.
An active sonar is described that adaptively changes its location and configuration in response to the echoes it observes in order to locate an object, position it at a known location, and identify it using features extracted from the echoes. The sonar consists of a center transmitter flanked by two receivers that can rotate and is positioned at the end of a robot arm that has five degree-of-freedom mobility. The sonar operates in air using Polaroid transducers that are resonant at 60 kHz with a nominal wavelength equal to 6 mm. The emitted pulse has a short duration with a useful bandwidth extending from 20 to 130 kHz. Using binaural information, the transmitter rotates to position an echo-producing object on its axis to maximize the acoustic intensity incident on the nearest echo-producing feature. The receivers rotate to maximize the echo amplitude and bandwidth. These optimizations are useful for differentiating objects. The system recognizes a collection of ball bearings, machine washers, and rubber O-rings of different sizes ranging from 0.45 to 2.54 cm, some differing by less than 1 mm in diameter. Learning is accomplished by extracting vectors of 32 echo envelope values acquired during a scan in elevation and forming a data base. Recognition is accomplished by comparing a single observed echo vector with the data base to find the least squared error match. A bent-wire paper clip illustrates the recognition of an asymmetric pose-dependent object 相似文献
8.
随着机器学习算法的不断更新发展,加之其良好的适应性、准确性及鲁棒性,在三维物体识别领域获得了广泛的应用,成为当前点云处理的研究热点。首先,本文对三维物体点云数据识别及机器学习的发展应用进行归纳。然后,从特征选择、特征提取、特征识别三个方面,进行分析总结。最后,指出机器学习在基于点云的三维物体识别领域的应用目前所面临的挑战及进一步研究的方向。 相似文献
9.
传统的单机判读服务系统,存在着判读标准不一、功能单一、插件依赖性高、系统集成性差等问题。在全面分析各类地理空间目标要素构成、地图表示方法和系统功能特点的基础上,对典型判读特征进行了归纳,完成了目标的分类、特征数据库的建立、平台总体架构的设计。基于HTML5和Web GL技术,构建了网络环境下多源、多尺度、多分辨率地理空间目标的三维判读一体化服务平台,实现了面向地理空间目标的判读、检索、三维显示及测试评定于一体的实用判读训练系统,为地理空间目标的网络判读提供了一定参考和借鉴。 相似文献
10.
Two qualitative results concerning statistical sonar signal processing and acoustic field matching are obtained. First, normal-mode field predictions are integrated with statistical signature analysis by constructing a boundary-value problem in the acoustic waveguide. From this construction it is found that the normal-mode filter is the unique acoustic preprocessor which does not confound deterministic waveguide correlation structure with stochastic source covariance structure. Second, the origin of deterministic, Gaussian, and non-Gaussian source signatures is investigated by associating physical parameters with the classical Lindeberg central limit conditions. From construction it is found that there are important objects that are not adequately represented either by infinitesimal points or by infinite surfaces. If receiver resolution is inadequate to resolve source complexity, these objects will exhibit a non-Gaussian acoustic signature via an entirely linear progression from internal excitation, to source radiation, through waveguide propagation, and finally to reception 相似文献
11.
多波束声呐系统与侧扫声呐系统均为海底面探测的重要工具,二者均采用声学方法,在工作原理上存在异同。本文简要介绍了二者的研究进展,分别对其数据处理进行了比对分析,认为多波束声呐处理方法侧重于数据的测量精度,而侧扫声呐则主要侧重于图像处理;归纳了当前二者主要的数据匹配融合方法,包括同名特征融合、基于SURF算法的匹配融合以及特征点融合,从数据采集原理上对数据融合方法进行了深入分析,发现在探头定位、单ping数据点分布以及ping之间的数据定位上存在一定的困难,即使经过一定的处理,二者采集的也非简单的平面图像,故二者的数据融合尚存在一定的难度。 相似文献
12.
《Oceanic Engineering, IEEE Journal of》1997,22(1):40-46
Sector-scanning sonar systems image the sea bottom to detect objects that can be distinguished from the background structure of the sea bottom. In current systems, images are displayed and discarded as new image data become available, In this paper, a method for improving sonar detection by utilizing all images in a sequence is investigated. The proposed method requires that sonar data are acquired with a sector-scanning sonar in a side-looking configuration. It is demonstrated that these data can be used to detect observation-point-dependent changes in sea-bottom backscattering characteristics. These changes provide additional cues for discrimination that can improve the detection of objects on the sea bottom. Results of applying the method to experimental data are presented 相似文献
13.
14.
Wavelet analysis of bathymetric sidescan sonar data for the classification of seafloor sediments in Hopvågen Bay - Norway 总被引：1，自引：0，他引：1
In this paper we examine the use of bathymetric sidescan sonar for automatic classification of seabed sediments. Bathymetric sidescan sonar, here implemented through a small receiver array, retains the advantage of sidescan in speed through illuminating large swaths, but also enables the data gathered to be located spatially. The spatial location allows the image intensity to be corrected for depth and insonification angle, thus improving the use of the sonar for identifying changes in seafloor sediment. In this paper we investigate automatic tools for seabed recognition, using wavelets to analyse the image of Hopvågen Bay in Norway. We use the back-propagation elimination algorithm to determine the most significant wavelet features for discrimination. We show that the features selected present good agreement with the grab sample results in the survey under study and can be used in a classifier to discriminate between different seabed sediments. 相似文献
15.
Panoramic sweeps produced by a scanning range sensor often defy interpretation using conventional line-of-sight models, particularly when the environment contains curved, specularly reflective surfaces. Combining multiple scans from different vantage points provides geometric constraints necessary to solve this problem, but not without introducing new difficulties. Existing multiple scan implementations, for the most part, ignore the data correspondence issue. The multiple hypothesis tracking (MHT) algorithm explicitly deals with data correspondence. Given canonical observations extracted from raw scans, the MHT applies multiple behavior models to explain their evolution from one scan to the next. This technique identifies different topological features in the world to which it assigns the corresponding measurements. We apply the algorithm to real sonar scans generated specifically for this investigation. The experiments consist of interrogating a variety of two-dimensional prismatic objects, standing on end in a 1.2-m-deep freshwater tank, from multiple vantage points using a 1.25 MHz profiling sonar system. The results reflect the validity of the algorithm under the initial assumptions and its gradual performance degradation when these assumptions fail to characterize the environment adequately. We close with recommendations that detail extending the approach to handle more natural underwater settings 相似文献
16.
多波束与侧扫声纳海底目标探测的比较分析 总被引：2，自引：0，他引：2
侧扫声纳是目前常用的海底目标(如沉船、水雷、管线等)探测工具,在测深领域,多波束以全覆盖和高效率证明了它的优越性。由于多波束具有很高的分辨率,目前在工程上已经开始应用多波束进行海底目标物的探测。对多波束和侧扫声纳进行了比较分析,并着重探讨了影响多波束分辨率的各种因素。结果表明:多波束的最大优点在于定位精度高,但其适用范围不如侧扫声纳广泛,尤其受到水深和波束角的限制,多波束和侧扫声纳在探测海底目标时具有很好的互补性,同时应用可以提高目标解译的准确性。 相似文献
17.
18.
19.
Development of real-time acoustic image recognition system using by autonomous marine vehicle 总被引：1，自引：0，他引：1
Automation of complicated underwater tasks require acoustic image based object recognition. This paper presents an acoustic image based real-time object recognition system. We proposed an acoustic image predictor to estimate an object's shape in advance. Depending on the acoustic camera's position, the predictor generates optimal template for recognition. The proposed method is implemented in our autonomous marine vehicle. For real-time processing, efficient recognition strategies are addressed. The vehicle detects an object and localizes it for recognition. In the detection process, the acoustic image's specific characteristics are used as the detection cues. In the localization process, the vehicle's horizontal and vertical positioning strategies are described. Efficient template generation method to minimize computing power is addressed. This realizes real-time recognition using the vehicle. To estimate the proposed system's accuracy and reliability, a recognition test was carried out in the field. The vehicle successfully recognized two different objects with high accuracy. 相似文献
20.
In this paper, image processing technique that reduces video images of buoy motion to yield time series of image coordinates
of buoy objects will be investigated. The buoy motion images are noisy due to time-varying brightness as well as non-uniform
background illumination. The occurrence of boats, wakes, and wind-induced white caps interferes significantly in recognition
of buoy objects. Thus, semiautomated procedures consisting of object recognition and image measurement aspects will be conducted.
These offer more satisfactory results than a manual process. Spectral analysis shows that the image coordinates of buoy objects
represent wave motion well, indicating its usefulness in the analysis of wave characteristics. 相似文献