Polarization-Based Depth Information Acquisition of Underwater Target

2015 ◽  
Vol 22 (8) ◽  
pp. 43-47 ◽  
Author(s):  
赵泓扬 ZHAO Hong-yang ◽  
姚文卿 YAO Wen-qing
Keyword(s):  
Information Acquisition ◽  
Depth Information ◽  
Underwater Target

scholarly journals A Self-Improving Framework for Joint Depth Estimation and Underwater Target Detection from Hyperspectral Imagery

2021 ◽  
Vol 13 (9) ◽  
pp. 1721
Author(s):  
Jiahao Qi ◽  
Pengcheng Wan ◽  
Zhiqiang Gong ◽  
Wei Xue ◽  
Aihuan Yao ◽  
...  
Keyword(s):  
Target Detection ◽  
Structural Information ◽  
Hyperspectral Imagery ◽  
Contextual Information ◽  
Water Environment ◽  
Depth Estimation ◽  
Detection Methods ◽  
Depth Information ◽  
Underwater Target Detection ◽  
Underwater Target

Underwater target detection (UTD) is one of the most attractive research topics in hyperspectral imagery (HSI) processing. Most of the existing methods are presented to predict the signatures of desired targets in an underwater context but ignore the depth information which is position-sensitive and contributes significantly to distinguishing the background and target pixels. So as to take full advantage of the depth information, in this paper a self-improving framework is proposed to perform joint depth estimation and underwater target detection, which exploits the depth information and detection results to alternately boost the final detection performance. However, it is difficult to calculate depth information under the interference of a water environment. To address this dilemma, the proposed framework, named self-improving underwater target detection framework (SUTDF), employs the spectral and spatial contextual information to pick out target-associated pixels as the guidance dataset for depth estimation work. Considering the incompleteness of the guidance dataset, an expectation-maximum liked updating scheme has also been developed to iteratively excavate the statistical and structural information from input HSI for further improving the diversity of the guidance dataset. During each updating epoch, the calculated depth information is used to yield a more diversified dataset for the target detection network, leading to a more accurate detection result. Meanwhile, the detection result will in turn contribute in detecting more target-associated pixels as the supplement for the guidance dataset, eventually promoting the capacity of the depth estimation network. With this specific self-improving framework, we can provide a more precise detection result for a hyperspectral UTD task. Qualitative and quantitative illustrations verify the effectiveness and efficiency of SUTDF in comparison with state-of-the-art underwater target detection methods.

scholarly journals Introducing Depth Information Into Generative Target Tracking

2021 ◽  
Vol 15 ◽  
Author(s):  
Dongyue Sun ◽  
Xian Wang ◽  
Yonghong Lin ◽  
Tianlong Yang ◽  
Shixu Wu
Keyword(s):  
Density Distribution ◽  
Target Tracking ◽  
Information Acquisition ◽  
Visual Information ◽  
Mean Shift ◽  
Three Dimensional ◽  
Depth Information ◽  
Data Source ◽  
Actual Target ◽  
Technical Framework

Common visual features used in target tracking, including colour and grayscale, are prone to failure in a confusingly similar-looking background. As the technology of three-dimensional visual information acquisition has gradually gained ground in recent years, the conditions for the wide use of depth information in target tracking has been made available. This study focuses on discussing the possible ways to introduce depth information into the generative target tracking methods based on a kernel density estimation as well as the performance of different methods of introduction, thereby providing a reference for the use of depth information in actual target tracking systems. First, an analysis of the mean-shift technical framework, a typical algorithm used for generative target tracking, is described, and four methods of introducing the depth information are proposed, i.e., the thresholding of the data source, thresholding of the density distribution of the dataset applied, weighting of the data source, and weighting of the density distribution of the dataset. Details of an experimental study conducted to evaluate the validity, characteristics, and advantages of each method are then described. The experimental results showed that the four methods can improve the validity of the basic method to a certain extent and meet the requirements of real-time target tracking in a confusingly similar background. The method of weighting the density distribution of the dataset, into which depth information is introduced, is the prime choice in engineering practise because it delivers an excellent comprehensive performance and the highest level of accuracy, whereas methods such as the thresholding of both the data sources and the density distribution of the dataset are less time-consuming. The performance in comparison with that of a state-of-the-art tracker further verifies the practicality of the proposed approach. Finally, the research results also provide a reference for improvements in other target tracking methods in which depth information can be introduced.

Research on Disparity Map Generation Method of Underwater Target Based on the Improved SIFT Algorithm

2015 ◽  
Vol 741 ◽  
pp. 701-704 ◽  
Author(s):  
Di Wang ◽  
Yong Jie Pang
Keyword(s):  
Stereo Matching ◽  
Water Channel ◽  
Depth Information ◽  
Disparity Map ◽  
Sift Algorithm ◽  
Underwater Image ◽  
Map Generation ◽  
Curvature Coefficient ◽  
Bm Algorithm ◽  
Underwater Target

In order to obtain the depth information of the underwater target, it’s necessary to generate the disparity map based on binocular vision stereo matching. In the circulation water channel, the stereo matching experiments with underwater target were carried out by using the BM algorithm, SGBM algorithms and SIFT algorithm respectively. Then the characteristics of the disparity maps were analyzed for the three kinds of stereo matching algorithms. Compared with the BM algorithm and SGBM algorithms, the SIFT algorithm has been proved to be more suitable for underwater stereo matching. In order to obtain more feature points of underwater image, it is necessary to improved SIFT algorithm parameter. Underwater image matching experiments were made to determine the principal curvature coefficientγ. The results illustrated that the improvedγis better than the original value for underwater disparity map generation.

A morphological and energy-dispersive x-ray spectroscopy (EDS) investigation of separator-grade cellophane

1994 ◽  
Vol 52 ◽  
pp. 430-431
Author(s):  
Michael E. Rock ◽  
Vern Kennedy ◽  
Bhaskar Deodhar ◽  
Thomas G. Stoebe
Keyword(s):  
Extrusion Process ◽  
Morphological Characterization ◽  
Energy Dispersive ◽  
Regenerated Cellulose ◽  
Battery System ◽  
X Ray ◽  
Functional Differences ◽  
Transmission Electron ◽  
Separator Material ◽  
Underwater Target

Cellophane is a composite polymer material, made up of regenerated cellulose (usually derived from wood pulp) which has been chemically transformed into "viscose", then formed into a (1 mil thickness) transparent sheet through an extrusion process. Although primarily produced for the food industry, cellophane's use as a separator material in the silver-zinc secondary battery system has proved to be another important market. We examined 14 samples from five producers of cellophane, which are being evaluated as the separator material for a silver/zinc alkaline battery system in an autonomous underwater target vehicle. Our intent was to identify structural and/or chemical differences between samples which could be related to the functional differences seen in the lifetimes of these various battery separators. The unused cellophane samples were examined by transmission electron microscopy (TEM) and energy dispersive X-ray spectroscopy (EDS). Cellophane samples were cross sectioned (125-150 nm) using a diamond knife on a RMC MT-6000 ultramicrotome. Sections were examined in a Philips 430-T TEM at 200 kV. Analysis included morphological characterization, and EDS (for chemical composition). EDS was performed using an EDAX windowless detector.

Financial Statement Ratio Analysis to Predict Bankruptcy nn Company Registered in BEI - Jakarta (Altman Z-Score Method and Zmijewski)

2020 ◽  
Vol 3 (3) ◽  
pp. 122
Author(s):  
Andi Silvan
Keyword(s):  
Financial Distress ◽  
Stock Exchange ◽  
Good Condition ◽  
Financial Statement ◽  
Depth Information ◽  
Z Score ◽  
Industrial Manufacturing ◽  
Financial Difficulties ◽  
A Value ◽  
Score Method

AbstractThis study takes the topic of predicting corporate bankruptcies. This research dqlam use traditional methods Altman Z-Score and Zmijewski. The purpose of this study was to obtain in-depth information about predicting bankruptcy of companies that are not necessarily directly to bankruptcy, but there is financial distress.Based on the results of research conducted on the four (4) non industrial manufacturing company listed on the Indonesia Stock Exchange (BEI). Obtaining the value z-score represents the average company are in good condition, which means no financial distress. Acquisition value of x-score has a value of less than 0 (zero) which means that the company is in good condition and is predicted not experiencing financial difficulties. This study led to the conclusion that the Altman Z-Score and Zmijewski method can be used to predict corporate bankruptcy. Keywords: Financial Ratios, Bankruptcy, Company.

Sign in / Sign up

Export Citation Format

Share Document