Journal of Information Hiding and Multimedia Signal Processing最新文献_第2页

Improving the Accuracy of Under-Fog Driving Assistance System 提高雾下驾驶辅助系统的准确性

Journal of Information Hiding and Multimedia Signal Processing Pub Date : 2020-07-28 DOI: 10.4236/jsip.2020.112002

B. Kerim

引用次数: 0

Application of 3D Projection Profilometry in the High Speed Impaction Surface Deformation Measurement Research 三维投影轮廓法在高速碰撞面变形测量中的应用研究

Journal of Information Hiding and Multimedia Signal Processing Pub Date : 2020-01-01 DOI: 10.4236/jsip.2020.114006

Eryi Hu

{"title":"Application of 3D Projection Profilometry in the High Speed Impaction Surface Deformation Measurement Research","authors":"Eryi Hu","doi":"10.4236/jsip.2020.114006","DOIUrl":"https://doi.org/10.4236/jsip.2020.114006","url":null,"abstract":"In order to study the strength of the composite material plate problems, need to adopt a nondestructive testing method to obtain the specimen surface under the effect of high-speed impact regularity of shape. The projection profilometry was used to measure the surface profile or the full field deformation. Furtherly, by using the Fourier transform algorithm, there is only one frame of captured image which is needed in the measurement, so that it can be introduced into the high speed impaction procedure measurement. An experimental system, which was contained with an impact setup and the projection profilometry measurement part, was constructed for the impaction action characteristic research. The metallic impact object can be launched by a gas gun or a spin fan, respectively. The detected object is manufactured by composite materials. In order to increase the surface deformation measurement accuracy, the calibration method and the error was discussed with different calibration specimen. And then, the proposed profilometry measurement method is proved by the gas gun and spin fan projectile test. The surface deformation of the manufactured composite plates and fan case are measured in the impaction procedure. So that the impact action details can be described much more clearly than the traditional video monitoring method.","PeriodicalId":38474,"journal":{"name":"Journal of Information Hiding and Multimedia Signal Processing","volume":"27 1","pages":"103-115"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80808637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Investigation of Automatic Speech Recognition Systems via the Multilingual Deep Neural Network Modeling Methods for a Very Low-Resource Language, Chaha 基于多语言深度神经网络建模方法的低资源语言自动语音识别系统研究，查哈

Journal of Information Hiding and Multimedia Signal Processing Pub Date : 2020-01-01 DOI: 10.4236/jsip.2020.111001

Tessfu Geteye Fantaye, Junqing Yu, Tulu Tilahun Hailu

{"title":"Investigation of Automatic Speech Recognition Systems via the Multilingual Deep Neural Network Modeling Methods for a Very Low-Resource Language, Chaha","authors":"Tessfu Geteye Fantaye, Junqing Yu, Tulu Tilahun Hailu","doi":"10.4236/jsip.2020.111001","DOIUrl":"https://doi.org/10.4236/jsip.2020.111001","url":null,"abstract":"Automatic speech recognition (ASR) is vital for very low-resource languages for mitigating the extinction trouble. Chaha is one of the low-resource languages, which suffers from the problem of resource insufficiency and some of its phonological, morphological, and orthographic features challenge the development and initiatives in the area of ASR. By considering these challenges, this study is the first endeavor, which analyzed the characteristics of the language, prepared speech corpus, and developed different ASR systems. A small 3-hour read speech corpus was prepared and transcribed. Different basic and rounded phone unit-based speech recognizers were explored using multilingual deep neural network (DNN) modeling methods. The experimental results demonstrated that all the basic phone and rounded phone unit-based multilingual models outperformed the corresponding unilingual models with the relative performance improvements of 5.47% to 19.87% and 5.74% to 16.77%, respectively. The rounded phone unit-based multilingual models outperformed the equivalent basic phone unit-based models with relative performance improvements of 0.95% to 4.98%. Overall, we discovered that multilingual DNN modeling methods are profoundly effective to develop Chaha speech recognizers. Both the basic and rounded phone acoustic units are convenient to build Chaha ASR system. However, the rounded phone unit-based models are superior in performance and faster in recognition speed over the corresponding basic phone unit-based models. Hence, the rounded phone units are the most suitable acoustic units to develop Chaha ASR systems.","PeriodicalId":38474,"journal":{"name":"Journal of Information Hiding and Multimedia Signal Processing","volume":"54 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83851324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Shadow Detection Method Based on HMRF with Soft Edges for High-Resolution Remote-Sensing Images 基于软边缘HMRF的高分辨率遥感图像阴影检测方法

Journal of Information Hiding and Multimedia Signal Processing Pub Date : 2019-11-29 DOI: 10.4236/jsip.2019.104011

Wenying Ge

{"title":"Shadow Detection Method Based on HMRF with Soft Edges for High-Resolution Remote-Sensing Images","authors":"Wenying Ge","doi":"10.4236/jsip.2019.104011","DOIUrl":"https://doi.org/10.4236/jsip.2019.104011","url":null,"abstract":"Shadow detection is a crucial task in high-resolution remote-sensing image processing. Various shadow detection methods have been explored during the last decades. These methods did improve the detection accuracy but are still not robust enough to get satisfactory results for failing to extract enough information from the original images. To take full advantage of various features of shadows, a new method combining edges information with the spectral and spatial information is proposed in this paper. As known, edge is one of the most important characteristics in the high-resolution remote-sensing images. Unfortunately, in shadow detection, it is a high-risk strategy to determine whether a pixel is the edge or not strictly because intensity values on shadow boundaries are always between those in shadow and non-shadow areas. Therefore, a soft edge description model is developed to describe the degree of each pixel belonging to the edges or not. Sequentially, the soft edge description is incorporating to a fuzzy clustering procedure based on HMRF (Hidden Markov Random Fields), in which more appropriate spatial contextual information can be used. More concretely, it consists of two components: the soft edge description model and an iterative shadow detection algorithm. Experiments on several remote sensing images have shown that the proposed method can obtain more accurate shadow detection results.","PeriodicalId":38474,"journal":{"name":"Journal of Information Hiding and Multimedia Signal Processing","volume":"46 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80589352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Perceptually Lossless Compression for Mastcam Multispectral Images: A Comparative Study 桅杆凸轮多光谱图像感知无损压缩的比较研究

Journal of Information Hiding and Multimedia Signal Processing Pub Date : 2019-11-28 DOI: 10.4236/jsip.2019.104009

C. Kwan, Jude Larkin

{"title":"Perceptually Lossless Compression for Mastcam Multispectral Images: A Comparative Study","authors":"C. Kwan, Jude Larkin","doi":"10.4236/jsip.2019.104009","DOIUrl":"https://doi.org/10.4236/jsip.2019.104009","url":null,"abstract":"The two mast cameras, Mastcams, onboard Mars rover Curiosity are multispectral imagers with nine bands in each. Currently, the images are compressed losslessly using JPEG, which can achieve only two to three times of compression. We present a comparative study of four approaches to compressing multispectral Mastcam images. The first approach is to divide the nine bands into three groups with each group having three bands. Since the multispectral bands have strong correlation, we treat the three groups of images as video frames. We call this approach the Video approach. The second approach is to compress each group separately and we call it the split band (SB) approach. The third one is to apply a two-step approach in which the first step uses principal component analysis (PCA) to compress a nine-band image cube to six bands and a second step compresses the six PCA bands using conventional codecs. The fourth one is to apply PCA only. In addition, we also present subjective and objective assessment results for compressing RGB images because RGB images have been used for stereo and disparity map generation. Five well-known compression codecs, including JPEG, JPEG-2000 (J2K), X264, X265, and Daala in the literature, have been applied and compared in each approach. The performance of different algorithms was assessed using four well-known performance metrics. Two are conventional and another two are known to have good correlation with human perception. Extensive experiments using actual Mastcam images have been performed to demonstrate the various approaches. We observed that perceptually lossless compression can be achieved at 10:1 compression ratio. In particular, the performance gain of the SB approach with Daala is at least 5 dBs in terms peak signal-to-noise ratio (PSNR) at 10:1 compression ratio over that of JPEG. Subjective comparisons also corroborated with the objective metrics in that perceptually lossless compression can be achieved even at 20 to 1 compression.","PeriodicalId":38474,"journal":{"name":"Journal of Information Hiding and Multimedia Signal Processing","volume":"15 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86489407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Deep Learning Based Target Tracking and Classification for Infrared Videos Using Compressive Measurements 基于压缩测量的红外视频深度学习目标跟踪与分类

Journal of Information Hiding and Multimedia Signal Processing Pub Date : 2019-11-13 DOI: 10.4236/jsip.2019.104010

C. Kwan, Bryan Chou, Jonathan Yang, T. Tran

{"title":"Deep Learning Based Target Tracking and Classification for Infrared Videos Using Compressive Measurements","authors":"C. Kwan, Bryan Chou, Jonathan Yang, T. Tran","doi":"10.4236/jsip.2019.104010","DOIUrl":"https://doi.org/10.4236/jsip.2019.104010","url":null,"abstract":"Although compressive measurements save data storage \u0000and bandwidth usage, they are difficult to be used directly for target tracking \u0000and classification without pixel reconstruction. This is because the Gaussian \u0000random matrix destroys the target location information in the original video \u0000frames. This paper summarizes our research effort on target tracking and \u0000classification directly in the compressive measurement domain. We focus on one \u0000particular type of compressive measurement using pixel subsampling. That is, \u0000original pixels in video frames are randomly subsampled. Even in such a special \u0000compressive sensing setting, conventional trackers do not work in a \u0000satisfactory manner. We propose a deep learning approach that integrates YOLO \u0000(You Only Look Once) and ResNet (residual network) for multiple target tracking \u0000and classification. YOLO is used for multiple target tracking and ResNet is for \u0000target classification. Extensive experiments using short wave infrared (SWIR), \u0000mid-wave infrared (MWIR), and long-wave infrared (LWIR) videos demonstrated the \u0000efficacy of the proposed approach even though the training data are very \u0000scarce.","PeriodicalId":38474,"journal":{"name":"Journal of Information Hiding and Multimedia Signal Processing","volume":"32 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78890066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 18

An Adaptive EMD Technique for Induction Motor Fault Detection 自适应EMD技术在感应电机故障检测中的应用

Journal of Information Hiding and Multimedia Signal Processing Pub Date : 2019-11-13 DOI: 10.4236/jsip.2019.104008

Manzar Mahmud, Wilson Q. Wang

引用次数: 1

New Results in Perceptually Lossless Compression of Hyperspectral Images 高光谱图像感知无损压缩的新成果

Journal of Information Hiding and Multimedia Signal Processing Pub Date : 2019-08-26 DOI: 10.4236/JSIP.2019.103007

C. Kwan, Jude Larkin

{"title":"New Results in Perceptually Lossless Compression of Hyperspectral Images","authors":"C. Kwan, Jude Larkin","doi":"10.4236/JSIP.2019.103007","DOIUrl":"https://doi.org/10.4236/JSIP.2019.103007","url":null,"abstract":"Hyperspectral images (HSI) have hundreds of bands, which impose heavy \u0000burden on data storage and transmission bandwidth. Quite a few compression \u0000techniques have been explored for HSI in the past decades. One high performing \u0000technique is the combination of principal component analysis (PCA) \u0000and JPEG-2000 (J2K). However, since there are several new compression codecs \u0000developed after J2K in the past 15 years, it is worthwhile to revisit this research \u0000area and investigate if there are better techniques for HSI compression. \u0000In this paper, we present some new results in HSI compression. We aim at \u0000perceptually lossless compression of HSI. Perceptually lossless means that the \u0000decompressed HSI data cube has a performance metric near 40 dBs in terms of \u0000peak-signal-to-noise ratio (PSNR) or human visual system (HVS) based metrics. \u0000The key idea is to compare several combinations of PCA and video/ \u0000image codecs. Three representative HSI data cubes were used in our studies. \u0000Four video/image codecs, including J2K, X264, X265, and Daala, have \u0000been investigated and four performance metrics were used in our comparative \u0000studies. Moreover, some alternative techniques such as video, split band, and \u0000PCA only approaches were also compared. It was observed that the combination \u0000of PCA and X264 yielded the best performance in terms of compression \u0000performance and computational complexity. In some cases, the PCA + X264 \u0000combination achieved more than 3 dBs than the PCA + J2K combination.","PeriodicalId":38474,"journal":{"name":"Journal of Information Hiding and Multimedia Signal Processing","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74762913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 10

Adaptive Lossy Image Compression Based on Singular Value Decomposition 基于奇异值分解的有损图像自适应压缩

Journal of Information Hiding and Multimedia Signal Processing Pub Date : 2019-08-08 DOI: 10.4236/JSIP.2019.103005

M. R. Souza, H. Pedrini

引用次数: 0

Target Tracking and Classification Using Compressive Measurements of MWIR and LWIR Coded Aperture Cameras 基于MWIR和LWIR编码孔径相机压缩测量的目标跟踪与分类

Journal of Information Hiding and Multimedia Signal Processing Pub Date : 2019-08-08 DOI: 10.4236/JSIP.2019.103006

C. Kwan, Bryan Chou, Jonathan Yang, Akshay Rangamani, T. Tran, Jack Zhang, R. Etienne-Cummings

引用次数: 19