2017 2nd International Conference on Multimedia and Image Processing (ICMIP)最新文献

Content Classification Based Reference Frame Reduction and Machine Learning Based Non-square Block Partition Skipping for Inter Prediction of Screen Content Coding 基于内容分类的参考框架约简和基于机器学习的非方块分割跳跃式屏幕内容编码内部预测

2017 2nd International Conference on Multimedia and Image Processing (ICMIP) Pub Date : 2017-12-15 DOI: 10.1109/ICMIP.2017.58

Yawei Wang, Gaoxing Chen, T. Ikenaga

{"title":"Content Classification Based Reference Frame Reduction and Machine Learning Based Non-square Block Partition Skipping for Inter Prediction of Screen Content Coding","authors":"Yawei Wang, Gaoxing Chen, T. Ikenaga","doi":"10.1109/ICMIP.2017.58","DOIUrl":"https://doi.org/10.1109/ICMIP.2017.58","url":null,"abstract":"Screen Content Coding (SCC) is the extension of the latest video compression standard High Efficiency Video Coding (HEVC). SCC is mainly developed for reducing the bit-rate of videos generated from computers. However, under inter configuration, SCC has large complexity which brings heavy burden to encoding. This paper proposes a content classification based reference frame reduction method and a non-square prediction unit (PU) skipping method to accelerate SCC. In reference frame reduction method, according to number of colors, input coding tree unit (CTUs) will be divided into two classes: natural contents and screen contents. For each class, reference frame can be reduced based on different standard. In PU partition skipping method, five features are extracted from a CTU. The classic learning tool SVM is used to classify CTUs, then six non-square PU partition in depth 1, 2, 3 can be skipped. Finally, 40.83% encoding time saving on average is achieved with only 0.71% BD-rate degradation compared with SCC reference software (SCM6.0).","PeriodicalId":227455,"journal":{"name":"2017 2nd International Conference on Multimedia and Image Processing (ICMIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129686800","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

Real-Time 3D Ball Tracking with CPU-GPU Acceleration Using Particle Filter with Multi-command Queues and Stepped Parallelism Iteration 基于多命令队列和步进并行迭代粒子滤波的CPU-GPU加速实时三维球跟踪

2017 2nd International Conference on Multimedia and Image Processing (ICMIP) Pub Date : 2017-12-15 DOI: 10.1109/ICMIP.2017.59

Yilin Hou, Xina Cheng, T. Ikenaga

{"title":"Real-Time 3D Ball Tracking with CPU-GPU Acceleration Using Particle Filter with Multi-command Queues and Stepped Parallelism Iteration","authors":"Yilin Hou, Xina Cheng, T. Ikenaga","doi":"10.1109/ICMIP.2017.59","DOIUrl":"https://doi.org/10.1109/ICMIP.2017.59","url":null,"abstract":"3D ball tracking is a critical function in manyapplications such as game and players behavior analysis, andreal time implementation has become increasingly importantfor it can be used for live broadcast and TV contents. To reacha high accuracy, algorithms usually are time consuming due toa large set of calculations which is challenging to meet realtime demanding. This paper proposes multiple commandqueues, tactical threads allocation and stepped iterativeaddition to empower such a capacity on the CPU-GPUplatform. Multiple command queues achieves a parallelismbetween tasks in the algorithm. Secondly, the tactical threadsallocation helps mapping the algorithm into GPU andenhances synchronism between threads. And this paperproposes stepped iterative addition to achieve partialparallelism in a sequential operation. This work implements inan Intel Core i7-6700 GPU and AMD Radeon R9 FURY GPU.Tracking speed of our work increases 37.8 times from original431ms to 11.7ms while the success rate of the algorithm retainsover 99%. This result fully meets the requirement of 16.6msper frame for 60fps video real-time tracking.","PeriodicalId":227455,"journal":{"name":"2017 2nd International Conference on Multimedia and Image Processing (ICMIP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125209160","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: 9

Automatic Registration Method of SAR and Optical Image Based on Line Features and Spectral Graph Theory 基于线特征和谱图理论的SAR与光学图像自动配准方法

2017 2nd International Conference on Multimedia and Image Processing (ICMIP) Pub Date : 2017-03-17 DOI: 10.1109/ICMIP.2017.49

Guoping Zhang, H. Sui, Zhina Song, Feng Hua, L. Hua

引用次数: 3

Automatic Parking Space Detection System 自动车位检测系统

2017 2nd International Conference on Multimedia and Image Processing (ICMIP) Pub Date : 2017-03-17 DOI: 10.1109/ICMIP.2017.4

Nazia Bibi, Muhammad Majid, H. Dawood, Ping Guo

引用次数: 42

Method of Remote Sensing Image Enhancement in NSST Domain Based on Multi-stages Particle Swarm Optimization 基于多阶段粒子群优化的NSST域遥感图像增强方法

2017 2nd International Conference on Multimedia and Image Processing (ICMIP) Pub Date : 2017-03-01 DOI: 10.1109/ICMIP.2017.54

D. Sheng, Yiquan Wu

{"title":"Method of Remote Sensing Image Enhancement in NSST Domain Based on Multi-stages Particle Swarm Optimization","authors":"D. Sheng, Yiquan Wu","doi":"10.1109/ICMIP.2017.54","DOIUrl":"https://doi.org/10.1109/ICMIP.2017.54","url":null,"abstract":"To further improve the definition and contrast of remote sensing images, a method of remote sensing image enhancement in non-subsampled shearlet transform (NSST) domain is proposed based on multi-stages particle swarm optimization (MSPSO) algorithm and fuzzy sets. Firstly, the image to be enhanced is decomposed into a low-frequency sub-band and several high-frequency sub-bands through NSST. Secondly, the coefficients of high-frequency sub-bands are enhanced according to adaptive Bayesian threshold method and nonlinear gain function, while that of the low-frequency sub-band is processed by using the fuzzy enhancement method with its fuzzy parameters optimized by MSPSO algorithm. A comparison is made among the proposed method, bidirectional histogram equalization method, stationary wavelet transform method, non-subsampled contourlet transform (NSCT) adaptive threshold method and artificial bee colony (ABC) optimization method in NSCT domain in terms of the subjective visual effect and objective quantitative evaluation indices such as contrast gain, definition gain and information entropy. Experimental results show that the method proposed in this paper can effectively improve the contrast and definition of remote sensing images and enhance edges details with better visual effect.","PeriodicalId":227455,"journal":{"name":"2017 2nd International Conference on Multimedia and Image Processing (ICMIP)","volume":"114 3-4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116460771","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

Examination of Shear Cut Mark Based on Local Multiscale Fractal Analysis 基于局部多尺度分形分析的剪切割痕检测

2017 2nd International Conference on Multimedia and Image Processing (ICMIP) Pub Date : 2017-03-01 DOI: 10.1109/ICMIP.2017.31

Li Mou, Min Yang, Cheng-Zhong Zhan, Yi-Ming Fu

{"title":"Examination of Shear Cut Mark Based on Local Multiscale Fractal Analysis","authors":"Li Mou, Min Yang, Cheng-Zhong Zhan, Yi-Ming Fu","doi":"10.1109/ICMIP.2017.31","DOIUrl":"https://doi.org/10.1109/ICMIP.2017.31","url":null,"abstract":"Examination and identification of tool marks is traditionally carried out under a comparison microscope by forensic scientists. This manual process is dependent on the experience of the examiner, including subjectivity. In order to improve the reliability and repeatability of the process in criminal investigation and trial, automation and quantification for tool mark examination is demanded. Shear cut tool mark is a classic type of tool marks. Local self-similarity appears on the shear cut mark. A local multi-scale fractal analysis method is developed to classify shear cut marks by using the surface characteristics of artificial marks. A shear cut mark is divided into four regions based on the consistence of the image texture. The local extended fractal dimensions of four scales are calculated along x-direction and y-direction for each region of a shear cut tool mark. Total thirty-two dimensional features for one mark are grouped into a feature vector which represents the texture of a shear cut mark. Finally, the feature vector is input into a Bayes classifier to classify the marks. Experimental results show that the classification rate using local multi-scale fractal features is significantly improved in comparison with using global feature.","PeriodicalId":227455,"journal":{"name":"2017 2nd International Conference on Multimedia and Image Processing (ICMIP)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122913322","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

A New Method for the Nonintrusive Load Monitoring Based on BP Neural Network 基于BP神经网络的非侵入式负荷监测新方法

2017 2nd International Conference on Multimedia and Image Processing (ICMIP) Pub Date : 2017-03-01 DOI: 10.1109/ICMIP.2017.55

TiangYang Wang, Bo Yin

引用次数: 2

No-Reference Stereoscopic Image Quality Assessment Using Natural Scene Statistics 基于自然场景统计的无参考立体图像质量评估

2017 2nd International Conference on Multimedia and Image Processing (ICMIP) Pub Date : 2017-03-01 DOI: 10.1109/ICMIP.2017.61

Yanqing Li, Xinping Hu

{"title":"No-Reference Stereoscopic Image Quality Assessment Using Natural Scene Statistics","authors":"Yanqing Li, Xinping Hu","doi":"10.1109/ICMIP.2017.61","DOIUrl":"https://doi.org/10.1109/ICMIP.2017.61","url":null,"abstract":"Stereoscopic image quality assessment is an effective way to evaluate the performance of stereoscopic video systems. However, the most of existing 3D quality assessment methods cant be consistent with the subjective results caused by unconsidered the information of 3D depth or disparity. In this paper, a blind image quality assessment method for stereoscopic images is proposed using deep learning and natural scene statistics. The proposed method is composed of two stages: firstly, the 3D distorted image is classified into symmetrical or asymmetrical distortion using the characteristics of wavelet domain and disparity information of 3D image. The Deep Belief Network (DBNs) is used to classify the wavelet domain features to distortion types. Then, the mapping relationship between the NSS features and 3D image quality is established according to the distortion type. The experiment is tested on the LIVE 3D database which includes both symmetric- and asymmetric-distorted stereoscopic 3D images. Experimental results show that the proposed objective method achieves consistent stereoscopic image quality evaluation results with subjective assessment for various types of distortion, especially show its effectiveness for assessing stereoscopic imagewithcross-distortion.","PeriodicalId":227455,"journal":{"name":"2017 2nd International Conference on Multimedia and Image Processing (ICMIP)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116361428","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: 44

3D Convolutional Neural Network Based on Face Anti-spoofing 基于人脸抗欺骗的三维卷积神经网络

2017 2nd International Conference on Multimedia and Image Processing (ICMIP) Pub Date : 2017-03-01 DOI: 10.1109/ICMIP.2017.9

Junying Gan, Shanlu Li, Yikui Zhai, Chengyun Liu

引用次数: 70

Aligning Algorithm of 3D Point Cloud Model Based on Dimensionality Reduction 基于降维的三维点云模型对齐算法

2017 2nd International Conference on Multimedia and Image Processing (ICMIP) Pub Date : 2017-03-01 DOI: 10.1109/ICMIP.2017.34

Lijiang He, Zhi Li, Shuqin Chen

引用次数: 1