Search Results 1-20 of 59

  • 1 / 3
  • Color-based registration of point cloud data by video camera for electromagnetic simulation

    Chen Zhihang , Saito Kentaro , Okamura Wataru , Kishiki Yukiko , Takada Jun-ichi

    … Recently, the ability of smartphones makes remarkable progress, and the point cloud data of the environment can be obtained by the video camera output of the smartphone. … In this paper, we proposed the color-based registration method by extending the fast descriptor algorithm. … We applied our proposed algorithm to the point cloud data taken by the video camera of the smartphone, and proved that the calculation time was reduced by 70% in the office scenario. …

    IEICE Communications Express 9(2), 54-59, 2020


  • Infants' Pain Recognition Based on Facial Expression: Dynamic Hybrid Descriptions

    ZHI Ruicong , ZAMZMI Ghada , GOLDGOF Dmitry , ASHMEADE Terri , LI Tingting , SUN Yu

    … Both dynamic facial texture feature and dynamic geometric feature are extracted from video sequences and utilized to classify facial expression of infants as pain or no pain. … Experiments are conducted on the video acquired from NICU infants, and the best accuracy of the proposed pain assessment approaches is 95.6%. …

    IEICE Transactions on Information and Systems E101.D(7), 1860-1869, 2018


  • Identity Verification Based on Facial Pose Pool and Bag of Words Model

    Chu Wangbin , Guan Yepeng

    … It is one of fundamental topics in image processing and video analysis, and so on. … Bag of words is selected to extract image features from the facial pose pool in affine SIFT descriptor. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 21(3), 448-455, 2017


  • A Robust Method of Detecting Multi-oriented Scene Text Candidate  [in Japanese]

    ENDO Rei , KAWAI Yoshihiko , SUMIYOSHI Hideki , SANO Masanori

    … An image retrieval system based on name of person/place which reflected in news video images is required to utilize archived videos. … Moreover, we define a rotated bounding box descriptor to fast find the rotated-aspect ratio. …



  • Full-HD 60fps FPGA Implementation of Spatio-Temporal Keypoint Extraction Based on Gradient Histogram and Parallelization of Keypoint Connectivity

    SUZUKI Takahiro , IKENAGA Takeshi

    … The hardware architecture is composed of a detection module utilizing descriptor, and grid-region-parallelization based density clustering. …

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E99.A(11), 1937-1946, 2016


  • Part-wise Geodesic Histogram Shape Descriptor for Unstructured Mesh Series Segmentation

    Mukasa Tomoyuki , Nobuhara Shohei , Tung Tony , Matsuyama Takashi

    … This paper presents a novel shape descriptor for topology-based segmentation of 3D video sequences. … 3D video is a series of 3D meshes without temporal correspondences which benefit for applications including compression, motion analysis, and kinematic editing. … In 3D video, both 3D mesh connectivities and the global surface topology can change frame by frame. …

    IPSJ Transactions on Computer Vision and Applications 8(0), 29-39, 2016


  • Video Level Violence Rating  [in Japanese]

    KATO Jien , WANG Yu , ZHANG Guanwen

    … Given a video as input, we propose an approach to estimate a rate which describes the extent of "how violent it is". … Our proposed approach includes (1) a novel video descriptor called Violent Attribute Activation (VAA), and (2) a rank-prediction-based rating approach that enforces the order constrains during the rating process. …

    Technical report of IEICE. PRMU 114(521), 235-238, 2015-03-19

  • Video Level Violence Rating  [in Japanese]

    KATO Jien , WANG Yu , ZHANG Guanwen

    … Given a video as input, we propose an approach to estimate a rate which describes the extent of "how violent it is". … Our proposed approach includes (1) a novel video descriptor called Violent Attribute Activation (VAA), and (2) a rank-prediction-based rating approach that enforces the order constrains during the rating process. …

    Technical Committee on Biometrics 114(520), 235-238, 2015-03-19

  • Collective Activity Recognition by Attribute-Based Spatio-Temporal Descriptor

    CHEN Changhong , DOU Hehe , GAN Zongliang

    … Collective activity recognition plays an important role in high-level video analysis. … To overcome these drawbacks, we present a new feature representation method, called attribute-based spatio-temporal (AST) descriptor. … Then, the ST features, attribute features and the relationship between the attributes are combined to form the AST descriptor. …

    IEICE Transactions on Information and Systems E98.D(10), 1875-1878, 2015


  • Deformable Surface Dynamics Modeling

    Tony Tung

    … For example, 3D video (i.e., sequence of full 3D models) representing live human performances or daily activities (e.g., dance or yoga) can be obtained using various techniques (e.g., multiview stereo [1], [2], [3] or depth data fusion [4]). … Particularly, we introduce a timing-based low-level descriptor to capture local spatiotemporal variations, and the bag-of-timings (BoT) paradigm to further handle challenging deformable surface classification and segmentation with respect to different level of rigidities. …

    IPSJ SIG Notes. CVIM 2014-CVIM-193(21), 1, 2014-08-25

  • Effective interest point detection and clustering method for action recognition  [in Japanese]

    AIHARA Kazuaki , AOKI Terumasa

    … In this paper, we propose the Motion dense sampling, which detects very informative interest points from video frames. … Our method achieves 87.5% accuracy for video classification by using only one descriptor. …

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 113(476), 95-102, 2014-03-06

  • Human Motion Recognition Using A Spatio-tempolal Feature Descriptor  [in Japanese]

    TAKEMOTO Yoshitaka , AOKI Kota , NAGAHASHI Hiroshi

    … Second, some visual words are selected from these feature vectors obtained from various human motion video, and defined as templates. …

    Reports of the Technical Conference of the Institute of Image Electronics Engineers of Japan 13.04(0), 152-159, 2014


  • Integrating Facial Expression and Body Gesture in Videos for Emotion Recognition

    YAN Jingjie , ZHENG Wenming , XIN Minhai , YAN Jingwei

    … In this letter, we research the method of using face and gesture image sequences to deal with the video-based bimodal emotion recognition problem, in which both Harris plus cuboids spatio-temporal feature (HST) and sparse canonical correlation analysis (SCCA) fusion method are applied to this end. …

    IEICE Transactions on Information and Systems E97.D(3), 610-613, 2014


  • Low Complexity Keypoint Extraction Based on SIFT Descriptor and Its Hardware Implementation for Full-HD 60 fps Video

    SUZUKI Takahiro , IKENAGA Takeshi

    … This paper proposes a low complexity keypoint extraction algorithm based on SIFT descriptor and utilization of the database, and its real-time hardware implementation for Full-HD resolution video. … The proposed algorithm computes SIFT descriptor on the keypoint obtained by corner detection and selects a scale from the database. … It is possible to parallelize the keypoint detection and descriptor computation modules in the hardware. …

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences 96(6), 1376-1383, 2013-06-01

    J-STAGE  References (20)

  • Facial Micro-Expression Detection in Hi-Speed Video Based on Facial Action Coding System (FACS)

    POLIKOVSKY Senya , KAMEDA Yoshinari , OHTA Yuichi

    … The core of this method is based on a descriptor that combines pre-processing masks, histograms and concatenation of spatial-temporal gradient vectors. … Presented 3D gradient histogram descriptor is able to detect and measure the timing characteristics of the fast and subtle changes of the facial skin surface. … The Facial Action Coding System was utilized to annotate the appearance and dynamics of the expressions in our new hi-speed micro-expressions video database. …

    IEICE Transactions on Information and Systems 96(1), 81-92, 2013-01-01

    IR  J-STAGE  References (30)

  • [Paper] Using Trajectory Features to Recognize Human Actions Within Crowd Sequences of Real Surveillance Video

    Takahashi Masaki , Naemura Masahide , Fujii Mahito , Satoh Shin'ichi

    … There is growing interest in automatic recognition of human actions in video sequences shot by surveillance cameras. … That is, almost all of the current techniques can only detect simple actions within video sequences showing controlled environments. … We propose action recognition methods based on multiple trajectories that can identify human actions within crowd sequences of real surveillance video. …

    ITE Transactions on Media Technology and Applications 1(2), 118-126, 2013


  • Video Signature Robust to Modifications for Large-scale Video Identification  [in Japanese]

    IWAMOTO Kota , OAMI Ryoma , SATO Takami , NOMURA Toshiyuki

    … This paper presents comparative evaluation of a robust frame-level descriptor for video identification, called a Video Signature, which was previously developed by the authors and was accepted as part of a new ISO/IEC standard “MPEG-7 Video Signature Tools”. …

    Journal of the Japan Society for Precision Engineering 79(11), 1089-1095, 2013


  • FPGA Implementation of HOG-based Real-Time Object Detection Processor  [in Japanese]

    TAKAGI Kenta , MIZUNO Kosuke , IZUMI Shintaro , KAWAGUCHI Hiroshi , YOSHIMOTO Masahiko

    … Histogram of Oriented Gradients (HOG) is widely accepted feature descriptor for object detection. … Results show that the proposed architecture can generate HOG features and detect objects with 40 MHz for SVGA resolution video (800 × 600 pixels) at 72 frames per second (fps). …

    Technical report of IEICE. ICD 112(365), 61, 2012-12-10

  • Reduced-Reference Objective Quality Assessment Model of Coded Video Sequences Based on the MPEG-7 Descriptor

    SATO Masaharu , HORITA Yuukou

    … Our research is focused on examining the video quality assessment model based on the MPEG-7 descriptor. … Video quality is estimated by using several features based on the predicted frame quality such as average value, worst value, best value, standard deviation, and the predicted frame rate obtained from descriptor information. …

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences 95(8), 1259-1263, 2012-08-01

    J-STAGE  References (13)

  • Topology Dictionary for 3D Video Understanding

    Tung Tony , Matsuyama Takashi

    … This paper presents a novel approach that achieves 3D video understanding. … 3D video consists of a stream of 3D models of subjects in motion. … We propose the topology dictionary to encode and describe 3D video content. … The model consists of a topology-based shape descriptor dictionary which can be generated from either extracted patterns or training sequences. …

    IEEE transactions on pattern analysis and machine intelligence 34(8), 1645-1657, 2012-08


  • 1 / 3
Page Top