• Title, Summary, Keyword: frame descriptor

Search Result 25, Processing Time 0.039 seconds

Frame-level Matching for Near Duplicate Videos Using Binary Frame Descriptor (이진 프레임 기술자를 이용한 유사중복 동영상 프레임 단위 정합)

  • Kim, Kyung-Rae;Lee, Jun-Tae;Jang, Won-Dong;Kim, Chang-Su
    • Journal of Broadcast Engineering
    • /
    • v.20 no.4
    • /
    • pp.641-644
    • /
    • 2015
  • In this paper, we propose a precise frame-level near-duplicate video matching algorithm. First, a binary frame descriptor for near-duplicate video matching is proposed. The binary frame descriptor divides a frame into patches and represent the relations between patches in bits. Seconds, we formulate a cost function for the matching, composed of matching costs and compensatory costs. Then, we roughly determine initial matchings and refine the matchings iteratively to minimize the cost function. Experimental results demonstrate that the proposed algorithm provides efficient performance for frame-level near duplicate video matching.

Robust HDR Video Synthesis Using Illumination Invariant Descriptor (밝기 변화에 강인한 특징 기술자를 이용한 고품질 HDR 동영상 합성)

  • Vo Van, Tu;Lee, Chul
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • /
    • pp.83-84
    • /
    • 2017
  • We propose a novel high dynamic range (HDR) video synthesis algorithm from alternatively exposed low dynamic range (LDR) videos. We first estimate correspondences between input fames using an illumination invariant descriptor. Then, we synthesize an HDR frame with the weights computed to maximize detail preservation in the output HDR frame. Experimental results demonstrate that the proposed algorithm provides high-quality HDR videos without noticeable artifacts.

  • PDF

The Extracting Method of Key-frame Using Color Layout Descriptor (컬러 레이아웃을 이용한 키 프레임 추출 기법)

  • 김소희;김형준;지수영;김회율
    • Proceedings of the IEEK Conference
    • /
    • /
    • pp.213-216
    • /
    • 2001
  • Key frame extraction is an important method of summarizing a long video. This paper propose a technique to automatically extract several key frames representative of its content from video. We use the color layout descriptor to select key frames from video. For selection of key frames, we calculate similarity of color layout features extracted from video, and extract key frames using similarity. An important aspect of our algorithm is that does not assume a fixed number of key frames per video; instead, it selects the number of appropriate key frames of summarizing a long video Experimental results show that our method using color layout descriptor can successfully select several key frames from a video, and we confirmed that the processing speed for extracting key frames from video is considerably fast.

  • PDF

Detecting near-duplication Video Using Motion and Image Pattern Descriptor (움직임과 영상 패턴 서술자를 이용한 중복 동영상 검출)

  • Jin, Ju-Kyong;Na, Sang-Il;Jenong, Dong-Seok
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.48 no.4
    • /
    • pp.107-115
    • /
    • 2011
  • In this paper, we proposed fast and efficient algorithm for detecting near-duplication based on content based retrieval in large scale video database. For handling large amounts of video easily, we split the video into small segment using scene change detection. In case of video services and copyright related business models, it is need to technology that detect near-duplicates, that longer matched video than to search video containing short part or a frame of original. To detect near-duplicate video, we proposed motion distribution and frame descriptor in a video segment. The motion distribution descriptor is constructed by obtaining motion vector from macro blocks during the video decoding process. When matching between descriptors, we use the motion distribution descriptor as filtering to improving matching speed. However, motion distribution has low discriminability. To improve discrimination, we decide to identification using frame descriptor extracted from selected representative frames within a scene segmentation. The proposed algorithm shows high success rate and low false alarm rate. In addition, the matching speed of this descriptor is very fast, we confirm this algorithm can be useful to practical application.

A motion descriptor design combining the global feature of an image and the local one of an moving object (영상의 전역 특징과 이동객체의 지역 특징을 융합한 움직임 디스크립터 설계)

  • Jung, Byeong-Man;Lee, Kyu-Won
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • /
    • pp.898-902
    • /
    • 2012
  • A descriptor which is suitable for motion analysis by using the motion features of moving objects from the real time image sequence is proposed. To segment moving objects from the background, the background learning is performed. We extract motion trajectories of individual objects by using the sequence of the $1^{st}$ order moment of moving objects. The center points of each object are managed by linked list. The descriptor includes the $1^{st}$ order coordinates of moving object belong to neighbor of the per-defined position in grid pattern, the start frame number which a moving object appeared in the scene and the end frame number which it disappeared. A video retrieval by the proposed descriptor combining global and local feature is more effective than conventional methods which adopt a single feature among global and local features.

  • PDF

A Descriptor Design for the Video Retrieval Combining the Global Feature of an Image and the Local of a Moving Object (영상의 전역 특징과 이동객체의 지역 특징을 융합한 동영상 검색 디스크립터 설계)

  • Jung, Byung-Man;Lee, Kyu-Won
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.18 no.1
    • /
    • pp.142-148
    • /
    • 2014
  • A descriptor which is suitable for motion analysis by using the motion features of moving objects from the real time image sequence is proposed. To segment moving objects from the background, the background learning is performed. We extract motion trajectories of individual objects by using the sequence of the 1st order moment of moving objects. The center points of each object are managed by linked list. The descriptor includes the 1st order coordinates of moving object belong to neighbor of the pre-defined position in grid pattern, The start frame number which a moving object appeared in the scene and the end frame number which it disappeared. A video retrieval by the proposed descriptor combining global and local feature is more effective than conventional methods which adopt a single feature among global and local features.

Content based Video Copy Detection Using Spatio-Temporal Ordinal Measure (시공간 순차 정보를 이용한 내용기반 복사 동영상 검출)

  • Jeong, Jae-Hyup;Kim, Tae-Wang;Yang, Hun-Jun;Jin, Ju-Kyong;Jeong, Dong-Seok
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.49 no.2
    • /
    • pp.113-121
    • /
    • 2012
  • In this paper, we proposed fast and efficient algorithm for detecting near-duplication based on content based retrieval in large scale video database. For handling large amounts of video easily, we split the video into small segment using scene change detection. In case of video services and copyright related business models, it is need to technology that detect near-duplicates, that longer matched video than to search video containing short part or a frame of original. To detect near-duplicate video, we proposed motion distribution and frame descriptor in a video segment. The motion distribution descriptor is constructed by obtaining motion vector from macro blocks during the video decoding process. When matching between descriptors, we use the motion distribution descriptor as filtering to improving matching speed. However, motion distribution has low discriminability. To improve discrimination, we decide to identification using frame descriptor extracted from selected representative frames within a scene segmentation. The proposed algorithm shows high success rate and low false alarm rate. In addition, the matching speed of this descriptor is very fast, we confirm this algorithm can be useful to practical application.

A High-performance Lane Recognition Algorithm Using Word Descriptors and A Selective Hough Transform Algorithm with Four-channel ROI (다중 ROI에서 영상 화질 표준화 및 선택적 허프 변환 알고리즘을 통한 고성능의 차선 인식 알고리즘)

  • Cho, Jae-Hyun;Jang, Young-Min;Cho, Sang-Bok
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.52 no.2
    • /
    • pp.148-161
    • /
    • 2015
  • The examples that used camera in the vehicle is increasing with the growth of the automotive market, and the importance of the image processing technique is expanding. In particular, the Lane Departure Warning System (LDWS) and related technologies are under development in various fields. In this paper, in order to improve the lane recognition rate more than the conventional method, we extract a Normalized Luminance Descriptor value and a Normalized Contrast Descriptor value, and adjust image gamma values to modulate Normalized Image Quality by using the correlation between the extracted two values. Then, we apply the Hough transform using the optimized accumulator cells to the four-channel ROI. The proposed algorithm was verified in 27 frame/sec and $640{\times}480$ resolution. As a result, Lane recognition rate was higher than the average 97% in day, night, and late-night road environments. The proposed method also shows successful lane recognition in sections with curves or many lane boundary.

Key frame extraction using Fourier transform (퓨리에 변환을 이용한 키 프레임 추출)

  • 이중용;문영식
    • Proceedings of the IEEK Conference
    • /
    • /
    • pp.179-182
    • /
    • 2001
  • In this paper. a key frame extraction algorithm for browsing and searching the summary of a video is proposed. Toward this end, important frames representing a shot are selected according to the correlations among frames. by using the Fourier descriptor which is useful for the shot boundary detection. To quantitatively evaluate the importance of selected frames. a new measure based on correlation coefficients of frames is proposed. If there are several frames with a same importance. another criteria is introduced to break the tie. by computing the partial moment of subframes including each candidate key frame so that the distortion rate is minimized Since a key frame extraction algorithm can be evaluated subjectively. the performance of the proposed algorithm has been verified by a statistical test. Experiments show that more than 20% improvement has been obtained by the proposed algorithm compared to existing methods.

  • PDF

Hierarchical Graph Based Segmentation and Consensus based Human Tracking Technique

  • Ramachandra, Sunitha Madasi;Jayanna, Haradagere Siddaramaiah;Ramegowda, Ramegowda
    • Journal of Information Processing Systems
    • /
    • v.15 no.1
    • /
    • pp.67-90
    • /
    • 2019
  • Accurate detection, tracking and analysis of human movement using robots and other visual surveillance systems is still a challenge. Efforts are on to make the system robust against constraints such as variation in shape, size, pose and occlusion. Traditional methods of detection used the sliding window approach which involved scanning of various sizes of windows across an image. This paper concentrates on employing a state-of-the-art, hierarchical graph based method for segmentation. It has two stages: part level segmentation for color-consistent segments and object level segmentation for category-consistent regions. The tracking phase is achieved by employing SIFT keypoint descriptor based technique in a combined matching and tracking scheme with validation phase. Localization of human region in each frame is performed by keypoints by casting votes for the center of the human detected region. As it is difficult to avoid incorrect keypoints, a consensus-based framework is used to detect voting behavior. The designed methodology is tested on the video sequences having 3 to 4 persons.