• Title/Summary/Keyword: Video sequence

Search Result 507, Processing Time 0.026 seconds

Lightweight Video-based Approach for Monitoring Pigs' Aggressive Behavior (돼지 공격 행동 모니터링을 위한 영상 기반의 경량화 시스템)

  • Mluba, Hassan Seif;Lee, Jonguk;Atif, Othmane;Park, Daihee;Chung, Yongwha
    • Annual Conference of KIPS
    • /
    • 2021.11a
    • /
    • pp.704-707
    • /
    • 2021
  • Pigs' aggressive behavior represents one of the common issues that occur inside pigpens and which harm pigs' health and welfare, resulting in a financial burden to farmers. Continuously monitoring several pigs for 24 hours to identify those behaviors manually is a very difficult task for pig caretakers. In this study, we propose a lightweight video-based approach for monitoring pigs' aggressive behavior that can be implemented even in small-scale farms. The proposed system receives sequences of frames extracted from an RGB video stream containing pigs and uses MnasNet with a DM value of 0.5 to extract image features from pigs' ROI identified by predefined annotations. These extracted features are then forwarded to a lightweight LSTM to learn temporal features and perform behavior recognition. The experimental results show that our proposed model achieved 0.92 in recall and F1-score with an execution time of 118.16 ms/sequence.

A Method of Generating Table-of-Contents for Educational Video (교육용 비디오의 ToC 자동 생성 방법)

  • Lee Gwang-Gook;Kang Jung-Won;Kim Jae-Gon;Kim Whoi-Yul
    • Journal of Broadcast Engineering
    • /
    • v.11 no.1 s.30
    • /
    • pp.28-41
    • /
    • 2006
  • Due to the rapid development of multimedia appliances, the increasing amount of multimedia data enforces the development of automatic video analysis techniques. In this paper, a method of ToC generation is proposed for educational video contents. The proposed method consists of two parts: scene segmentation followed by scene annotation. First, video sequence is divided into scenes by the proposed scene segmentation algorithm utilizing the characteristics of educational video. Then each shot in the scene is annotated in terms of scene type, existence of enclosed caption and main speaker of the shot. The ToC generated by the proposed method represents the structure of a video by the hierarchy of scenes and shots and gives description of each scene and shot by extracted features. Hence the generated ToC can help users to perceive the content of a video at a glance and. to access a desired position of a video easily. Also, the generated ToC automatically by the system can be further edited manually for the refinement to effectively reduce the required time achieving more detailed description of the video content. The experimental result showed that the proposed method can generate ToC for educational video with high accuracy.

Context-Dependent Video Data Augmentation for Human Instance Segmentation (인물 개체 분할을 위한 맥락-의존적 비디오 데이터 보강)

  • HyunJin Chun;JongHun Lee;InCheol Kim
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.12 no.5
    • /
    • pp.217-228
    • /
    • 2023
  • Video instance segmentation is an intelligent visual task with high complexity because it not only requires object instance segmentation for each image frame constituting a video, but also requires accurate tracking of instances throughout the frame sequence of the video. In special, human instance segmentation in drama videos has an unique characteristic that requires accurate tracking of several main characters interacting in various places and times. Also, it is also characterized by a kind of the class imbalance problem because there is a significant difference between the frequency of main characters and that of supporting or auxiliary characters in drama videos. In this paper, we introduce a new human instance datatset called MHIS, which is built upon drama videos, Miseang, and then propose a novel video data augmentation method, CDVA, in order to overcome the data imbalance problem between character classes. Different from the previous video data augmentation methods, the proposed CDVA generates more realistic augmented videos by deciding the optimal location within the background clip for a target human instance to be inserted with taking rich spatio-temporal context embedded in videos into account. Therefore, the proposed augmentation method, CDVA, can improve the performance of a deep neural network model for video instance segmentation. Conducting both quantitative and qualitative experiments using the MHIS dataset, we prove the usefulness and effectiveness of the proposed video data augmentation method.

An Efficient Video Dehazing to Without Flickering Artifacts (비디오에서 플리커 현상이 없는 효율적인 안개제거)

  • Kim, Young Min;Park, Ki Tae;Lee, Dong Seok;Choi, Wonju;Moon, Young Shik
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.51 no.8
    • /
    • pp.51-57
    • /
    • 2014
  • In this paper, we propose a novel method to effectively eliminate flickering artifacts caused by dehazing in video sequences. When applying a dehazing technique directly to each image in a video sequence, flicker artifacts may occur because atmospheric values are calculated without considering the relation of adjacent frames. Although some existing methods reduce flickering artifacts by calculating highly correlated transmission values between adjacent frames, flickering artifacts may still occur. Therefore, in order to effectively reduce flickering artifacts, we propose a novel approach considering temporal averages of atmospheric light values calculated from adjacent frames. Experimental results have shown that the proposed method achieves better performance of video dehazing with less flickering artifact than existing methods.

Digital Video Scrambling Method using Intra Prediction Mode of H.264 (H.264 인트라 예측 모드를 이용한 디지털 비디오 스크램블링 방법)

  • Ahn Jinhaeng;Jeon Byeungwoo
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.42 no.2 s.302
    • /
    • pp.59-68
    • /
    • 2005
  • The amount of digitalized contents has been rapidly increased, but the main distribution channel of them is Internet which is easily accessible. Therefore 'security' necessarily arises as one of the most important issues and the method of protecting contents becomes a major research topic as much as data coding techniques. In recent years, many developers have studied on techniques that allow only authorized person to access contents. Among them the scrambling method is one of well-known security techniques. In this paper, we propose a simple and effective digital video scrambling method which utilizes the intra block properties of a recent video coding technique, H.264. Since intra prediction modes are adopted in H.264 standard, it is easy to scramble a video sequence with modification of the intra prediction modes. In addition to its simplicity, the proposed method does not increase bit rate after scrambling. The inter blocks are also distorted by scrambling intra blocks only. This paper introduces a new digital video scrambling method and verifies its effectiveness through simulation.

Ontology and Sequential Rule Based Streaming Media Event Recognition (온톨로지 및 순서 규칙 기반 대용량 스트리밍 미디어 이벤트 인지)

  • Soh, Chi-Seung;Park, Hyun-Kyu;Park, Young-Tack
    • Journal of KIISE
    • /
    • v.43 no.4
    • /
    • pp.470-479
    • /
    • 2016
  • As the number of various types of media data such as UCC (User Created Contents) increases, research is actively being carried out in many different fields so as to provide meaningful media services. Amidst these studies, a semantic web-based media classification approach has been proposed; however, it encounters some limitations in video classification because of its underlying ontology derived from meta-information such as video tag and title. In this paper, we define recognized objects in a video and activity that is composed of video objects in a shot, and introduce a reasoning approach based on description logic. We define sequential rules for a sequence of shots in a video and describe how to classify it. For processing the large amount of increasing media data, we utilize Spark streaming, and a distributed in-memory big data processing framework, and describe how to classify media data in parallel. To evaluate the efficiency of the proposed approach, we conducted an experiment using a large amount of media ontology extracted from Youtube videos.

A Video Watermarking Based on Wavelet Transform Using Spread Spectrum Technique (대역확산방법을 이용한 웨이블릿 기반의 비디오 워터마킹)

  • Kim, Seung-Jin;Kim, Tae-Su;Lee, Kuhn-Il
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.42 no.5 s.305
    • /
    • pp.11-18
    • /
    • 2005
  • In this paper, we proposed a video watermarking algerian based on wavelet transform using statistical characteristic of video according to the energy distribution and the spread spectrum technique. In the proposed method, the original video is splitted by spatial difference metric and classified into the motion region and the motionless region according to the motion degree. The motion region is decomposed into 3-levels using 3D DWT and the motionless region is decomposed into 2-levels using 2D DWT The baseband of the wavelet-decomposed image is not utilized because of the image quality. So that the standard deviation of the highest subband coefficients except for the baseband is used to determine the threshold. Binary video watermarks preprocessed by the random permutation and the spread spectrum technique are embedded into selected coefficients. In computer experiments, the proposed algorithm was found to be more invisible and robust than the conventional algorithms.

A Fast Block Matching Motion Estimation Algorithm by using an Enhanced Cross-Flat Hexagon Search Pattern (개선된 크로스-납작한 육각 탐색 패턴을 이용한 고속 블록 정합 움직임 예측 알고리즘)

  • Nam, Hyeon-Woo
    • Journal of the Korea Society of Computer and Information
    • /
    • v.13 no.7
    • /
    • pp.99-108
    • /
    • 2008
  • For video compression, we have to consider two performance factors that are the search speed and coded video's quality. In this paper, we propose an enhanced fast block matching algorithm using the spatial correlation of the video sequence and the center-biased characteristic of motion vectors(MV). The proposed algorithm first finds a predicted motion vector from the adjacent macro blocks of the current frame and determines an exact motion vector using the cross pattern and a flat hexagon search pattern. From the performance evaluations, we can see that our algorithm outperforms both the hexagon-based search(HEXBS) and the cross-hexagon search(CHS) algorithms in terms of the search speed and coded video's quality. Using our algorithm, we can improve the search speed by up to 31%, and also increase the PSNR(Peak Signal Noise Ratio) by at most 0.5 dB, thereby improving the video quality.

  • PDF

A Video Watermarking Using 3D DWT and Binary Image Watermark (3차원 웨이블릿 변환과 이진 영상 워터마크를 이용한 비디오 워터마킹)

  • Kim Seung-Jin;Kim Tae-Su;Kwon Ki-Ryong;Lee Kuhn-Il
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.42 no.6
    • /
    • pp.27-32
    • /
    • 2005
  • An effective video watermarking algorithm is proposed to protect the copyright. The watermarking procedure is based on a three-dimensional discrete wavelet transform (3D DWT) and spread spectrum sequences. Two perceptual binary watermarks are preprocessed using mixing and pseudorandom permutation. After dividing the video sequence into video shots, the 3D DWT is performed, then the preprocessed watermarks are embedded into the 3D DWT coefficients, while considering robustness and invisibility, using two spread spectrum sequences defined as the user key. Experimental results show that the watermarked frames are subjectively indistinguishable from the original frames, plus the proposed video watermarking algorithm is sufficiently robust against such attacks as low pass filtering, frame dropping, frame average, and MPEG coding.

Channel-Adaptive Mobile Streaming Video Control over Mobile WiMAX Network (모바일 와이맥스망에서 채널 적응적인 모바일 스트리밍 비디오 제어)

  • Pyun, Jae-Young
    • Journal of the Institute of Electronics Engineers of Korea CI
    • /
    • v.46 no.5
    • /
    • pp.37-43
    • /
    • 2009
  • Streaming video service over wireless and mobile communication networks has received significant interests from both academia and industry recently. Specifically, mobile WiMAX (IEEE 802.16e) is capable of providing high data rate and flexible Quality of Service (QoS) mechanisms, supporting mobile streaming very attractive. However, we need to note that streaming videos can be partially deteriorated in their macroblocks and/or slices owing to errors on OFDMA subcarriers, as we consider that compressed video sequence is generally sensitive to the error-prone channel status of the wireless and mobile network. In this paper, we introduce an OFDMA subcarrier-adaptive mobile streaming server based on cross-layer design. This streaming server system is substantially efficient to reduce the deterioration of streaming video transferred on the subcarriers of low power strength without any modifications of the existing schedulers, packet ordering/reassembly, and subcarrier allocation strategies in the base station.