Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Flux Tensor Constrained Geodesic Active Contours with Sensor Fusion for Persistent Object Tracking  [cached]
Filiz Bunyak,Kannappan Palaniappan,Sumit Kumar Nath,Gunasekaran Seetharaman
Journal of Multimedia , 2007, DOI: 10.4304/jmm.2.4.20-33
Abstract: This paper makes new contributions in motion detection, object segmentation and trajectory estimation to create a successful object tracking system. A new efficient motion detection algorithm referred to as the flux tensor is used to detect moving objects in infrared video without requiring background modeling or contour extraction. The flux tensor-based motion detector when applied to infrared video is more accurate than thresholding ”hot-spots”, and is insensitive to shadows as well as illumination changes in the visible channel. In real world monitoring tasks fusing scene information from multiple sensors and sources is a useful core mechanism to deal with complex scenes, lighting conditions and environmental variables. The object segmentation algorithm uses level set-based geodesic active contour evolution that incorporates the fusion of visible color and infrared edge informations in a novel manner. Touching or overlapping objects are further refined during the segmentation process using an appropriate shapebased model. Multiple object tracking using correspondence graphs is extended to handle groups of objects and occlusion events by Kalman filter-based cluster trajectory analysis and watershed segmentation. The proposed object tracking algorithm was successfully tested on several difficult outdoor multispectral videos from stationary sensors and is not confounded by shadows or illumination variations.
Video Object Extraction Algorithm Based on Spatio-temporal Information in Dynamic Scene

TIAN Hong-yang,CHEN Hui,MA Wen-jing,

中国图象图形学报 , 2007,
Abstract: In practical applications,many video sequences have moving background,and then the extraction of video object becomes complicated.An algorithm is proposed in the paper to extract video object from dynamic scene based on motion estimation and the graph pyramid.Phase correlation is first used to obtain the motion vector with high efficiency and robustness,and to weaken the impacts of illumination in the video sequence.Then global motion estimation with parameter-model is used to find the final motion template.Finally,to extract the semantic video object,spatial segmentation using the graph pyramid is applied to the image region in the current motion template.Compared with some prevailing methods,in the case of extraction of moving object from video sequences of dynamic scene,our algorithm avoids precise background compensation and is very computationally efficient,while the extracted semantic object is of high precision.The experimental results show that both rigid and non-rigid moving objects in dynamic scene are well extracted by this algorithm.
An Optimized Dynamic Scene Change Detection Algorithm for H.264/AVC Encoded Video Sequences  [PDF]
Giorgio Rascioni,Susanna Spinsante,Ennio Gambi
International Journal of Digital Multimedia Broadcasting , 2010, DOI: 10.1155/2010/864123
Abstract: Scene change detection plays an important role in a number of video applications, including video indexing, semantic features extraction, and, in general, pre- and post-processing operations. This paper deals with the design and performance evaluation of a dynamic scene change detector optimized for H.264/AVC encoded video sequences. The detector is based on a dynamic threshold that adaptively tracks different features of the video sequence, to increase the whole scheme accuracy in correctly locating true scene changes. The solution has been tested on suitable video sequences resembling real-world videos thanks to a number of different motion features, and has provided good performance without requiring an increase in decoder complexity. This is a valuable issue, considering the possible application of the proposed algorithm in post-processing operations, such as error concealment for video decoding in typical error prone video transmission environments, such as wireless networks. 1. Introduction Scene change detection is an issue easy to solve for humans, but it becomes really complicated when it has to be performed automatically by a device, which usually requires complex algorithms and computations, involving a huge amount of operations. The process of scene change detection becomes more and more complex when other constraints and specific limitations, due to the peculiar environment of application, may be present. A scene in a movie, and, in general, in a video sequence, can be defined as a succession of individual shots semantically related, where a shot is intended as an uninterrupted segment of the video sequence, with static frames or continuous camera motion. In the field of video processing, scene change detection can be applied either in preprocessing and postprocessing operations, according to the purposes that the detection phase has to achieve, and with different features and performance. As an example, in H.264/AVC video coding applications, scene change detection can be used in preprocessing as a decisional algorithm, in order to force Intraframe encoding (I) instead of temporal prediction (P), when a scene change occurs, and to confirm predicted or bi-predicted (B) coding for the remaining frames. As discussed in [1], a dynamic threshold model for real time scene change detection among consecutive frames may serve as a criterion for the selection of the compression method, as well as for the temporal prediction; it may also help to optimize rate control mechanisms at the encoder. In lossy video transmission environments, the effects of
Multiple Characters Motion Fusion with Virtual Scene

LUO Zhong-Xiang,ZHUANG Yue-Ting,PAN Yun-He,LI Yue-Mei,

软件学报 , 2003,
Abstract: In the computer animation based on motion capture, most of the available approaches to edit motion only deal with single character motion, which are mostly planned beforehand. Thus, characters lack the capability of responding to the environments. To improve the characters?ability to sense and respond to the environment, collaborate with each other, a new concept of motion fusion, which fuses multiple single-character motions captured in the structured environment into one unstructured virtual one, is presented in this paper. Based on the architecture of multi-character motion fusion with virtual scene which covers motion decision, motion collaboration, motion solving and motion execution, the key issues such as motion capture, planning, collaboration and generation of continuous movement and discrete movement are discussed in detail in this paper. The experimental results demonstrate that the presented method can efficiently fuse the motion of characters with virtual scenes. The independent collaboration of animated characters and high reuse enable the application of the presented idea into computer animation and game.
Stereoscopic Video Object Extraction Based on Disparity and Threshold

AN Ping,LIU Su-xin,GAO Xin,ZHANG Zhao-yang,

中国图象图形学报 , 2006,
Abstract: Object segmentation and extraction are vital tasks in many issues of content-based video processing. A video object segmentation algorithm is proposed in this paper based on disparity analysis and threshold segmentation for stereoscopic sequences including overlapped multi-objects with global motion. An improved area-based method is firstly adopted for disparity estimation by accelerating the matching processing. Then, to segment different objects in the scene, iterative threshold segmentation and self-adaptive threshold segmentation are respectively performed on the images, and the objects are extracted at last. Experimental results show that the proposed algorithm is an effective object extraction method suitable for stereoscopic sequences with unitary global motion.
An Efficient Method for Video Scene Detection

CHENG Wen-gang,XU De,LANG Cong-yan,

中国图象图形学报 , 2004,
Abstract: It is important to organize the unstructured video data properly for content video analysis and application. However, existing shot-based video analysis can not get good performance for effective browsing and retrieval because shots are too numerous to handle and can not convey meaningful semantics, so it is necessary to organize video content with the scene structure, which is a more meaningful and high-level semantic video unit. In this paper, a simple and efficient method is presented for video scene detection. As the buildup of video scene should obey the film grammar, it concludes the types of the scenes that are widely used in filmmaking firstly. The rules to generating the video scene are put out then. Based on the rules, a scheme for video scene detection is proposed: The video stream is segmented into shots through shot boundary detection; Key frame extraction is performed based on the content variation of shots; A new clustering method based on the sliding shot window is used to group the shots into shot clusters; A correlation function between shot clusters is defined to analysis the correlations of them and to construct the final video scene structure. Experimental results verify it is an efficient method.
A Framework Based on Multi-models and Multi-features for Sports Video Semantic Analysis  [PDF]
Jiaqi Fu,Hongping Hu,Richao Chen,Heng Ren
Information Technology Journal , 2012,
Abstract: The proliferation of video posed a challenging problem for the automatic analysis, interpretation and indexing of video data. Among them, sports video analysis has attracted the most attention because of the appeal of sports to large audience. This study presented an effective sports video semantic analysis algorithm based on the fusion and interaction of multi-models and multi-features. By utilizing the semantic color ratio, the video shot was classified into global shot, in-field shot and out-of-field shot which facilitated the HMM-based classification. For shot corresponding to a specific scene, by introducing image registration, the artifacts of noise and camera movement were reduced and accurate local motion features were obtained. Then, Hidden Markov Models (HMMs) were exploited to associate every video shot with a particular semantic class. Experimental results on Football and Tennis sequence showed that the proposed approach can achieve a relatively high ratio of correct semantic recognition.
Flexible Human Behavior Analysis Framework for Video Surveillance Applications  [PDF]
Weilun Lao,Jungong Han,Peter H. N. de With
International Journal of Digital Multimedia Broadcasting , 2010, DOI: 10.1155/2010/920121
Abstract: We study a flexible framework for semantic analysis of human motion from surveillance video. Successful trajectory estimation and human-body modeling facilitate the semantic analysis of human activities in video sequences. Although human motion is widely investigated, we have extended such research in three aspects. By adding a second camera, not only more reliable behavior analysis is possible, but it also enables to map the ongoing scene events onto a 3D setting to facilitate further semantic analysis. The second contribution is the introduction of a 3D reconstruction scheme for scene understanding. Thirdly, we perform a fast scheme to detect different body parts and generate a fitting skeleton model, without using the explicit assumption of upright body posture. The extension of multiple-view fusion improves the event-based semantic analysis by 15%–30%. Our proposed framework proves its effectiveness as it achieves a near real-time performance (13–15 frames/second and 6–8 frames/second) for monocular and two-view video sequences. 1. Introduction Visual surveillance for human-behavior analysis has been investigated worldwide as an active research topic [1]. In order to have automatic surveillance accepted by a large community, it requires a sufficiently high accuracy and the computation complexity should enable a real-time performance. In the video-based surveillance application, even if the motion of persons is known, this is not sufficient to describe the posture of the person. The postures of the persons can provide important clues for understanding their activities. Therefore, accurate detection and recognition of various human postures both contribute to the scene understanding. The accuracy of the system is hampered by the use of a single camera, in case of complex situations and several people undertaking actions in the same scene. Often, the posture of people is occluded, so that the behavior cannot be realized in high accuracy. In this paper, we contribute to improve the analysis accuracy by exploiting the use of second camera and mapping the event into a 3D scene model, that enables analysis of the behavior in the 3D domain. Let us now discuss related work from the literature. 1.1. Related Work Most surveillance systems have focused on understanding the events through the study of trajectories and positions of persons using a priori knowledge about the scene. The Pfinder [2] system was developed to describe a moving person in an indoor environment. It tracks a single nonoccluded person in complex scenes. The VSAM [3] system can monitor
Motion trails from time-lapse video  [PDF]
Camille Goudeseune
Computer Science , 2015,
Abstract: From an image sequence captured by a stationary camera, background subtraction can detect moving foreground objects in the scene. Distinguishing foreground from background is further improved by various heuristics. Then each object's motion can be emphasized by duplicating its positions as a motion trail. These trails clarify the objects' spatial relationships. Also, adding motion trails to a video before previewing it at high speed reduces the risk of overlooking transient events.
Composition and Comparison of Sports Video with Dynamic Scene

PAN Xue-feng,WU Si,LI Jin-tao,ZHANG Yong-dong,LIU Jin-gang,

计算机应用研究 , 2006,
Abstract: An automatic composition algorithm for sports video in same scene is proposed. First, the information of the foreground areas in current frame is obtained with global motion estimation and image registration between current frame and temporally adjacent frames, Then ,the spatial relationship between the two pre-composition frames is obtained by using global motion estimation method. Finally, the composition frame is constructed based on the information of the foreground areas of both pre-composition frames. Experiments demonstrate that proposed method is robust to the dynamic scene and able to compose the sports video keeping both of the foreground areas of pre-composition frames clear.
Page 1 /100
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.