• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.6
• /
• pp.582-592
• /
• 2001

Video indexing plays an important role in the applications such as digital video libraries or web VOD which archive large volume of digital videos. Video indexing is usually based on video segmentation. In this paper, we propose a software tool called V2Web Studio which can generate video clips utilizing shot boundary detection algorithm. With the V2Web Studio, the process of clip generation consists of the following four steps: 1) Automatic detection of shot boundaries by parsing the video, 2) Elimination of errors by manually verifying the results of the detection, 3) Building a modeling structure of logical hierarchy using the verified shots, and 4) Generating multiple video clips corresponding to each logically modeled segment. The aforementioned steps are performed by shot detector, shot verifier, video modeler and clip generator in the V2Web Studio respectively.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.12C
• /
• pp.1200-1208
• /
• 2003

Affective computing plays an important role in intelligent Human Computer Interactions(HCI). To detect emotional events, it is desirable to construct a computing model for extracting emotion related features from video. In this paper, we propose a statistical model based on the probabilistic distribution of low level features in video shots. The proposed method extracts low level features from video shots and then from a GMM(Gaussian Mixture Model) for them to detect emotional shots. As low level features, we use color, camera motion and sequence of shot lengths. The features can be modeled as a GMM by using EM(Expectation Maximization) algorithm and the relations between time and emotions are estimated by MLE(Maximum Likelihood Estimation). Finally, the two statistical models are combined together using Bayesian framework to detect emotional events in video.

• The KIPS Transactions:PartD
• /
• v.10D no.7
• /
• pp.1115-1126
• /
• 2003

In this paper, we propose modeling method for video data that represents structural and semantic contents of video data efficiently. Also, a browsing method that helps users easily understand and play the contents of video data is presented. The proposed modeling scheme consists of three layers such as raw data layer, content layer and key frame layer The content layer represents logical hierarchy and semantic contents of video data. We implement two kinds of browsers for playing video data and providing video contents. The playing browser plays video data and Presents the information of currently playing shot. The content browser allows users to browse raw data, structural information and semantic contents of video data.

• Journal of Computing Science and Engineering
• /
• v.2 no.1
• /
• pp.98-108
• /
• 2008

Terrain reconstruction from images is an ill-posed, yet commonly desired Structure from Motion task when compositing visual effects into live-action photography. These surfaces are required for choreography of a scene, casting physically accurate shadows of CG elements, and occlusions. We present a novel framework for generating the geometry of landscapes from extremely noisy point cloud datasets obtained via limited resolution techniques, particularly optical flow based vision algorithms applied to live-action video plates. Our contribution is a new statistical approach to remove erroneous tracks ('outliers') by employing a unique combination of well established techniques-including Gaussian Mixture Models (GMMs) for robust parameter estimation and Radial Basis Functions (REFs) for scattered data interpolation-to exploit the natural constraints of this problem. Our algorithm offsets the tremendously laborious task of modeling these landscapes by hand, automatically generating a visually consistent, camera position dependent, thin-shell surface mesh within seconds for a typical tracking shot.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.417-429
• /
• 2010

Though background subtraction has been widely studied for last decades, it is still a poorly solved problem especially when it meets real environments. In this paper, we first address some common problems for background subtraction that occur in real environments and then those problems are resolved by improving an existing GMM-based background modeling method. First, to achieve low computations, fixed point operations are used. Because background model usually does not require high precision of variables, we can reduce the computation time while maintaining its accuracy by adopting fixed point operations rather than floating point operations. Secondly, to avoid erroneous backgrounds that are induced by high pedestrian traffic, static levels of pixels are examined using shot-time statistics of pixel history. By using a lower learning rate for non-static pixels, we can preserve valid backgrounds even for busy scenes where foregrounds dominate. Finally, to adapt rapid illumination changes, we estimated the intensity change between two consecutive frames as a linear transform and compensated learned background models according to the estimated transform. By applying the fixed point operation to existing GMM-based method, it was able to reduce the computation time to about 30% of the original processing time. Also, experiments on a real video with high pedestrian traffic showed that our proposed method improves the previous background modeling methods by 20% in detection rate and 5~10% in false alarm rate.