The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we present a robust and efficient approach to extract motion layers from a pair of images with large disparity motion. First, motion models are established as: 1) initial SIFT matches are obtained and grouped into a set of clusters using our developed topological clustering algorithm; 2) for each cluster with no less than three matches, an affine transformation is estimated with least-square...
In this paper, a novel model of pedestrian tracking by using object-based attention and human knowledge is presented. The selective units in the system are the objects and groupings which are space-driven as well as feature-driven. The factors of speed, motion direction and spatial location are used to cluster and form the groupings. Hierarchical selectivity of attention for objects in a grouping...
Video-based moving vehicle detection and tracking are important parts of modern intelligent transportation system (ITS). They can provide valuable information such as vehicle velocity and trajectory for ITS. However, vehicle tracking at urban intersection is more challenging than that at highway, due to the complicated scenarios, such as the variety of vehicle moving direction, inter-vehicle clustering...
This paper presented a video moving object segmentation and tracking system based on the active contour and the color classification models. First, the active contour model is applied to segment the target object in the initial frame. From the segmented object, the object and background regions are extracted. Then the object and the background regions are separately clustered according to color feature...
This paper proposes a hierarchical visual motion retrieval system on the web. To make it possible for the user to retrieve motion data interactively and visually on a computer screen from coarse level to fine level about motion similarity, the proposed system employs tree based visualization method for the hierarchical structure of motion data. The hierarchical structure of motion data is constructed...
An improved moving object segmentation approach which extracted motion field from H.264 compressed domain is proposed. Pre-treatments such as vector median filtering and forward block vector accumulation are used to obtain more obvious motion field. Then mix and hierarchical clustering algorithm based on improved k-means and EM is exploited to segment the moving on the macro-block level and on the...
In this paper, we propose a macro-observation scheme for unusual event detection in daily life, where motions in time-space domain are described by a global representation and individual activities do not have to be defined and modeled beforehand. The proposed representation records the time-space energy of motions of all moving objects in a scene without segmenting individual object parts or tracking...
The camera of traffic system takes numerous photos every day. It's critically important for judging kinds of car movements and intelligent transportation to pick up the outlines of automobiles and fix their positions. However, the popular car positioning algorithm is unable to reach the required fast speed in this field. In this paper we will provide readers with an algorithm to locate cars based...
In this paper, we propose a new learning method in human motion data analysis. We use Isomap algorithm to reduce high dimensionality of motion's features data. And Support Vector Machine (SVM) for clustering and handling new data. Then data driven decision trees based on multiple instance are automatically constructed to reflect the influence of each point during the comparison of motion similarity...
Anomaly detection in crowd scene is very important because of more concern with people safety in public place. This paper presents an approach to automatically detect abnormal behavior in crowd scene. For this purpose, instead of tracking every person, KLT corners are extracted as feature points to represent moving objects and tracked by optical flow technique to generate motion vectors, which are...
Based on the observation that motion of different pixels from the same target has very similar spatial-temporal properties in bus video surveillance images, a feature point's trajectory clustering method is proposed to estimate passenger flow in this paper. Firstly, the pyramid-based optical flow algorithm is utilized to tracking the feature point's movement in the images; then, their trajectories...
This paper proposes a new approach to describe traffic scene including vehicle collisions and vehicle anomalies at intersections by video processing and motion statistic techniques. The research mainly targets on extracting abnormal event characteristics at intersections and learning normal traffic flow by trajectory clustering techniques. Detecting and analyzing accident events are done by observing...
This paper presents a novel slice-based approach to detect pedestrians in still images. A pedestrian is divided into limited numbers of slice-based sub-regions through a spatio-temporal slice processing. First, sub-regions of interest are detected in different spatio-temporal slice images. Then, a clustering algorithm is proposed to combine these sub-regions into individual pedestrians based on their...
Detecting dominant motion flows in crowd scenes is one of the major problems in video surveillance. This is particularly difficult in unstructured crowd scenes, where the participants move randomly in various directions. This paper presents a novel method which utilizes SIFT features' flow vectors to calculate the dominant motion flows in both unstructured and structured crowd scenes. SIFT features...
We present a method for segmentation of articulated 3D shapes by incorporating the motion information obtained from time-varying models. We assume that the articulated shape is given in the form of a mesh sequence with fixed connectivity so that the inter-frame vertex correspondences, hence the vertex movements, are known a priori. We use different postures of an articulated shape in multiple frames...
In this paper we develop a novel approach called the compensated HS (CHS) optical flow estimation algorithm to improve the precision of the large displacement optical flow field. For the lack of the higher order term in the optical flow constraint equation, the traditional optical flow estimation based on the first-order gradient always produce the optical flow field with obvious error in the case...
In this work, we propose a method for tracking individuals in crowds. Our method is based on a trajectory-based clustering approach that groups trajectories of image features that belong to the same person. The key novelty of our method is to make use of a person's individuality, that is, the gait features and the temporal consistency of local appearance to track each individual in a crowd. Gait features...
This paper presents a novel approach to skim and describe 3D videos. 3D video is an imaging technology which consists in a stream of 3D models in motion captured by a synchronized set of video cameras. Each frame is composed of one or several 3D models, and therefore the acquisition of long sequences at video rate requires massive storage devices. In order to reduce the storage cost while keeping...
Much of recent action recognition research is based on space-time interest points extracted from video using a Bag of Words (BOW) representation. It mainly relies on the discriminative power of individual local space-time descriptors, whilst ignoring potentially valuable information about the global spatio-temporal distribution of interest points. In this paper, we propose a novel action recognition...
This paper proposes a novel approach for motion primitive segmentation from continuous full body human motion captured on monocular video. The proposed approach does not require a kinematic model of the person, nor any markers on the body. Instead, optical flow computed directly in the image plane is used to estimate the location of segment points. The approach is based on detecting tracking features...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.