This paper presents a general framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature o...
详细信息
This paper presents a general framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature of object trajectories is used to build a topographical scene description where nodes are points of interest (POT) and the edges correspond to activity paths (AP). The POI are learned through as a mixture of Gaussians and AP by clustering trajectories. The paths are probabilistically represented by hidden Markov models and adapt to temporal variations using online maximum likelihood regression (MLLR) and through a periodic batch update. Using the scene graph, new trajectories can be analyzed in online fashion to categorize past and present activity, predict future behavior, and detect abnormalities.
This paper presents a new framework for a multi-stage multi-view approach for human interactions and activity analysis. The analysis is performed in a distributed vision system that synergistically integrate track- an...
详细信息
ISBN:
(纸本)9781424431366;9780769527932
This paper presents a new framework for a multi-stage multi-view approach for human interactions and activity analysis. The analysis is performed in a distributed vision system that synergistically integrate track- and body-level representations across multiple cameras. Our system aims at versatile and easily-deployable system that does not require careful camera calibration. Main contributions of the paper are: (1) context-dependent camera handover for occlusion handling, (2) switching the multi-stage analysis between track- and body-level representations, and (3) a hypothesis-verification paradigm for top-down feedback exploiting spatio-temporal constraints inherent in human interaction. Experimental evaluation shows the efficacy of the proposed system for analyzing multi-person interactions. Current implementation uses two views, but extension to more views is straightforward.
In recent years, large number of cameras have been installed in freeway and road environments. While the use of some of these cameras is being automated through computervision, few computervision systems allow for t...
详细信息
In recent years, large number of cameras have been installed in freeway and road environments. While the use of some of these cameras is being automated through computervision, few computervision systems allow for true wide-area large scaled automation. This paper describes a distributed computing system capable of managing an arbitrarily large sensor network using only common computing and networking platforms. The architecture is capable of handling many common computervision tasks, as well as the inter-sensor communication necessary for developing new algorithms which employ data from multiple sensors. This system is tested with an algorithm which tracks moving objects through a prototype camera network with non-overlapping fields or view in a college campus environment This algorithm allows the system to maintain the identity of a tracked objects as it leaves and enters the fields of view of individual sensors. Such an algorithm is necessary for applications which require tracking objects over large distances or over long periods of time in an environment without complete sensor coverage.
Motion information is extracted by identifying the temporal signature associated with the textured objects in the scene. In this paper, we present a new computational framework for motion perception. Our methodology c...
详细信息
Motion information is extracted by identifying the temporal signature associated with the textured objects in the scene. In this paper, we present a new computational framework for motion perception. Our methodology considers spatiotemporal frequency (STF) domain analysis to extract the optical flow information. First, we show that a sequence of image frames can be used to extract the motion parameters for the different regions in a dynamic scene using the basic Fourier transform properties in the STF analysis approach. When the observer (or the camera) moves, motion is induced in the scene, and the extracted motion information can then be used to estimate the depth parameters. A detailed analytical description of this model to interchangably extract motion and depth parameters and results to highlight their salient properties are presented.< >
This paper presents an new framework for homography-based analysis of pedestrian-vehicle activity in crowded scenes. Planar homography constraint is exploited to extract view-invariant object features including footag...
详细信息
This paper presents an new framework for homography-based analysis of pedestrian-vehicle activity in crowded scenes. Planar homography constraint is exploited to extract view-invariant object features including footage area and velocity of objects on the ground plane. Spatio-temporal relationships between people- and vehicle- tracks are represented by a semantic event. Context awareness of the situation is achieved by the estimated density distribution of objects and the anticipation of possible directions of near-future tracks using piecewise velocity history. Single-view and multi-view based homography mapping options are compared. Our framework can be used to enhance situational awareness for disaster prevention, human interactions in structured environments, and crowd movement analysis at wide regions
vision based systems for "smart" airbag systems aim to give precise information about occupant pose and location. This information can be used to make intelligent airbag deployment decisions. This paper revi...
详细信息
vision based systems for "smart" airbag systems aim to give precise information about occupant pose and location. This information can be used to make intelligent airbag deployment decisions. This paper reviews both a stereo-based and long wave infrared-based system for "smart" airbag deployment. The algorithms are systematically evaluated through extensive real-time occupant tests. Data for both algorithms is simultaneously collected and evaluated for viability in an intelligent airbag system. Results of these experimental trials show the feasibility of each video based occupant position analysis system. Advantages and drawbacks of each method are discussed and potential solutions are suggested.
This paper presents an adaptive framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature...
详细信息
ISBN:
(纸本)9781424421749
This paper presents an adaptive framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature of object trajectories are used to build a topographical map, where nodes are points of interest and the edges correspond to activities, to describe a scene. The graph is learned in an unsupervised manner but is flexible and able to adjust to changes in the environment or other scene variations.
This paper describes an approach for detecting objects in front of an automobile using wide field of view stereo with a pair of omni cameras. Several configurations are suggested for effective detection of vehicles an...
详细信息
This paper describes an approach for detecting objects in front of an automobile using wide field of view stereo with a pair of omni cameras. Several configurations are suggested for effective detection of vehicles and pedestrians. The omni cameras are calibrated using sets of parallel lines on a parking lot. The calibration is used to rectify the omni images. Stereo matching is performed on the rectified images to detect other vehicles and pedestrians. Experimental results show promise of detecting these objects on the road.
We present face recognition schemes based on video streams: the majority decision rule and HMM maximum likelihood (ML) decision rules. PCA type of subspace feature analysis is first applied to the face images in a vid...
详细信息
We present face recognition schemes based on video streams: the majority decision rule and HMM maximum likelihood (ML) decision rules. PCA type of subspace feature analysis is first applied to the face images in a video segment of a fixed number of frames. The majority decision rule is then applied to PCA recognition results in the video segment. Discrete HMM (DHMM) is also applied to the single-frame recognition sequences. Continuous density HMM (CDHMM) is applied directly to the sequence of PCA feature vectors for ML decision on the video segment in a delayed decision manner. Experimental results are compared between these three schemes in terms of the number of states and Gaussian mixtures of the HMMs. CDHMM-based decision rule achieved a 99% correct recognition rate in average. A geometric interpretation of ML in the feature subspace well explains the observed performances.
暂无评论