We describe a novel system called V-Sentinel (Virtual Sentinel) that offers a unique solution for situational awareness, assessment, and response support for security and military applications. Unlike traditional surveillance systems that display 2D videos or images on separate windows/screens, thereby providing no integration of information, no high-level scene comprehension, and no situational awareness, the V-Sentinel provides users a complete global view of entire surveillance scene including 3D geospatial models of the environment, aerial and terrestrial imagery, real-time videos, and dynamic sensor alarm/status designators - all on one screen, and from arbitrary viewpoints. This paper discusses the system design and integration of various capabilities to create a V-Sentinel system, and the results from our demonstrations and performance evaluations of the system to several government agencies and defense contractors for military and national security applications.
KEYWORDS: Detection and tracking algorithms, RGB color model, Systems modeling, Video, Cameras, 3D modeling, Video surveillance, Expectation maximization algorithms, Motion estimation, Data modeling
Robust and accurate tracking of multiple objects is a key challenge in video surveillance. Tracking algorithms generally suffer from either one or more of the following problems, excluding detection errors. First, objects can be incorrectly interpreted as one of the other objects in the scene. Second, interactions between objects, such as occlusions, may cause tracking errors. Third, globally-optimum tracking is hard to achieve since the combinatorial assignment problem is NP-Complete. We present a modified Multiple-Hypothesis Tracking algorithm, MHT, for globally optimum tracking of moving objects. The system defines five states for tracked objects: appear, disappear, track, split, and merge, and these states cover all the interactions of object pairs. After the detection of objects in the current frame, a resemblance matrix is computed for every object pair. We convert the two-dimensional resemblance matrix into a three-dimensional state-likelihood structure and use a MHT technique to solve the state-assignment problem in 3D. This prevents incorrect assignments due to local minima in the assignment process. Moreover, the method models occlusion cases with the split and merge states. Finally, this method approximates a globally optimum state assignment in polynomial time complexity.
In traditional vision-based Augmented Reality tracking system, artificially-designed fiducials have been used as camera tracking primitives. The 3D positions of these fiducials should be pre-calibrated, which imposes limitations in ranges of tracking view. Fortunately, the advance of computer vision technologies combined with new point position estimation technology enable natural features to be detected, and calibrated to be used as camera tracking primitives. This paper describes how these technologies are used to track in an unprepared environment for Augmented Reality.
This paper addresses the problem of robust 2D image motion estimation in natural environments. We develop an adaptive tracking-region selection and optical-flow estimation technique. The strategy of adaptive region selection locates reliable tracking regions and makes their motion estimation more reliable and computationally efficient. The multi-stage estimation procedure makes it possible to discriminate between good and poor estimation areas, which maximizes the quality of the final motion estimation. Furthermore, the model fitting stage further reduces the estimation error and provides a more compact and flexible motion field representation that is better suited for high-level vision processing. We demonstrate the performance of our techniques on both synthetic and natural image sequences.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.