This article researches the problem of accurately tracking a target that is moving in an environment where there are a large number of disturbing factors, using multiple cameras for a larger observation field and better positioning accuracy than that of using a single camera. This paper proposes a method based on the common features learned through multidomain networks to reduce the interference of the external environment and thus more accurately and steadily track the target. The image model proposed by Multi-domain Network has significantly improved the fusion and utilization efficiency of multi-scale features. We also establish a consistent calibration of the same target between cameras by making full use of the overlapping visual field of multiple cameras and counting the number of similar pairs between the template and the target image search window to achieve target association and handover between cameras, making the cameras’ vision field expanded. By extracting the geometric constraint relationship between the cameras and combining the views of the target from multiple angles, the spatial positioning of the target object is finally achieved. Experiments show that the proposed tracking and positioning method can accurately track the moving target and can accurately position it.
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.