Abstract
In this paper, we describe a robust method for compensating the panning and tilting motion of a camera, applied to foreground–background segmentation. First, the necessary internal camera parameters are determined through feature-point extraction and tracking. From these parameters, two motion models for points in the image plane are established. The first model assumes a fixed tilt angle, whereas the second model allows simultaneous pan and tilt. At runtime, these models are used to compensate for the motion of the camera in the background model. We will show that these methods provide a robust compensation mechanism and improve the foreground masks of an otherwise state-of-the-art unsupervised foreground–background segmentation method. The resulting algorithm is always able to obtain scores above on every daytime video in our test set when a minimal number of only eight feature matches are used to determine the background compensation, whereas the standard approaches need significantly more feature matches to produce similar results.
Highlights
Pan-tilt-zoom (PTZ) cameras provide maximum coverage of a scene with a single camera.They expand the level of flexibility, since the operator can select the desired camera viewpoint at runtime, which is not possible with standard fixed-camera solutions
PTZ cameras are applied in numerous applications, such as the detection of people in prohibited areas or in the counting of vehicles
As mentioned earlier, we found that the fixed parameter estimation framework could optimally be initiated with tracks consisting of a total number of nmin = 200 feature points in our experiments
Summary
Pan-tilt-zoom (PTZ) cameras provide maximum coverage of a scene with a single camera.They expand the level of flexibility, since the operator can select the desired camera viewpoint at runtime, which is not possible with standard fixed-camera solutions. Pan-tilt-zoom (PTZ) cameras provide maximum coverage of a scene with a single camera. PTZ cameras are applied in numerous applications, such as the detection of people in prohibited areas or in the counting of vehicles. To further automate these applications, the interesting objects (foreground) first need to be separated from less interesting ones (background). Spherical coordinates with respect to the camera center will simplify the mathematical expressions for a rotating (panning) camera .
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
