Background subtraction adapted to PTZ cameras by keypoint density estimation
نویسندگان
چکیده
PTZ cameras have the ability to cover wide areas with an adapted resolution. In this article we propose a background subtraction algorithm suitable for a PTZ camera performing a guard tour. It relies on the estimation of a probability density function based on the matching of keypoints between the background and the current image. Its main interest consists in the resulting robustness to sudden illumination changes. Experiments show that our algorithm is more robust to sudden changes in illumination than one of the state of the art approaches in situations of low camera frame-rate. These properties allow us to successfully maintain up to date the background model of a wide scene made up of a collection of images.
منابع مشابه
Cooperative Moving Object Segmentation using Two Cameras based on Background Subtraction and Image Registration
Moving camera, such as PTZ (pan-tilt-zoom) camera, has been widely applied in visual surveillance system. However, it’s difficult to extract moving objects because of the dynamic background caused by the camera motion. In this paper, a novel framework for moving object segmentation exploiting two cameras collaboration is presented by combining background subtraction and image registration metho...
متن کاملIntegration of Omnidirectional and Movable Cameras for Indoor Surveillance
In this paper, an omnidirectional camera and a movable PTZ (Pan, Tilt, Zoom) camera are utilized to the proposed indoor surveillance system. The traditional foreground-background extraction method and frame difference method are combined together in this paper; the combined method not only can ignore noises generated form background subtraction and focus on moving objects but also can eliminate...
متن کاملJoint Spatial and Tonal Mosaic Alignment for Motion Detection with PTZ Camera
Scene segmentation among background and foreground (moving) regions represents the first layer of many applications such as visual surveillance. Exploiting PTZ cameras permits to widen the field of view of a surveyed area and to achieve real object tracking through pan and tilt movements of the observer point of view. Having a mosaiced background allows a system to exploit the background subtra...
متن کاملStatistical Background Subtraction Based on the Exact Per-pixel Distributions
Most of background subtraction methods represent background statistics using probabilistic unified frameworks such as the Gaussian mixture model or kernel density estimation. But these models cannot define the exact difference between two pixels. It causes misclassification such as false alarms and misses. We presented a new sensor noise model appropriate for general CCD cameras. Based on this,...
متن کامل