This paper describes a new method for estimating optical flow that strikes a balance between the flexibility of local dense computations and the robustness and accuracy of global ...
Robust estimators, such as Least Median of Squared (LMedS) Residuals, M-estimators, the Least Trimmed Squares (LTS) etc., have been employed to estimate optical flow from image se...
The faithful detection of the motion and of the distance of the objects in the visual scene is a desirable feature of any artificial vision system designed to operate in unknown e...
We propose a principled framework to model persistent motion in dynamic scenes. In contrast to previous efforts on object tracking and optical flow estimation that focus on local...
—Moving object detection is very important for video surveillance. In this paper, we present a new real time motion detection algorithm that is based on the integration of accumu...