Dynamic cues have until recently been usually considered as a simple extension of the static saliency, usually in the form of optic flow between two frames. The evolution of stimuli over a period longer than two frames has been largely ignored in saliency research. We argue that considering temporal evolution of trajectory even for a relatively short period can significantly extend the kind of ...

The purpose of this study was to examine whether the social interaction can affect vection strength. We compared the strength of self-motion perception (vection) with and without an audience (two people in addition to the participant) present during stimulus presentation. We presented the optical flow (dots’ expansion) for 40 seconds and obtained vection duration and latency and we also obtaine...

We design a compact but effective CNN model for optical flow by exploiting the well-known design principles: pyramid, warping, and cost volume. Cast in a learnable feature pyramid, our network uses the current optical flow estimate to warp the CNN features of the second image. It then uses the warped features and features of the first image to construct the cost volume, which is processed by a ...

Motion information is an important cue for human to perceive video content. However, it is hard to use motion in video retrieval due to the lack of effective representation. In this paper, we propose a perceived motion based shot content representation, perceived motion energy spectrum (PMES), for content-based video retrieval. The human perceivable motion regions or objects can be detected dir...

analysis is the task of finding the root cause of a failure situation in an industrial process. In this paper a new approach for performing alarm analysis using mul-tilevel flow models (MFM) is introduced. This approach is compared with existing methods for alarm analysis using MFM. The result of the alarm analysis presented in this paper is a set of explanations that fits the observed state of...

The image formation process involves both geometric and photometric aspects. The definition of optical flow is descriptive and the conformity of optical flow to motion flow is closely related to the algorithm, or the assumption that one takes for optical flow computation. This paper presents an algorithm for optical flow computation based on the massconserving assumption by first showing that t...

The image formation process involves both geometric and photometric aspects. The definition of optical flow is descriptive and the conformity of optical flow to motion flow is closely related to the algorithm, or the assumption that one takes for optical flow computation. This paper presents an algorithm for optical flow computation based on the mass-conserving assumption by first showing that ...

Object tracking and detection is first step in applications such as video surveillance. The main aim of object tracking has been developed to estimate location, velocity and distance parameters of moving objects with the help of static camera. Object tracking system require accurate segmentation of objects from the background for effective tracking. Motion segmentation or optical flow can be us...