Understanding human behaviors is a challenging problem in computer vision that has
recently seen important advances. Human behavior understanding combines image and …

In this paper, we present a novel method for the labeling of human motion which uses
Constraint-Based Genetic Algorithm (CBGA) to optimize the probabilistic model of body …

We propose a novel model for the spatio-temporal clustering of trajectories based on motion,
which applies to challenging street-view video sequences of pedestrians captured by a …

The last few years have seen considerable progress in pedestrian detection. Recent work
has established a combination of oriented gradients and optic flow as effective features …

A power packet is a unit of electric power composed of a power pulse and an information
tag. In Shannon's information theory, messages are represented by symbol sequences in a …

The present invention relates to video analysis and more speci? cally to the identi? cation of
moving features in a video. The motion of moving features in a video can be repre sented by …

This paper presents a system that estimates accurately the speed of individual pedestrians
with constant walking speed from monocular image sequences with people captured from …

US9014422B2 - Method of recognizing a moving feature in a video sequence - Google Patents
US9014422B2 - Method of recognizing a moving feature in a video sequence - Google Patents …

The problem of understanding motion in video has been an area of intense research in
computer vision for decades. The traditional approach is to represent motion using optical …

This paper is about detecting bipedal motion in video sequences by using point trajectories
in a framework of classification. Given a number of point trajectories, we find a subset of …