A HMM-Based Method for Recognizing Dynamic Video Contents from Trajectories

Abstract

This paper describes an original method for classifying object motion trajectories in video sequences in order to recognize dynamic events. Similarities between trajectories are expressed from Hidden Markov Models representing each trajectory. We have favorably compared our method to several other ones, including histogram comparison, Longest Common Subsequence distance and SVM classification. Trajectory features are computed from the curvature and velocity values at each point of the trajectory, so that they are invariant to translation, rotation and scale. We have evaluated our method on two sets of data, a first one composed of typical classes of synthetic trajectories (such as parabola or clothoid), and a second one formed with trajectories obtained by tracking cars in a Formula1 race video.

Activity-based temporal segmentation for videos of interacting objects using invariant trajectory features

“…It can be shown [7] thatγ t,k is invariant to translation, rotation and scale in the frame. The considered feature vector used to characterize a given activity of a video object V O k is the vector containing the successive values ofγ t,k :…”

“…Relying on the works of Hervieu et al [7,8] we reliably compute the local differential trajectory features (i.e.,u t,k ,v t,k , u t,k andv t,k , u and v being defined below) from a continuous representation of a curve approximating the trajectory T k defined by {(u t,k , v t,k )} t∈[1;n k ] with:…”

“…Each of these features is modeled, in a first layer, using a HMM-based approach proposed in [7,8]. In a second stage, these HMM-based modelings will be used in a hierarchical way to model activities using SMCs (see Fig.…”

“…Tackling with the first layer modeling of the features (i.e.,γ i andd), the HMM modeling proposed in [7] has been used to build a probabilistic modeling of the spatio-temporal behavior of the V k and D feature vectors.…”

“…Günsel et al [6] developed an objectbased indexing of video filmed by a single camera, dealing with the motion and shape properties of the viewed objects and considering the camera motion and the object trajectories and interactions. A work by Hervieu et al [7,8] proposed a HMM-based shot classification method and rare event detection using the mobile object trajectories that may be used after a shot segmentation and a tracking processing. However, it did not account for interactions between objects.…”