Jean-Pierre Le Cadre

Recovery of the trajectories of multiple moving objects in an image sequence with a PMHT approach

This paper is concerned with the tracking of multiple moving objects in an image sequence and the reconstruction of the entire trajectories of these objects all over the sequence. More specifically, we address the joint issue of trajectory estimation and measurement-to-trajectory associations, which is the key problem in that context due to the occurrence of object occlusions or crossings. An original and efficient scheme is proposed, that adapts the Probabilistic Multiple Hypothesis Tracking (PMHT) technique to the case of tracking of regions in video, for which geometry and motion models can be introduced. Moreover, reliable partial associations can be obtained as an initialization. Data association and trajectory estimation are conducted within a probabilistic framework. The latter relies on Kalman filtering, while the former is solved with an EM algorithm for which a suitable initial configuration can be defined. The proposed tracking method is validated by experiments carried out on real image sequences depicting complex situations.

Trajectory-based handball video understanding

This paper presents a content-based approach for understanding handball videos. Tracked players are characterized by their 2D trajectories in the court plane. The trajectories and their interactions are used to model visual semantics, i.e., the observed activity phases. To this end, hierarchical parallel semi-Markov models (HPaSMMs) are computed in order to take into account the temporal causalities of object motions. Players motions are characterized using velocity informations while their interactions are described by the distances between trajectories. We have evaluated our method on real video sequences, and have favorably compared with another method, i.e., hierarchical parallel hidden Markov models (HPaHMMs).

A hierarchical approach for planning a multisensor multizone search for a moving target

This paper deals with a well-known problem in the general area of search theory: optimize the search resources sharing so as to maximize the probability of detection of a (moving) target. However, the problem we consider here considerably differs from the classical one. First, there is a bilevel search planning and we have to consider jointly discrete and continuous optimization problems. To this perspective original methods are proposed within a common framework. Furthermore, this framework is sufficiently general and versatile so as to be easily and successfully extended to the difficult problem of the multizone multisensor search planning for a Markovian target.

Target motion analysis and track association with a network of proximity sensors

Target motion analysis and track association are the aims of this paper. It is assumed that the target trajectory is only partially observable by using temporal processing of a single sensor. Thus, original algorithms have been developed for fusing local estimates. Though suboptimal, such algorithms are feasible and close to optimality. Their performances have been theoretically investigated. Another problem is track-to-track association, the aim of which is to perform decision if the tracks estimated by two local subsystems are related to a single target or not and for which an original approach has been developed. This study is illustrated by a specific case study: the detection of a moving target by stationary electric sensors.

Spatio-temporal multi-mode information management for moving target detection

This paper deals with the resource management for the detection of a moving target. Based on a generalized linear formalism, an algebraic framework for spatio-temporal optimization of the search efforts is developed, which allows management of multi-modes resources under various rules: modalization, conditionality, parallelizing. This formalism is an extension of Koopman/Brown search model and requires a continuous or pseudo-continuous hypothesis about the detection resources. This formalism is sufficiently general to provide a convenient framework for a wide variety of sensor management problems, even if practical applications require additional work for rendering more precise the particular modelling of detection resource.

Distribution of continuous search effort for the detection of a target with optimal moving strategy

Analytical resolution of search theory problems, as formalized by B.O. Koopman, may be applied with some model extension to various resource management and data fusion issues. Such method is based on a probabilistic prior about the target. Even so, this approximation forbids any reactive behavior of the target. As a preliminary step towards reactive target study stands the problem of resource placement under a minimax game context. Nakai gave an elegant solution of the game placement of resources for the detection of a stationary target. In this paper, our interest focuses however on the minimax detection of a moving target. A new method is developed and confronted to Nakai’s work.