No abstract

No abstract

Swimmer tracking has specic diculties compared to the other tracking systems due to some complex problems such as occlusion (by another person, a wall or splashing), variability of the target (in appearance, lighting or behavior). For the sake of conceiving a robust swimmer tracking system we started by developing mono-tracking systems based on some well-known pattern recognition techniques such as optical correlation (Non-linear JTC (Joint Transform Correlator)) and histogram based approaches (Color histogram, LBP (Local Binary Patterns) and HOG (Histogram of Oriented Gradients)). As an enhancement to these systems, we introduce the aspect of multi-tracking. Its basic idea is to track several potential targets which will give us several tracks then we choose the best track and relaunch the multi-tracking process. Forasmuch each technique has its own periods of good tracking and dropouts (loss of the object to be tracked), we propose a novel heterogeneous multi-tracking system by taking advantage of dierent tracking techniques. Each track represents an independent mono-tracking system. The use of the proposed heterogeneous multi-tracking system has improved signicantly the tracking results from 81.34% to 94%.

In order to accompany the swimming coaches in evaluating high-level swimmers, we developed a prototype for instantaneous speed estimation. To achieve this, we proposed and validated, in a previous work, a swimmer tracking system based on data fusion. However, the initialization phase is done manually, and our aim, in this paper, is to automate this process. First, we propose a region of interest localization module that allows the detection of the first appearance of the swimmer in the lane as well as the restriction of the region of interest around him. This module is based on the method a contrario which consists of modeling the random noise corresponding to the water and detecting the structured movement relative to the swimmer motion. To do that, we calibrate the pool using DLT (Direct Linear Transform) technique, extract the concerned lane, apply the frame difference approach to detect the moving objects, and then decompose the lane into blocs and classify them into swimmer motion or noise. Second, in order to detect the swimmer’s head, we propose the Scaled Composite JTC which is based on the NL-JTC correlation technique. The input plane of this latter includes a target and a reference image. The first is the region of interest detected by the method a contrario. The second consists of a Scaled Composite Reference. The tests conducted on real video sequences of French swimming championships (Limoges 2015) showed very good results in terms of region of interest localization and swimmer’s head detection which allows a reliable initialization for the tracking system.