Non-Invasive Forehead Segmentation in Thermographic Imaging.

The temperature of the forehead is known to be highly correlated with the internal body temperature. This area is widely used in thermal comfort systems, lie-detection systems, etc. However, there is a lack of tools to achieve the segmentation of the forehead using thermographic images and non-intrusive methods. In fact, this is usually segmented manually. This work proposes a simple and novel method to segment the forehead region and to extract the average temperature from this area solving this lack of non-user interaction tools. Our method is invariant to the position of the face, and other different morphologies even with the presence of external objects. The results provide an accuracy of 90% compared to the manual segmentation using the coefficient of Jaccard as a metric of similitude. Moreover, due to the simplicity of the proposed method, it can work with real-time constraints at 83 frames per second in embedded systems with low computational resources. Finally, a new dataset of thermal face images is presented, which includes some features which are difficult to find in other sets, such as glasses, beards, moustaches, breathing masks, and different neck rotations and flexions.

D2R-TED: Data-Domain Reduction Model for Threshold-Based Event Detection in Sensor Networks.

The reduction of sensor network traffic has become a scientific challenge. Different compression techniques are applied for this purpose, offering general solutions which try to minimize the loss of information. Here, a new proposal for traffic reduction by redefining the domains of the sensor data is presented. A configurable data reduction model is proposed focused on periodic duty⁻cycled sensor networks with events triggered by threshold. The loss of information produced by the model is analyzed in this paper in the context of event detection, an unusual approach leading to a set of specific metrics that enable the evaluation of the model in terms of traffic savings, precision, and recall. Different model configurations are tested with two experimental cases, whose input data are extracted from an extensive set of real data. In particular, two new versions of Send⁻on⁻Delta (SoD) and Predictive Sampling (PS) have been designed and implemented in the proposed data⁻domain reduction for threshold⁻based event detection (D2R-TED) model. The obtained results illustrate the potential usefulness of analyzing different model configurations to obtain a cost⁻benefit curve, in terms of traffic savings and quality of the response. Experiments show an average reduction of 76 % of network packages with an error of less than 1%. In addition, experiments show that the methods designed under the proposed D2R⁻TED model outperform the original event⁻triggered SoD and PS methods by 10 % and 16 % of the traffic savings, respectively. This model is useful to avoid network bottlenecks by applying the optimal configuration in each situation.