In this paper we associate features obtained from ECG signals with the expected levels of stress of real firefighters in action when facing specific events such as fires or car accidents. Five firefighters were monitored using wearable technology collecting ECG signals. Heart rate and heart rate variability features were analyzed in consecutive 5-min intervals during several types of events. A questionnaire was used to rank these types of events according to stress and fatigue and a measure of association was applied to compare this ranking to the ECG features. Results indicate associations between this ranking and both heart rate and heart rate variability features extracted in the time domain. Finally, an example of differences in inter personal responses to stressful events is shown and discussed, motivating future challenges within this research field.

With the advent of autonomous vehicles, detection of the occupants' posture is crucial to tackle the needs of infotainment interaction or passive safety systems. Generative approaches have been recently proposed for human body pose in-car detection, but this type of approaches requires a large training dataset for a feasible accuracy. This requirement poses a difficulty, given the substantial time required to annotate such large amount of data. In the in-car scenario, this requirement risk increases even further, since a robust human body pose ground-truth system capable of working in it is needed but inexistent. Currently, the gold standard for human body pose capture is based on optical systems, requiring up to 39 visible markers for a plug-in gait model, which in this case are not feasible given the occlusions inside the car. Other solutions, such as inertial suits, also have limitations linked to magnetic sensitivity and global positioning drift. In this paper, a system for the generation of images for human body pose detection in an in-car environment is proposed. To this end, we propose to smartly combine inertial and optical systems to suppress their individual limitations: By combining the global positioning of 3 visible head markers provided by the optical system with the inertial suit's relative human body pose, we obtain an occlusion-ready, drift-free full-body global positioning system. This system is then spatially and temporally calibrated with a time-of-flight sensor, automatically obtaining in-car image data with (multi-person) pose annotations. Besides quantifying the inertial suit inherent sensitivity and accuracy, the feasibility of the overall system for human body pose capture in the in-car scenario was demonstrated. Our results quantify the errors associated with the inertial suit, pinpoint some sources of the system's uncertainty and propose how to minimize some of them. Finally, we demonstrate the feasibility of using system generated data (which was made publicly available), independently or mixed with two publicly available generic datasets (not in-car), to train 2 machine learning algorithms, demonstrating the improvement in their algorithmic accuracy for the in-car scenario.

Over the next years, the number of autonomous vehicles is expected to increase. This new paradigm will change the role of the driver inside the car, and so, for safety purposes, the continuous monitoring of the driver/passengers becomes essential. This monitoring can be achieved by detecting the human body pose inside the car to understand the driver/passenger's activity. In this paper, a method to accurately detect the human body pose on depth images acquired inside a car with a time-of-flight camera is proposed. The method consists in a deep learning strategy where the architecture of the convolutional neural network used is composed by three branches: the first branch is used to estimate the confidence maps for each joint position, the second one to associate different body parts, and the third branch to detect the presence of each joint in the image. The proposed framework was trained and tested in 8820 and 1650 depth images, respectively. The method showed to be accurate, achieving an average distance error between the detected joints and the ground truth of 7.6 pixels and an average accuracy, precision, and recall of 95.6%, 96.0%, and 97.8% respectively. Overall, these results demonstrate the robustness of the method and its potential for in-car body pose monitoring purposes.

In this paper, a toolchain for the generation of realistic synthetic images for human body pose detection in an in-car environment is proposed. The toolchain creates a customized synthetic environment, comprising human models, car, and camera. Poses are automatically generated for each human, taking into account a per-joint axis Gaussian distribution, constrained by anthropometric and range of motion measurements. Scene validation is done through collision detection. Rendering is focused on vision data, supporting time-of-flight (ToF) and RGB cameras, generating synthetic images from these sensors. Ground-truth data is then generated, comprising the car occupants' body pose (2D/3D), as well as full body RGB segmentation frames with different body parts' labels. We demonstrate the feasibility of using synthetic data, combined with real data, to train distinct machine learning agorithms, demonstrating the improvement in their algorithmic accuracy for the in-car scenario.