Optical Flow-Based Obstacle Detection for Mid-Air Collision Avoidance.

The sky may seem big enough for two flying vehicles to collide, but the facts show that mid-air collisions still occur occasionally and are a significant concern. Pilots learn manual tactics to avoid collisions, such as see-and-avoid, but these rules have limitations. Automated solutions have reduced collisions, but these technologies are not mandatory in all countries or airspaces, and they are expensive. These problems have prompted researchers to continue the search for low-cost solutions. One attractive solution is to use computer vision to detect obstacles in the air due to its reduced cost and weight. A well-trained deep learning solution is appealing because object detection is fast in most cases, but it relies entirely on the training data set. The algorithm chosen for this study is optical flow. The optical flow vectors can help us to separate the motion caused by camera motion from the motion caused by incoming objects without relying on training data. This paper describes the development of an optical flow-based airborne obstacle detection algorithm to avoid mid-air collisions. The approach uses the visual information from a monocular camera and detects the obstacles using morphological filters, optical flow, focus of expansion, and a data clustering algorithm. The proposal was evaluated using realistic vision data obtained with a self-developed simulator. The simulator provides different environments, trajectories, and altitudes of flying objects. The results showed that the optical flow-based algorithm detected all incoming obstacles along their trajectories in the experiments. The results showed an F-score greater than 75% and a good balance between precision and recall.

Vision-Based Flying Obstacle Detection for Avoiding Midair Collisions: A Systematic Review.

This paper presents a systematic review of articles on computer-vision-based flying obstacle detection with a focus on midair collision avoidance. Publications from the beginning until 2022 were searched in Scopus, IEEE, ACM, MDPI, and Web of Science databases. From the initial 647 publications obtained, 85 were finally selected and examined. The results show an increasing interest in this topic, especially in relation to object detection and tracking. Our study hypothesizes that the widespread access to commercial drones, the improvements in single-board computers, and their compatibility with computer vision libraries have contributed to the increase in the number of publications. The review also shows that the proposed algorithms are mainly tested using simulation software and flight simulators, and only 26 papers report testing with physical flying vehicles. This systematic review highlights other gaps to be addressed in future work. Several identified challenges are related to increasing the success rate of threat detection and testing solutions in complex scenarios.

Self-Regulation in Children with Neurodevelopmental Disorders "SR-MRehab: Un Colegio Emocionante": A Protocol Study.

Self-regulation refers to the ability to control and modulate behavior, and it can include both emotional and cognitive modulation. Children with neurodevelopmental disorders may show difficulties in self-regulation. The main objective of this study is to improve self-regulation skills in children between 6 and 11 years of age with neurodevelopmental disorders. Methodology: A randomized controlled trial will be conducted with the use of "SR-MRehab: Un colegio emocionante", based on a non-immersive virtual reality system where virtual objects can be managed by children in a natural way using their hands. Children will be recruited from several schools of Granada (Spain) and they will be randomly allocated to two groups. An assessment will be conducted before and after the intervention and 24 weeks after the end of the intervention process. The experimental group will receive the intervention using virtual reality. The control group will receive a standard self-regulation program. Both interventions will be performed once a week for a total of 10 sessions. Changes in self-regulation, as well as the acceptability of technology with the use of SR-MRehab, will be evaluated. The results will be published and will provide evidence regarding the use of this type of intervention in children with neurodevelopmental disorders. Trial registration: Registered with code NCT04418921.

Ambient Intelligence Environment for Home Cognitive Telerehabilitation.

Higher life expectancy is increasing the number of age-related cognitive impairment cases. It is also relevant, as some authors claim, that physical exercise may be considered as an adjunctive therapy to improve cognition and memory after strokes. Thus, the integration of physical and cognitive therapies could offer potential benefits. In addition, in general these therapies are usually considered boring, so it is important to include some features that improve the motivation of patients. As a result, computer-assisted cognitive rehabilitation systems and serious games for health are more and more present. In order to achieve a continuous, efficient and sustainable rehabilitation of patients, they will have to be carried out as part of the rehabilitation in their own home. However, current home systems lack the therapist's presence, and this leads to two major challenges for such systems. First, they need sensors and actuators that compensate for the absence of the therapist's eyes and hands. Second, the system needs to capture and apply the therapist's expertise. With this aim, and based on our previous proposals, we propose an ambient intelligence environment for cognitive rehabilitation at home, combining physical and cognitive activities, by implementing a Fuzzy Inference System (FIS) that gathers, as far as possible, the knowledge of a rehabilitation expert. Moreover, smart sensors and actuators will attempt to make up for the absence of the therapist. Furthermore, the proposed system will feature a remote monitoring tool, so that the therapist can supervise the patients' exercises. Finally, an evaluation will be presented where experts in the rehabilitation field showed their satisfaction with the proposed system.

Identifying Virtual 3D Geometric Shapes with a Vibrotactile Glove.

The emergence of off-screen interaction devices is bringing the field of virtual reality to a broad range of applications where virtual objects can be manipulated without the use of traditional peripherals. However, to facilitate object interaction, other stimuli such as haptic feedback are necessary to improve the user experience. To enable the identification of virtual 3D objects without visual feedback, a haptic display based on a vibrotactile glove and multiple points of contact gives users an enhanced sensation of touching a virtual object with their hands. Experimental results demonstrate the capacity of this technology in practical applications.