Explore the vast range of titles available.

In rehabilitation settings that exploit Mixed Reality, a clinician risks losing empathy with the patient by being immersed in different worlds, either real and/or virtual. While the patient perceives the rehabilitation stimuli in a mixed real–virtual world, the physician is only immersed in the real part. While in rehabilitation, this may cause the impossibility for the clinician to intervene, in skill assessment, this may cause difficulty in evaluation. To overcome the above limitation, we propose an innovative Augmented Reality (AR) framework for rehabilitation and skill assessment in clinical settings. Data acquired by a distributed sensor network are used to feed a “shared AR” environment so that both therapists and end-users can effectively operate/perceive it, taking into account the specific interface requirements for each user category: (1) for patients, simplicity, immersiveness, engagement and focus on the task; (2) for clinicians/therapists, contextualization and natural interaction with the whole set of data that is linked with the users’ performances in real-time. This framework has a strong potential in Occupational Therapy (OT) but also in physical, psychological, and neurological rehabilitation. Hybrid real and virtual environments may be quickly developed and personalized to match end users’ abilities and emotional and physiological states and evaluate nearly all relevant performances, thus augmenting the clinical eye of the therapist and the clinician-patient empathy. In this paper, we describe a practical exploitation of the proposed framework in OT: setting-up the table for eating. Both a therapist and a user wear Microsoft HoloLens 2. First, the therapist sets up the table with virtual furniture. Next, the user places the corresponding real objects (also in shape) to match them as closely as possible to the corresponding virtual ones. The therapist’s view is augmented during the test with motion, balance, and physiological estimated cues. Once the training is completed, he automatically perceives deviations in the position and attitude of each object and the elapsed time. We used a camera-based localization algorithm achieving a level of accuracy of 5 mm with a confidence level of 95% for position and 1° for rotation. The framework was designed and tested in collaboration with clinical experts of Villa Rosa rehabilitation hospital in Pergine (Italy), involving both a set of patients and healthy users to demonstrate the effectiveness of the designed architecture and the significance of the analyzed parameters between healthy users and patients.

Accurate localization is essential for Automated Guided Vehicles (AGVs) to ensure reliable motion planning and precise execution of docking tasks. A key challenge lies in robust environmental perception for industrial applications. This paper introduces a novel reflection-based marker detection and identification method that relies solely on two-dimensional Light Detection and Ranging (2D LiDAR) technology. The proposed docking method and 2D marker design enable the AGV to accurately estimate the marker’s distance and orientation, reliably identify it, and determine the docking point. Experimental validation on a heavy industrial AGV demonstrated that the docking method achieves accuracy of up to 1 cm in position and below 0.05 degree in YAW orientation. As a result, the AGV achieved docking precision at an assembly station with a standard deviation below 2 cm in X and Y axes and YAW orientation below 1.8 degree.

This research aims to test the performance of you only look once (YOLOv8) in identifying fish species in Indonesian waters. Fish image data is obtained from various sources to conduct testing. The results show that YOLOv8 is able to identify fish species with a mAP accuracy rate of 97%. These results reveal the great potential of deep learning technology in supporting the preservation of marine biodiversity as well as the development of various applications, such as fisheries monitoring, conservation, and marine-based tourism development in Indonesia. With its efficient object detection and classification capabilities, YOLOv8 can simplify and accelerate the process of identifying fish species, even on a large scale. Thus, this technology is a highly effective solution to overcome the challenges of manual fish species identification, which requires a lot of time and effort. The results of this study provide valuable insights into the potential utilization of Indonesia's natural resources in the context of scientific development, the tourism industry, and the fisheries sector, which is vital to the country's economy.

Optical tracking of unknown space objects requires both spatial accuracy and temporal stability to enable high-resolution identification through narrow field-of-view sensors. Traditional performance indices such as RMS error and persistence time (PT) have been used for controller tuning, but they each capture only a subset of the requirements for successful optical identification. This paper proposes a new composite metric, the Persistence-Weighted Tracking Index (PWTI), which combines spatial precision and segment-level continuity into a single measure. The metric assigns a frame-level score based on positional error and accumulates weighted scores over the longest continuous in-threshold segment. Using PWTI as the optimization objective, a genetic algorithm (GA) is employed to tune the PID gains of a frame-by-frame offset correction controller. Comparative simulations under various observation scenarios demonstrate that the PWTI-based approach outperforms RMS- and PT-based tuning methods in both alignment accuracy and consistency. The results validate the proposed metric as a more suitable performance indicator for optical identification tasks involving unknown or uncataloged targets.

Abstract The three-dimensional normalized full gradient (3DNFG) method was developed to identify multiple objects in complex geology. Two synthetic models- one with a single object and the other with multiple objects- were designed to evaluate the performance of 3DNFG. Through the analysis and study of these synthetic models, it was found that the planar position of targets can be easily determined using the 3DNFG response, regardless of whether the model is simple or complex. To accurately estimate the depth of targets, it is crucial to determine the optimal harmonic coefficient. For the simple model, commonly used methods such as the maxima method are feasible. For the multiple-object model, the local optimal harmonic coefficient induced by each target should be identified separately, after which the depth of each target can be determined using the corresponding harmonic coefficient. The 3DNFG methos was then applied to process gravity data collected from the Dachang area in Guangxi. The analysis revealed that the upper interface of the concealed granite at Longxianggai is approximately H = -530 m. Furthermore, the 3DNFG response indicates that the granite intrusion is shallow in several areas, including Longxianggai, Ruomacun, Dafulou, Yangjiaojian, and Tongkeng. These findings are in close agreement with the results obtained from inversion using the controlled random search method. Both synthetic models and the case study demonstrate that the 3DNFG performs well in identifying multiple objects in complex geological environments.

In the current study, we asked whether delays in the earliest stages of picture naming elicit disfluency. To address this question, we used a network task, where participants describe the route taken by a marker through visually presented networks of objects. Additionally, given that disfluencies are arguably multifactorial, we combined this task with eye tracking, to be able to disentangle disfluency related to word preparation from other factors (e.g., stalling strategy). We used visual blurring, which hinders visual identification of the items and thereby slows down selection of a lexical concept. We tested the effect of this manipulation on disfluency production and visual attention. Blurriness did not lead to more disfluency on average and viewing times decreased with blurred pictures. However, multivariate pattern analyses revealed that a classifier could predict above chance, from the pattern of disfluency, whether each participant was about to name blurred or control pictures. Impeding the conceptual generation of a message therefore affected the pattern of disfluencies of each participant individually, but this pattern was not consistent from one participant to another. Additionally, some of the disfluency and eye-movement variables correlated with individual cognitive differences, in particular with inhibition.

Statistical shape models are widely used in biomedical research. They are routinely implemented for automatic image segmentation or object identification in medical images. In these fields, however, the acquisition of the large training datasets, required to develop these models, is usually a time-consuming process. Even after this effort, the collections of datasets are often lost or mishandled resulting in replication of work. To solve these problems, the Virtual Skeleton Database (VSD) is proposed as a centralized storage system where the data necessary to build statistical shape models can be stored and shared. The VSD provides an online repository system tailored to the needs of the medical research community. The processing of the most common image file types, a statistical shape model framework, and an ontology-based search provide the generic tools to store, exchange, and retrieve digital medical datasets. The hosted data are accessible to the community, and collaborative research catalyzes their productivity. To illustrate the need for an online repository for medical research, three exemplary projects of the VSD are presented: (1) an international collaboration to achieve improvement in cochlear surgery and implant optimization, (2) a population-based analysis of femoral fracture risk between genders, and (3) an online application developed for the evaluation and comparison of the segmentation of brain tumors. The VSD is a novel system for scientific collaboration for the medical image community with a data-centric concept and semantically driven search option for anatomical structures. The repository has been proven to be a useful tool for collaborative model building, as a resource for biomechanical population studies, or to enhance segmentation algorithms.

Autonomous outdoor moving objects like cars, motorcycles, bicycles, and pedestrians present different risks to the safety of Visually Impaired People (VIPs). Consequently, many camera-based VIP mobility assistive solutions have resulted. However, they fail to guarantee VIP safety in practice, i.e., they cannot effectively prevent collisions with more dangerous threats moving at higher speeds, namely, Critical Moving Objects (CMOs). This paper presents the first practical camera-based VIP mobility assistant scheme, ARAware, that effectively identifies CMOs in real-time to give the VIP more time to avoid danger through simultaneously addressing CMO identification, CMO risk level evaluation and classification, and prioritised CMO warning notification. Experimental results based on our real-world prototype demonstrate that ARAware accurately identifies CMOs (with 97.26% mAR and 88.20% mAP) in real-time (with a 32 fps processing speed for 30 fps incoming video). It precisely classifies CMOs according to their risk levels (with 100% mAR and 91.69% mAP), and warns in a timely manner about high-risk CMOs while effectively reducing false alarms by postponing the warning of low-risk CMOs. Compared to the closest state-of-the-art approach, DEEP-SEE, ARAware achieves significantly higher CMO identification accuracy (by 42.62% in mAR and 10.88% in mAP), with a 93% faster end-to-end processing speed.

It is well known that visual search for a mirror target (i.e., a horizontally flipped item) is more difficult than search for other-oriented items (e.g., vertically flipped items). Previous studies have typically attributed costs of mirror search to early, attention-guiding processes but could not rule out contributions from later processes. In the present study we used eye tracking to distinguish between early, attention-guiding processes and later target identification processes. The results of four experiments revealed a marked human weakness in identifying mirror targets: Observers appear to frequently fail to classify a mirror target as a target on first fixation and to continue with search even after having directly looked at the target. Awareness measures corroborated that the location of a mirror target could not be reported above chance level after it had been fixated once. This mirror blindness effect explained a large proportion (45–87%) of the overall costs of mirror search, suggesting that part of the difficulties with mirror search are rooted in later, object identification processes (not attentional guidance). Mirror blindness was significantly reduced but not completely eliminated when both the target and non-targets were held constant, which shows that perfect top-down knowledge can reduce mirror blindness, without completely eliminating it. The finding that non-target certainty reduced mirror blindness suggests that object identification is not solely achieved by comparing a selected item to a target template. These results demonstrate that templates that guide search toward targets are not identical to the templates used to conclusively identify those targets.