In the context in which severe visual impairment significantly affects human life, this article emphasizes the potential of Artificial Intelligence (AI) and Visible Light Communications (VLC) in developing future assistive technologies. Toward this path, the article summarizes the features of some commercial assistance solutions, and debates the characteristics of VLC and AI, emphasizing their compatibility with blind individuals\' needs. Additionally, this work highlights the AI potential in the efficient early detection of eye diseases. This article also reviews the existing work oriented toward VLC integration in blind persons\' assistive applications, showing the existing progress and emphasizing the high potential associated with VLC use. In the end, this work provides a roadmap toward the development of an integrated AI-based VLC assistance solution for visually impaired people, pointing out the high potential and some of the steps to follow. As far as we know, this is the first comprehensive work which focuses on the integration of AI and VLC technologies in visually impaired persons\' assistance domain.

Background and Objectives: Vision significantly contributes to postural control, balance, coordination, and body kinematics, thus deeply influencing everyday functionality. Sight-impaired subjects often show upper body anatomofunctional and kinetic chain alterations negatively impacting daily living efficiency and autonomy. The present study aimed to investigate and train, for the first time, upper body sensorimotor control in an Italian blind baseball team to boost global and segmental functionality while contemporarily prevent injuries. Materials and Methods: The whole team underwent a validated test battery using both quantitative traditional tools, such as goniometric active range of motion and muscular/functional tests, and an innovative biofeedback-based device, a Libra proprioceptive board. Consequently, a 6-week adapted training protocol was designed and leaded to improve sensorimotor control and, hence, counteract disability-related deficits and sport-specific overuse syndromes. Results: Statistically significant improvements were observed in all the investigated parameters. Noteworthy, an overall boost of global and segmental stability was detected through an orthostatic dynamic balance enhancement during the Y Balance test (p = 0.01) and trunk multiplanar control improvement on the Libra board (p = 0.01). Concurrently, the comparison of baseline vs. post-intervention outcomes revealed a consistent increase in upper body mobility (p < 0.05 for all the assessed districts), core recruitment (p = 0.01 for all the administered functional tests), and proprioceptive postural control (p = 0.01 for the Libra board validated test). Conclusions: Our findings suggest that a tailored sensorimotor training, conceived and led by an adapted physical activity kinesiologist, may effectively improve upper body functional prerequisites and global proprioceptive control, thus potentially promoting autonomy, quality of life, and physical activity/sport practice adherence in visually impaired individuals.

UNASSIGNED: To compare objective physical activity (PA) levels of children with visual impairment (VI) and children with normal sight.
UNASSIGNED: One hundred children with VI and 100 age- and gender-matched normal-sighted peers 7 to 17 years of age wore an ActiGraph for 1 week. Activity count per minute (cpm) was modeled using a series of generalized linear mixed-effects models including vision, age, sex, time of day, and vision by time of day interaction. PA outcomes included mean counts per minute and proportion of time spent on sedentary, light, moderate, and vigorous intensity PA.
UNASSIGNED: Data of 83 children with VI and 77 normal-sighted peers were included. Mean counts per minute were lower in children with VI (P < 0.001), especially during and after school. Children with VI were less sedentary (55%; 95% confidence interval [CI], 53-57) than children with normal sight before school (62%; 95% CI, 60-64) and over weekends: children with VI, 41% (95% CI, 39-43); children with normal sight, 45% (95% CI, 43-47). Yet, children with VI were more sedentary during school (36%; 95% CI, 34-37) compared with children with normal sight (30%; 95% CI, 29-32). They also spent more time performing light PA and less time performing moderate PA at school and vigorous PA across all periods of day (P < 0.001).
UNASSIGNED: Children with VI participated in light and moderate PA but did not perform as much vigorous PA as children with normal sight, especially during school hours.
UNASSIGNED: There is a need to promote more intense PA programs in schools tailored for children with VI.

暂无摘要。

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.

CONCLUSIONS: Autonomous vehicles (AVs) have the promise to be an alternative transportation solution for those with vision loss. However, the impact of vision loss on the perceptions and concerns of AVs is unknown. This study therefore examined whether AVs are perceived differently by blind, visually impaired (VI), and normally sighted people.
OBJECTIVE: This study compared the perceptions of AVs among the blind, VI, and normally sighted.
METHODS: Participants\' opinions on four perception measures (general opinion, trust, impact on quality of life, and intention to use AVs) and nine concerns regarding AVs were measured. The survey was administered to 51 normally sighted, 68 VI, and 65 blind participants. Analyses of covariance assessed whether the four perception measures and nine concerns varied by vision status (normal vision, VI, blind) and driving status (driver, nondriver). Univariate correlations and multiple regression analyses identified associations and predictors of AV perceptions and concerns from demographic, mood, cognition, travel behavior, and vision measures, which included visual acuity, contrast sensitivity, and visual field.
RESULTS: The blind (p<0.001), VI (p<0.001), and nondrivers (p<0.001) showed a greater intention to use AVs compared with those with normal vision and drivers. Similar findings were found for the other perception measures. As visual acuity, contrast sensitivity, and visual field extent declined, positivity toward AVs increased (p<0.001). Visual field extent best predicted general opinion and trust in AVs, whereas driving measures were the best predictors of impact on quality of life and intention to use AVs. Concerns about AVs showed no differences based on vision (p=0.94) or driving (p=0.63) status.
CONCLUSIONS: Individuals with vision loss expressed more acceptance of AVs despite their concerns. How positive someone is toward AVs appears to be dependent on their visual field extent and driving status.

CONCLUSIONS: This study has shown a vibrotactile sensory substitution device (SSD) prototype, VibroSight, has the potential to improve functional outcomes (i.e., obstacle avoidance, face detection) for people with profound vision loss, even with brief familiarization (<20 minutes).
OBJECTIVE: Mobility aids such as long canes are still the mainstay of support for most people with vision loss, but they do have limitations. Emerging technologies such as SSDs are gaining widespread interest in the low vision community. The aim of this project was to assess the efficacy of a prototype vibrotactile SSD for people with profound vision loss in the face detection and obstacle avoidance tasks.
METHODS: The VibroSight device was tested in a movement laboratory setting. The first task involved obstacle avoidance, in which participants were asked to walk through an obstacle course. The second was a face detection task, in which participants were asked to step toward the first face they detected. Exit interviews were also conducted to gather user experience data. Both people with low vision (n = 7) and orientation and mobility instructors (n = 4) completed the tasks.
RESULTS: In obstacle avoidance task, participants were able to use the device to detect (p<0.001) and avoid (p<0.001) the obstacles within a significantly larger range, but were slower (p<0.001), when compared with without the device. In face detection task, participants demonstrated a great level of accuracy, precision, and sensitivity when using the device. Interviews revealed a positive user experience, although participants identified that they would require a lighter and compact design for real-world use.
CONCLUSIONS: Overall, the results verified the functionality of vibrotactile SSD prototype. Further research is warranted to evaluate the user performance after an extended training program and to add new features, such as object recognition software algorithms, into the device.

CONCLUSIONS: Future work should develop and evaluate interventional strategies to help overcome visual and health-related barriers to travel in visually impaired seniors and mitigate adverse impacts of loneliness for those who do not leave town.
OBJECTIVE: Life space refers to the area in which a person travels within a given time period. We explored whether demographics, vision, and/or health characteristics were related to restrictions in self-reported life space for visually impaired seniors.
METHODS: Visually impaired (n = 114) clinical trial participants aged ≥55 years learned visual assistive iPhone apps and completed the following baseline questionnaires: Life Space, 36-Item Short-Form Health Survey, University of California, Los Angeles Loneliness Scale, and New-General Self-efficacy Scale. Multiple logistic regressions evaluated associations between life space and patient factors after accounting for their distance to the next county or state.
RESULTS: During 2021 to 2023, 17%, 43%, and 70% of participants had not left their town, county, or state, respectively, in the past 3 months, or planned to in the next 3 months. Those with reduced distance best-corrected visual acuity had greater odds of not leaving the county in these time frames (odds ratio [OR] = 3.5; p=0.04). Minority race was associated with greater odds of not leaving town or the county in the past 2 weeks or future 3 months (OR = 4.3 to 6.4; p=0.009 to 0.049). Increased self-efficacy was associated with reduced odds of not leaving the state in the past 3 months, next 3 months, or past and/or future 3 months (OR = 0.54 to 0.55; p=0.02 to 0.03). Better physical function was associated with reduced odds of not leaving the state in the past 2 weeks or 3 months (OR = 0.96 to 0.98; p=0.01 to 0.04). Increased loneliness was related to greater odds of not leaving town in the past and/or future 3 months (OR = 1.8 to 2.0; p=0.007 to 0.009).
CONCLUSIONS: Minority race, reduced vision, self-efficacy, and physical health were related to life space restrictions in this cohort of visually impaired seniors, whereas loneliness was greater among those who were not leaving town.

BACKGROUND: Uncorrected refractive error (URE) is a readily treatable cause of visual impairment (VI). This study provides updated estimates of global and regional vision loss due to URE, presenting temporal change for VISION 2020 METHODS: Data from population-based eye disease surveys from 1980-2018 were collected. Hierarchical models estimated prevalence (95% uncertainty intervals [UI]) of blindness (presenting visual acuity (VA) < 3/60) and moderate-to-severe vision impairment (MSVI; 3/60 ≤ presenting VA < 6/18) caused by URE, stratified by age, sex, region, and year. Near VI prevalence from uncorrected presbyopia was defined as presenting near VA < N6/N8 at 40 cm when best-corrected distance (VA ≥ 6/12).
RESULTS: In 2020, 3.7 million people (95%UI 3.10-4.29) were blind and 157 million (140-176) had MSVI due to URE, a 21.8% increase in blindness and 72.0% increase in MSVI since 2000. Age-standardised prevalence of URE blindness and MSVI decreased by 30.5% (30.7-30.3) and 2.4% (2.6-2.2) respectively during this time. In 2020, South Asia GBD super-region had the highest 50+ years age-standardised URE blindness (0.33% (0.26-0.40%)) and MSVI (10.3% (8.82-12.10%)) rates. The age-standardized ratio of women to men for URE blindness was 1.05:1.00 in 2020 and 1.03:1.00 in 2000. An estimated 419 million (295-562) people 50+ had near VI from uncorrected presbyopia, a +75.3% (74.6-76.0) increase from 2000 CONCLUSIONS: The number of cases of VI from URE substantively grew, even as age-standardised prevalence fell, since 2000, with a continued disproportionate burden by region and sex. Global population ageing will increase this burden, highlighting urgent need for novel approaches to refractive service delivery.

BACKGROUND: We aimed to update estimates of global vision loss due to age-related macular degeneration (AMD).
METHODS: We did a systematic review and meta-analysis of population-based surveys of eye diseases from January, 1980, to October, 2018. We fitted hierarchical models to estimate the prevalence of moderate and severe vision impairment (MSVI; presenting visual acuity from <6/18 to 3/60) and blindness ( < 3/60) caused by AMD, stratified by age, region, and year.
RESULTS: In 2020, 1.85 million (95%UI: 1.35 to 2.43 million) people were estimated to be blind due to AMD, and another 6.23 million (95%UI: 5.04 to 7.58) with MSVI globally. High-income countries had the highest number of individuals with AMD-related blindness (0.60 million people; 0.46 to 0.77). The crude prevalence of AMD-related blindness in 2020 (among those aged ≥ 50 years) was 0.10% (0.07 to 0.12) globally, and the region with the highest prevalence of AMD-related blindness was North Africa/Middle East (0.22%; 0.16 to 0.30). Age-standardized prevalence (using the GBD 2019 data) of AMD-related MSVI in people aged ≥ 50 years in 2020 was 0.34% (0.27 to 0.41) globally, and the region with the highest prevalence of AMD-related MSVI was also North Africa/Middle East (0.55%; 0.44 to 0.68). From 2000 to 2020, the estimated crude prevalence of AMD-related blindness decreased globally by 19.29%, while the prevalence of MSVI increased by 10.08%.
CONCLUSIONS: The estimated increase in the number of individuals with AMD-related blindness and MSVI globally urges the creation of novel treatment modalities and the expansion of rehabilitation services.