Search Results (38)

The ImpactAlert system is a chest-mounted system that detects objects that are likely to hit a pedestrian and alerts that pedestrian. The primary use cases are visually impaired pedestrians or pedestrians who need to be warned about vehicles or other pedestrians coming from unseen directions. This paper argues for the need for such a system, the design and algorithms of ImpactAlert, and experiments carried out in varied urban environments, ranging from densely crowded to semi-urban in the United States, India and China. ImpactAlert makes use of a LiDAR camera found on a commercial wireless phone, processes the data over several frames to evaluate the time to impact and speed of potential threats. When ImpactAlert determines a threat meets the criteria set by the user, it sends warning signals through an output device to warn a pedestrian. The output device can be an audible warning and/or a low-cost smart cane that vibrates when danger approaches. Our experiments in urban and semi-urban environments show that (i) ImpactAlert can avoid nearly all false negatives (when an alarm should be sent and it isn’t) and (ii) enjoys a low false positive rate. The net result is an effective low cost system to alert pedestrians in an urban environment. Full article

The movement of visually impaired people is still limited, and they often require assistance from others. In this study, along with the development of autonomous driving technology, a future mobility design that will help visually impaired people conveniently move around was proposed. The Double-Diamond model, a representative UX evaluation method, was revised and used for the evaluation. After discovering the mobility problems of the visually impaired, we developed the problem into an idea and designed future mobility based on the idea. Then, it was delivered to visually impaired people, and a utility test was performed on the new concept and functions. Six functions were proposed in scenarios for each moving process, and the evaluation results showed that drop-off notification using multi-senses showed the highest utilization. It is hoped that the expansion of self-driving vehicles will increase the mobility of visually impaired people with difficulty driving. Full article

Safe street crossing poses significant challenges for visually impaired pedestrians, who must rely on non-visual cues to assess crossing safety. Conventional assistive technologies often fail to provide real-time, actionable information about oncoming traffic, making independent navigation difficult, particularly in uncontrolled or vehicle-based crossing scenarios. To address these challenges, we designed and evaluated two assistive systems utilizing haptic and visual feedback, tailored for traffic signal-controlled intersections and vehicle-based crossings. The results indicate that visual feedback significantly improved decision efficiency at signalized intersections, enabling users to make faster decisions, regardless of their confidence levels. However, in vehicle-based crossings, where real-time hazard assessment is crucial, haptic feedback proved more effective, enhancing decision efficiency by enabling quicker and more intuitive judgments about approaching vehicles. Moreover, users generally preferred haptic feedback in both scenarios, citing its comfort and intuitiveness. These findings highlight the distinct challenges posed by different street-crossing environments and confirm the value of multimodal feedback systems in supporting visually impaired pedestrians. Our study provides important design insights for developing effective assistive technologies that enhance pedestrian safety and independence across varied urban settings. Full article

This paper proposes a solution for guiding visually impaired people to reach predefined locations marked with preregistered passive ultra-high-frequency RFID tags inside public buildings (e.g., secretary’s offices and information desks). Our approach employs an unmanned ground vehicle guidance system that assists customers in following predefined routes. The solution also includes a methodology for recording the best routes between all possible locations that may be visited. When reaching the destination, the system will read the tag, extract all the associated information from a database, and translate it into an audio format played into the user’s headphones. The system includes functionalities such as recording and playback of prerecorded routes, voice commands, and audio instructions. By describing the software and hardware architecture of the proposed guiding systems prototype, we show how combining ultra-high-frequency RFID technology with unmanned ground vehicle guiding systems equipped with ultrasonic, grayscale, hall sensors, and voice interfaces allows the development of accessible, low-cost guiding systems with increased functionalities. Moreover, we compare and analyze two different modes of route recording based on line following and manual recording, obtaining a performance regarding route playback with deviations under 10% for several basic scenarios. Full article

Nowadays, rapid advancements in computer vision, image processing, and artificial intelligence (AI) have significantly benefited autonomous vehicles. Visual perception is crucial for enhancing the functionality and safety of self-driving technology. However, adverse weather and illumination conditions can impair visual capabilities, affecting environmental awareness, decision-making, and safe navigation. This work provides a comprehensive review of AI image enhancement methods and benchmark datasets, including deblurring, deraining, dehazing, and low-light enhancement, along with the integration of multiple image enhancement techniques in computer vision tasks. Specifically, this review focuses on advancements for real-world applications and summarizes performance metrics for real-time operation in automotive vision systems. Furthermore, the paper highlights efforts and challenges in real-world testing to ensure the effectiveness and reliability of these solutions in practical applications, which is essential for enabling autonomous vehicles to operate safely and efficiently under various challenging conditions, thereby contributing to the future of intelligent transportation systems. Full article

The Sustainable Development Goals (SDGs) set forth by the United Nations aim to eradicate poverty, protect the environment, and promote global prosperity by 2030. Within this framework, Goal 11 targets explicitly sustainable cities and communities, emphasizing the need for accessible, safe, and sustainable transportation systems for all individuals, including those with disabilities. However, despite these aspirations, individuals with disabilities often face unique challenges and barriers in accessing transportation services. This study delves into the complexities of transportation accessibility for people with disabilities, aiming to understand their perceptions and expectations of service quality regarding reliability, tangibles, cleanliness, safety, comfort, personnel, and stops. In a comprehensive survey involving 302 individuals with disabilities, data were collected considering strata such as visual impairment, hearing impairment, chronic illness, and physical disability. In the study where cluster analysis was applied to examine the common and unique assessments of individuals with disabilities, both demographic characteristics and transportation habits were evaluated to determine the most effective inputs. The optimal results were obtained using disability level, car ownership, access to stops, and frequency of service use, while the inclusion of other sociodemographic variables (such as age and income) negatively affected the quality of the clustering process. By analyzing service quality independently for each cluster, the study unveils potential variations in how people with disabilities perceive and evaluate transportation services. The findings shed light on the distinct evaluation approaches employed by people with disabilities based on their characteristics, highlighting the need for tailored transportation planning and policy-making solutions. For example, in the overall assessment of individuals with disabilities, vehicle ergonomics was not highlighted as an area for improvement, but it emerged as the aspect with the least satisfaction among individuals with higher levels of disability. By addressing these nuances, policymakers and stakeholders can better understand and meet the diverse needs of people with disabilities, contributing to the creation of more inclusive and accessible transportation systems in line with the SDGs. Full article

With the advancement of autonomous driving technology, especially the growing adoption of SAE Level 3 and above systems, drivers are transitioning from active controllers to supervisors who must take over in emergencies. For hearing-impaired drivers in a fatigued state, conventional voice alert systems often fail to provide timely and effective warnings, increasing safety risks. This study proposes an adaptive in-vehicle interface that combines visual and tactile feedback to address these challenges. Experiments were conducted to evaluate response accuracy, reaction time, and cognitive load under varying levels of driver fatigue. The findings show that the integration of visual and tactile cues significantly improves takeover efficiency and reduces mental strain in fatigued drivers. These results highlight the potential of multimodal designs in enhancing the safety and driving experience for hearing-impaired individuals. By providing practical strategies and evidence-based insights, this research contributes to the development of more inclusive and effective interaction designs for future autonomous driving systems. Full article

Visually Impaired Persons (VIPs) have difficulty in recognizing vehicles used for navigation. Additionally, they may not be able to identify the bus to their desired destination. However, the bus bay in which the designated bus stops has not been analyzed in the existing literature. Thus, a guidance system for VIPs that identifies the correct bus for transportation is presented in this paper. Initially, speech data indicating the VIP’s destination are pre-processed and converted to text. Next, utilizing the Arctan Gradient-activated Recurrent Neural Network (ArcGRNN) model, the number of bays at the location is detected with the help of a Global Positioning System (GPS), input text, and bay location details. Then, the optimal bay is chosen from the detected bays by utilizing the Experienced Perturbed Bacteria Foraging Triangular Optimization Algorithm (EPBFTOA), and an image of the selected bay is captured and pre-processed. Next, the bus is identified utilizing a You Only Look Once (YOLO) series model. Utilizing the Sub-pixel Shuffling Convoluted Encoder–ArcGRNN Decoder (SSCEAD) framework, the text is detected and segmented for the buses identified in the image. From the segmented output, the text is extracted, based on the destination and route of the bus. Finally, regarding the similarity value with respect to the VIP’s destination, a decision is made utilizing the Multi-characteristic Non-linear S-Curve-Fuzzy Rule (MNC-FR). This decision informs the bus conductor about the VIP, such that the bus can be stopped appropriately to pick them up. During testing, the proposed system selected the optimal bay in 247,891 ms, which led to deciding the bus stop for the VIP with a fuzzification time of 34,197 ms. Thus, the proposed model exhibits superior performance over those utilized in prevailing works. Full article

In this paper, an intelligent blind guide system based on 2D LiDAR and RGB-D camera sensing is proposed, and the system is mounted on a smart cane. The intelligent guide system relies on 2D LiDAR, an RGB-D camera, IMU, GPS, Jetson nano B01, STM32, and other hardware. The main advantage of the intelligent guide system proposed by us is that the distance between the smart cane and obstacles can be measured by 2D LiDAR based on the cartographer algorithm, thus achieving simultaneous localization and mapping (SLAM). At the same time, through the improved YOLOv5 algorithm, pedestrians, vehicles, pedestrian crosswalks, traffic lights, warning posts, stone piers, tactile paving, and other objects in front of the visually impaired can be quickly and effectively identified. Laser SLAM and improved YOLOv5 obstacle identification tests were carried out inside a teaching building on the campus of Hainan Normal University and on a pedestrian crossing on Longkun South Road in Haikou City, Hainan Province. The results show that the intelligent guide system developed by us can drive the omnidirectional wheels at the bottom of the smart cane and provide the smart cane with a self-leading blind guide function, like a “guide dog”, which can effectively guide the visually impaired to avoid obstacles and reach their predetermined destination, and can quickly and effectively identify the obstacles on the way out. The mapping and positioning accuracy of the system’s laser SLAM is 1 m ± 7 cm, and the laser SLAM speed of this system is 25~31 FPS, which can realize the short-distance obstacle avoidance and navigation function both in indoor and outdoor environments. The improved YOLOv5 helps to identify 86 types of objects. The recognition rates for pedestrian crosswalks and for vehicles are 84.6% and 71.8%, respectively; the overall recognition rate for 86 types of objects is 61.2%, and the obstacle recognition rate of the intelligent guide system is 25–26 FPS. Full article

The structural and biomechanical properties of collagen-rich ocular tissues, such as the sclera, are integral to ocular function. The degradation of collagen in such tissues is associated with debilitating ophthalmic diseases such as glaucoma and myopia, which often lead to visual impairment. Collagen mimetic peptides (CMPs) have emerged as an effective treatment to repair damaged collagen in tissues of the optic projection, such as the retina and optic nerve. In this study, we used atomic force microscopy (AFM) to assess the potential of CMPs in restoring tissue stiffness in the optic nerve head (ONH), including the peripapillary sclera (PPS) and the glial lamina. Using rat ONH tissue sections, we induced collagen damage with MMP-1, followed by treatment with CMP-3 or vehicle. MMP-1 significantly reduced the Young’s modulus of both the PPS and the glial lamina, indicating tissue softening. Subsequent CMP-3 treatment partially restored tissue stiffness in both the PPS and the glial lamina. Immunohistochemical analyses revealed reduced collagen fragmentation after MMP-1 digestion in CMP-3-treated tissues compared to vehicle controls. In summary, these results demonstrate the potential of CMPs to restore collagen stiffness and structure in ONH tissues following enzymatic damage. CMPs may offer a promising therapeutic avenue for preserving vision in ocular disorders involving collagen remodeling and degradation. Full article

The psychosocial and health consequences of ocular conditions that cause visual impairment (VI) are extensive and include impaired daily activities, social isolation, cognitive impairment, impaired functional status and functional decline, increased reliance on others, increased risk of motor vehicle accidents, falls and fractures, poor self-rated health, and depression. We aimed to determine whether VI increases the likelihood of a poor prognosis, including mental illness, suicide, and mortality over time. In this large, location, population-based, nested, cohort study, we used data from 2000 to 2015 in the Taiwan National Health Insurance Research Database (NHIRD), which includes diagnoses of all the patients with VI. Baseline features, comorbidities, and prognostic variables were evaluated using a 1:4-matched cohort analysis. Furthermore, comparisons were performed using Cox regression and Bonferroni-correction (for multiple comparisons) to study the association between VI and poor prognosis (mental illness, suicide). The study outcome was the cumulative incidence of poor prognosis among the visually impaired and controls. A two-tailed Bonferroni-corrected p < 0.001 was considered statistically significant. Among the 1,949,101 patients enlisted in the NHIRD, 271 had been diagnosed with VI. Risk factors for poor prognosis and the crude hazard ratio was 3.004 (95% confidence interval 2.135–4.121, p < 0.001). Participants with VI had an increased risk of poor prognosis according to the sensitivity analysis, with a poor prognosis within the first year and first five years. VI was associated with suicide and mental health risks. This study revealed that patients with VI have a nearly 3-fold higher risk of psychiatric disorders, including anxiety, depression, bipolar, and sleep disorders, than the general population. Early detection through comprehensive examinations based on increased awareness in the clinical context may help maintain visual function and avoid additional complications. Full article

This cross-sectional study aims to examine the quality of life and difficulties in the daily functioning of patients with impaired visual acuity treated with intravitreal drugs. The survey included 180 adult respondents (78 male and 102 female). The standardized, validated questionnaire VFQ 25 version 2000 was used to measure the quality of life. Results show that, in general, regarding visual functioning, men are significantly more satisfied than women, they rate less intensity of pain, and their distance vision is better. Men report fewer restrictions than women, better color, peripheral vision, and overall visual functioning. The best vision results are in individuals under the age of 60 who also report significantly better social functioning, mental health, fewer restrictions, and less dependence on others. The only significant association between the number of drug applications and the scale of visual functioning is driving motor vehicles—the more applications of the drug they received, the less likely they are to drive a car. The quality of life in patients with chronic ophthalmic diseases treated with intravitreal drugs is reduced, particularly in elderly and female patients who have poorer visual acuity, poorer health in general, and limited social roles. Full article

Despite the measures put in place in different countries, road traffic fatalities are still considered one of the leading causes of death worldwide. Thus, the reduction of traffic fatalities or accidents is one of the contributing factors to attaining sustainability goals. Different factors such as the geometric structure of the road, a non-signalized road network, the mechanical failure of vehicles, inexperienced drivers, a lack of communication skills, distraction and the visual or cognitive impairment of road users have led to this increase in traffic accidents. These factors can be categorized under four headings that are: human, road, vehicle factors and environmental road conditions. The advent of machine learning algorithms is of great importance in analysing the data, extracting hidden patterns, predicting the severity level of accidents and summarizing the information in a useful format. In this study, three machine learning algorithms for classification, such as Decision Tree, LightGBM and XGBoost, were used to model the accuracy of road traffic accidents in the UK for the year 2020 using their default and hyper-tuning parameters. The results show that the high performance of the Decision Tree algorithm with default parameters can predict traffic accident severity and provide reference to the critical variables that need to be monitored to reduce accidents on the roads. This study suggests that preventative strategies such as regular vehicle technical inspection, traffic policy strengthening and the redesign of vehicle protective equipment be implemented to reduce the severity of road accidents caused by vehicle characteristics. Full article

Objective: To compare established clinical outcome assessments for predicting behind the wheel driving readiness and driving simulator results across age groups and in traumatic brain injury. Methods: Participants included adults who had a traumatic brain injury ranging in age from 31 to 57 years and a non-impaired adult population ranging in age from 18 to 80 years. Physical and cognitive outcomes measures were collected included range of motion and coordination, a “Rules of the Road Test” a “Sign Identification Test,” Trails A and B, and the clock drawing test. Visual measures included the Dynavision D2 system and motor-free visual perceptual test-3 (MVPT-3). Finally, the driving simulators (STI^Ò version M300) metro drive assessment was used, which consisted of negotiating several obstacles in a metropolitan area including vehicles abruptly changing lanes, pedestrians crossing streets, and negotiating construction zones. Results: Our findings suggest that the standard paper-pencil cognitive assessments and sign identification test significantly differentiate TBI from a non-impaired population (Trails A, B and Clock drawing test p < 0.001). While the driving simulator did not show as many robust differences with age, the TBI population did have a significantly greater number of road collisions (F_{3, 78} = 3.5, p = 0.02). We also observed a significant correlation between the cognitive assessments and the simulator variables. Conclusions: Paper-pencil cognitive assessments and the sign identification test highlight greater differences than the STI Driving Simulator between non-impaired and TBI populations. However, the driving simulator may be useful in assessing cognitive ability and training for on the road driving. Full article

Multiple Sclerosis (MS) is a highly disabling neurological disease characterized by inflammation, neuronal damage, and demyelination. Vision impairment is one of the major clinical features of MS. Previous studies from our lab have shown that MDL 72527, a pharmacological inhibitor of spermine oxidase (SMOX), is protective against neurodegeneration and inflammation in the models of diabetic retinopathy and excitotoxicity. In the present study, utilizing the experimental autoimmune encephalomyelitis (EAE) model of MS, we determined the impact of SMOX blockade on retinal neurodegeneration and optic nerve inflammation. The increased expression of SMOX observed in EAE retinas was associated with a significant loss of retinal ganglion cells, degeneration of synaptic contacts, and reduced visual acuity. MDL 72527-treated mice exhibited markedly reduced motor deficits, improved neuronal survival, the preservation of synapses, and improved visual acuity compared to the vehicle-treated group. The EAE-induced increase in macrophage/microglia was markedly reduced by SMOX inhibition. Upregulated acrolein conjugates in the EAE retina were decreased through MDL 72527 treatment. Mechanistically, the EAE-induced ERK-STAT3 signaling was blunted by SMOX inhibition. In conclusion, our studies demonstrate the potential benefits of targeting SMOX to treat MS-mediated neuroinflammation and vision loss. Full article