Monocular Vision Research Articles

Influence Evaluation of Systematic Errors and Prismatic Postures on Field of View in Monocular Stereo Vision

Influence Evaluation of Systematic Errors and Prismatic Postures on Field of View in Monocular Stereo Vision

Accurate 3-D Positioning of Aircraft Based on Laser Rangefinder Combining Monocular Vision Measurement

Accurate 3-D Positioning of Aircraft Based on Laser Rangefinder Combining Monocular Vision Measurement

Monocular vision transmission line sag measurement method based on local photography

Monocular vision transmission line sag measurement method based on local photography

D-LDRNet: Monocular vision framework merging prior LiDAR knowledge for all-weather safe monitoring of vehicle in transmission lines

D-LDRNet: Monocular vision framework merging prior LiDAR knowledge for all-weather safe monitoring of vehicle in transmission lines

Неврологические осложнения в косметологии: обзор литературы

INTRODUCTION. The article discusses complications from the nervous system during such cosmetic procedures as botulinum therapy, the use of fillers, mesotherapy and thread lifting. AIM. Conduct an analysis of literary sources of domestic and foreign authors describing the modern understanding of neurological complications that arise in cosmetology practice. MATERIAL AND METHODS. An analysis of literature in Russian and English was carried out for the period from 2013–2024. Sources from the Russian scientific electronic library eLIBRARY, RSCI databases, and PubMed were used. RESULTS AND DISCUSSION. One of the most common neurological side effects of botulinum toxin is paralysis of the facial and masticatory muscles, innervated by the facial and trigeminal nerves, respectively. The mechanism of the negative effect of fillers on nervous tissue is associated, first of all, with their composition, which can have a toxic effect. During filler injections, nerve fibers can be damaged, which leads to disruption of the transmission of nerve impulses. The literature describes cases of deterioration or even loss of monocular vision, ptosis and ophthalmoplegia after injection of hyaluronic acid filler. A complication when using fillers based on hyaluronic acid and autologous fat is acute cerebrovascular accident. Prevention of neurological complications during cosmetic procedures is an important aspect of safety and successful results in aesthetic medicine.CONCLUSION. Neurological complications can occur as a result of various cosmetic procedures. The main factors are technique, lack of understanding of facial anatomy, and the use of low-quality drugs. It is important to be aware of the potential risks and contact only experienced specialists to reduce the likelihood of neurological complications. KEYWORDS: fillers, botulinum therapy, thread lifting, neurological complications, facial nerve neuropathy

Omnidirectional spatial monocular vision indoor localization measurement based on a two-degree-of-freedom rotary platform

Omnidirectional spatial monocular vision indoor localization measurement based on a two-degree-of-freedom rotary platform

Measuring near-field wave elevation with monocular vision using self-supervised learning techniques

Ocean waves are among the most influential factors affecting marine mechanical systems. The existing methods for measuring wide-area wave-field data have limitations and require high maintenance costs. Therefore, it is crucial to develop a reliable and efficient field measurement method for wide-area wave fields. This study proposes a monocular vision-based approach for wave field measurement, where the depth of each pixel is equalised to summation of the depth of the mean water surface and the depth variation induced by wave elevation. A deep network was trained using a self-supervised algorithm to approximate the depth variation induced by wave elevation. A loss of representative features was proposed to improve the performance of deep networks. The images of an open-source dataset were used to train and validate the proposed model. By using the proposed method, the images were utilised to reconstruct the three-dimensional wave field of the test set. The time history and wave spectrum of the wave fields were compared with those calculated by existing method and measured by wave gauge. The influence of the training set on the measurement results was also investigated. The results indicate that the proposed method is capable of performing effective near-field wave measurements by monocular images, effectively reducing the device requirements, and increasing update frequency for ocean wave measurement.

Diagnosis and management of transient smartphone blindness: A literature review

The development of smartphones worldwide has rapidly increased the number of smartphone users. Although smartphones have many benefits, prolonged use causes various visual disorders, of which transient smartphone blindness (TSB) is one of the most important concerns. This study aims to analyse the phenomenon of TSB and explore its etiology, pathophysiology, symptoms, and examination to determine the diagnosis and management. Transient smartphone blindness is a new physiologic phenomenon caused by exposure to a certain level of smartphone bright light and the body posture of the smartphone user. It leads to the use of monocular vision to stare at the smartphone. By exploring recent literature, this study found that patients with TSB experienced retinal photopigment bleaching, which decreased light sensitivity. Typically, the sensitivity returned physiologically after several minutes. Patients with this blindness showed several symptoms. For example, they perceived shapes, outlines, or figures during the blackout. The diagnosis of TSB should be primarily based on a detailed history of smartphone use, with the differential diagnosis based on circumstance or occurrence. This diagnosis is useful to distinguish it from transient ischemic attack (TIA). Transient smartphone blindness is a basic monocular transient loss that does not require therapy or drugs. However, it was found that the reassurance of patients’ condition and suggestions on smartphone use were sufficient for the intervention. With a limited scientific study of TSB, this review is the first to raise the discussion topic. It is expected to help physicians to diagnose TSB significantly. In addition, this study will enrich the literature, particularly on the scientific and clinical mechanisms of recognising TSB for clinical diagnosis and management.

A Review of Human Pose Estimation Methods Based on Monocular Vision

This article is a review of the technology methods and industry applications of monocular human pose estimation, which focuses on the recent development of monocular human pose estimation. With the rapid development of computer vision and machine learning, monocular human pose estimation has become a research direction that has attracted much attention. In this article, we first introduce the relevant concepts and significance of monocular human pose estimation, explain the importance of research in this field. Then, we provide a detailed overview of the technical methods of monocular human pose estimation, including two different approaches: monocular 2D human pose estimation and monocular 3D human pose estimation. For each research method, we discuss its principles, development, and pros and cons. Next, we explore the applications of monocular human pose estimation in various fields such as human-computer interaction, autonomous driving, healthcare, and provide examples to highlight the significance of human pose estimation. Finally, we analyze the current research hotspots and challenges and also look forward to the future directions of monocular human pose estimation. This article aims to provide researchers and practitioners with a comprehensive overview and promote the application and further research of monocular human pose estimation technology.

К вопросу о врожденных заболеваниях хрусталика глаза у детей

Material and methods. 110 children with congenital cataract and 16 with lens subluxation aged 1–17 years (on average 8.7±2.3) were under observation, 57 of them boys and 69 girls. All patients were examined using standard ophthalmological techniques: visometry, autorefractometry, keratometry, ultrasound biometry, an optical biometer IOL Master-500 was used to calculate IOL. Surgical treatment was required only by patients with monocular vision – with a number of 32 (45 eyes) and 6 (11 eyes). Surgical method of traetmen was presented in Saint-Petersburg brunchof S. Fyodorov Eye Microsurgery Federal State Institution. It included phacoaspiration, implantation of IOLs, including monofocal, toric and IOLs with aExtended Depth of Focus (EDOF). In cases of congenital pathology of the ligaments, an intracapsular ring (ICR) was used, including its suture fixation. Results. Children with congenital cataracts showedseveral prognostic symptoms – relatively favorable, conditionally favorable, negative and critical. Surgery of the first two of them allowed to increase monocular visual acuity (with correction) in the range from 0.1–0.4 (44.0%;) to the level of 0.9 (31%), all in binocular cases. Patients with negative symptoms (strabismus) showed low vision due to functional disorders, especially with congenital amblyopia (caused by obscuration, strabismus, and refractive changes). It required long-term pleoptoorthoptic treatment, but without a guarantee of restoration of binocularity. Finally, children with critical symptoms had extremely low vision (less than 0.09 and up to light perception) and was practically not acceptable for rehabilitation. Children with lens subluxation also required specific surgery. Their monolateral visual acuity with correction ranged from 0.13 to 0.39 (children 3–7 years old) and 0.13–0.8 (12–15 years old), that was sufficiently high, but without binocularity. Key words: congenital cataract, subluxation of the lens, clinical refraction, axial length, strabismus

AUTONOMOUS VEHICLES LOCALISATION BASED ON SEMANTIC MAP MATCHING METHOD

Abstract. In autonomous driving systems, a positioning method that can be used in scenarios with no satellite signals or long signal interruptions is a must. In this paper, we address the problems in map construction methods and map matching methods in scenes without satellite signals or long signal interruptions, and construct a semantic map matching-based localization method to meet the localization requirements by means of monocular vision sensors on the basis of weighing the accuracy and cost of map construction and localization. In this paper, firstly, the method of map construction is studied and a static semantic map construction method based on monocular camera is constructed. Then the map matching localization method is studied, and a semantic map matching based localization method is constructed to align the local map built during localization with the pre-built global semantic map to obtain the current location information. Finally, this paper constructs a method to fuse the visual odometry and map matching localization results, so as to obtain more accurate localization results.

Visual Sensing and Depth Perception for Welding Robots and Their Industrial Applications.

With the rapid development of vision sensing, artificial intelligence, and robotics technology, one of the challenges we face is installing more advanced vision sensors on welding robots to achieve intelligent welding manufacturing and obtain high-quality welding components. Depth perception is one of the bottlenecks in the development of welding sensors. This review provides an assessment of active and passive sensing methods for depth perception and classifies and elaborates on the depth perception mechanisms based on monocular vision, binocular vision, and multi-view vision. It explores the principles and means of using deep learning for depth perception in robotic welding processes. Further, the application of welding robot visual perception in different industrial scenarios is summarized. Finally, the problems and countermeasures of welding robot visual perception technology are analyzed, and developments for the future are proposed. This review has analyzed a total of 2662 articles and cited 152 as references. The potential future research topics are suggested to include deep learning for object detection and recognition, transfer deep learning for welding robot adaptation, developing multi-modal sensor fusion, integrating models and hardware, and performing a comprehensive requirement analysis and system evaluation in collaboration with welding experts to design a multi-modal sensor fusion architecture.

Light Field Display Based on Monocular Stereo Vision

Light Field Display Based on Monocular Stereo Vision

The effect of different depth planes during a manual tracking task in three-dimensional virtual reality space

Unlike ballistic arm movements such as reaching, the contribution of depth information to the performance of manual tracking movements is unclear. Thus, to understand how the brain handles information, we investigated how a required movement along the depth axis would affect behavioral tracking performance, postulating that it would be affected by the amount of depth movement. We designed a visually guided planar tracking task that requires movement on three planes with different depths: a fronto-parallel plane called ROT (0), a sagittal plane called ROT (90), and a plane rotated by 45° with respect to the sagittal plane called ROT (45). Fifteen participants performed a circular manual tracking task under binocular and monocular visions in a three-dimensional (3D) virtual reality space. As a result, under binocular vision, ROT (90), which required the largest depth movement among the tasks, showed the greatest error in 3D. Similarly, the errors (deviation from the target path) on the depth axis revealed significant differences among the tasks. Under monocular vision, significant differences in errors were observed only on the lateral axis. Moreover, we observed that the errors in the lateral and depth axes were proportional to the required movement on these axes under binocular vision and confirmed that the required depth movement under binocular vision determined depth error independent of the other axes. This finding implies that the brain may independently process binocular vision information on each axis. Meanwhile, the required depth movement under monocular vision was independent of performance along the depth axis, indicating an intractable behavior. Our findings highlight the importance of handling depth movement, especially when a virtual reality situation, involving tracking tasks, is generated.

Space, time, and dynamics of binocular interactions

Binocular summation (BS), defined as the superiority of binocular over monocular visual performance, shows that thresholds are about 40% (a factor of 1.4) better in binocular than in monocular viewing. However, it was reported that different amounts of BS exist in a range from 1.4 to 2 values because BS is affected by the spatiotemporal parameters of the stimulus. Lateral interactions can be defined as the neuron’s ability to affect the neighboring neurons by either inhibiting or exciting their activity. We investigated the effect of the spatial and temporal domains on binocular interactions and BS under the lateral masking paradigm and how BS would be affected by lateral interactions via a lateral masking experiment. The two temporal alternative forced-choice (2TAFC) method was used. The stimuli consisted of a central vertically oriented Gabor target and high-contrast Gabor flankers positioned in two configurations (orthogonal or collinear) with target-flanker separations of either 2 or 3 wavelengths (λ), presented at 4 different presentation times (40, 80, 120, and 200 ms) using a different order of measurements across the different experiments. Opaque lenses were used to control the monocular and binocular vision. BS is absent at close distances (2λ), depending on the presentation time’s order, for the collinear but not for the orthogonal configuration. However, BS exists at more distant flankers (collinear and orthogonal, 3λ). BS is not uniform (1.4); it depends on the stimulus condition, the presentation times, the order, and the method that was used to control the monocular and binocular vision.

MONO-HYDRA: REAL-TIME 3D SCENE GRAPH CONSTRUCTION FROM MONOCULAR CAMERA INPUT WITH IMU

Abstract. The ability of robots to autonomously navigate through 3D environments depends on their comprehension of spatial concepts, ranging from low-level geometry to high-level semantics, such as objects, places, and buildings. To enable such comprehension, 3D scene graphs have emerged as a robust tool for representing the environment as a layered graph of concepts and their relationships. However, building these representations using monocular vision systems in real-time remains a difficult task that has not been explored in depth.This paper puts forth a real-time spatial perception system Mono-Hydra, combining a monocular camera and an IMU sensor setup, focusing on indoor scenarios. However, the proposed approach is adaptable to outdoor applications, offering flexibility in its potential uses. The system employs a suite of deep learning algorithms to derive depth and semantics. It uses a robocentric visual-inertial odometry (VIO) algorithm based on square-root information, thereby ensuring consistent visual odometry with an IMU and a monocular camera. This system achieves sub-20 cm error in real-time processing at 15 fps, enabling real-time 3D scene graph construction using a laptop GPU (NVIDIA 3080). This enhances decision-making efficiency and effectiveness in simple camera setups, augmenting robotic system agility. We make Mono-Hydra publicly available at: https://github.com/UAV-Centre-ITC/Mono_Hydra.

Multiscale feature fusion network for monocular complex hand pose estimation

AbstractHand pose estimation based on a single RGB image has low accuracy due to the complexity of the pose, local self‐similarity of finger features, and occlusion. A multiscale feature fusion network (MS‐FF) for monocular vision gesture pose estimation is proposed to address this problem. The network can take full advantage of different channel information to enhance important gesture information, and it can simultaneously extract features from feature maps of different resolutions to obtain as much detailed feature information and deep semantic information as possible. The feature maps are merged to obtain the hand pose results. The InterHand2.6M dataset and Rendered Handpose Dataset (RHD) are used to train the MS‐FF. Compared with the other methods, the MS‐FF obtains the smallest average error of hand joints, verifying its effectiveness.

Effect of binocular vision during target shooting in archery.

This study aimed to evaluate the difference between binocular and monocular vision and eye movements during the competition using video-oculography (VOG). Experiment 1 included 14 participants to evaluate differences in arrow convergence. Then, seven participants in Experiment 1 were randomly selected and included in Experiment 2, which evaluated eye movements during archery using VOG. The target used an 80-cm waterproof target face and was set at a distance of 30 m. All players shot the target 36 times using their bows and arrows. Experiments 1 and 2 evaluated the distribution of arrows in each score and the number of focus points, respectively, between binocular and monocular conditions. The arrows, which include the area of 9 points, were significantly greater in the binocular condition (11.85 ± 5.04 shots) than in the monocular condition (9.36 ± 5.41 shots) in Experiment 1 (P = 0.047). The players focused on the target under both binocular and monocular conditions, although the players were switching off fixation between the target and shooting sight under the binocular condition in Experiment 2. These behaviors indicated that the players were trying to accurately shoot the target by exploring the distance between themselves and the target as a cue for depth perception.

Retracted: FastQR: Fast Pose Estimation of Objects Based on Multiple QR Codes and Monocular Vision in Mobile Embedded Devices

Retracted: FastQR: Fast Pose Estimation of Objects Based on Multiple QR Codes and Monocular Vision in Mobile Embedded Devices

Prevalence and causes of vision impairment in elderly Chinese people living in suburban Shanghai

PurposeTo investigate the current prevalence and causes of moderate and severe visual impairment (MSVI) and blindness in elderly people in suburban Shanghai, China. MethodsA cross-sectional study based on the population was conducted, which involved 5846 individuals (11,692 eyes) aged 65 years or older. Thorough eye examinations were performed to assess the prevalence and leading factors of MSVI (BCVA <20/63 to ≥20/400) and blindness (BCVA <20/400). ResultsThe standardized prevalence of bilateral MSVI and blindness was 3.3% and 0.6%, correspondingly. The standardized prevalence of monocular MSVI and blindness was 7.4% and 2.0%, correspondingly. Cataract (47.9% and 20.7%, correspondingly) and myopic macular degeneration (MMD, 25.7% and 31.1%, correspondingly) were the principal causes of bilateral MSVI and blindness. As for monocular MSVI, the primary causes were cataract (39.4%), age-related macular degeneration (AMD, 16.6%), and MMD (16.6%). The primary causes of monocular blindness were other posterior segment eye diseases (30.1%) and MMD (14.2%). In adults aged 65–74 years, MMD was the foremost factor causing bilateral vision impairment. Conversely, cataract was identified as the primary cause of bilateral and monocular vision impairment among adults aged ≥ 75 years. AMD accounts for a significant proportion of individuals across all age groups. ConclusionsThe significant prevalence of MSVI and blindness among Chinese adults represents a critical public health issue. In addition to cataract, the vision impairment caused by MMD and AMD become an important issue in the elderly Chinese people.