Distant Objects Research Articles

Enhancing 3D object detection by using neural network with self-adaptive thresholding

Robust 3D object detection remains a pivotal concern in the domain of autonomous field robotics. Despite notable enhancements in detection accuracy across standard datasets, real-world urban environments, characterized by their unstructured and dynamic nature, frequently precipitate an elevated incidence of false positives, thereby undermining the reliability of existing detection paradigms. In this context, our study introduces an advanced post-processing algorithm that modulates detection thresholds dynamically relative to the distance from the ego object. Traditional perception systems typically utilize a uniform threshold, which often leads to decreased efficacy in detecting distant objects. In contrast, our proposed methodology employs a Neural Network with a self-adaptive thresholding mechanism that significantly attenuates false negatives while concurrently diminishing false positives, particularly in complex urban settings. Empirical results substantiate that our algorithm not only augments the performance of 3D object detection models in diverse urban and adverse weather scenarios but also establishes a new benchmark for adaptive thresholding techniques in field robotics.

Study of Migration of Giant Planets and Formation of Populations of Distant Trans-Neptunian Objects in the Nice Model

Study of Migration of Giant Planets and Formation of Populations of Distant Trans-Neptunian Objects in the Nice Model

Reimagining Accessibility: Leveraging Deep Learning in Smartphone Applications to Assist Visually Impaired People Indoor Object Distance Estimation

Every other aspect of life is organized around the sight. A person with vision impairment suffers severely from independent mobility and quality of life. The proposed framework combines mobile deep learning with distance estimation algorithms to detect and classify indoor objects with estimated distance in real-time during indoor navigation. The user, wearing the device with a lanyard or holding it in a way that positions the camera forward, identifies in real-time surroundings indoor objects with estimated distance and voice commentary. Moreover, the mobile framework provides an estimated distance to the obstacles and suggests a safe navigational path through voice-guided feedback. By harnessing the power of deep learning in a mobile setting, this framework aims to improve the independence of visually impaired individuals by facilitating them a higher degree of independence in indoor navigation. This study's proposed mobile object detection and distance estimation framework achieved 99.75% accuracy. This research contributes by leveraging mobile deep learning with identifying objects in real-time, classification and distance estimation, a state-of-the-art approach to use the latest technologies to enhance indoor mobility challenges faced by visually impaired people.

Synthetic Data Enhancement and Network Compression Technology of Monocular Depth Estimation for Real-Time Autonomous Driving System.

Accurate 3D image recognition, critical for autonomous driving safety, is shifting from the LIDAR-based point cloud to camera-based depth estimation technologies driven by cost considerations and the point cloud's limitations in detecting distant small objects. This research aims to enhance MDE (Monocular Depth Estimation) using a single camera, offering extreme cost-effectiveness in acquiring 3D environmental data. In particular, this paper focuses on novel data augmentation methods designed to enhance the accuracy of MDE. Our research addresses the challenge of limited MDE data quantities by proposing the use of synthetic-based augmentation techniques: Mask, Mask-Scale, and CutFlip. The implementation of these synthetic-based data augmentation strategies has demonstrably enhanced the accuracy of MDE models by 4.0% compared to the original dataset. Furthermore, this study introduces the RMS (Real-time Monocular Depth Estimation configuration considering Resolution, Efficiency, and Latency) algorithm, designed for the optimization of neural networks to augment the performance of contemporary monocular depth estimation technologies through a three-step process. Initially, it selects a model based on minimum latency and REL criteria, followed by refining the model's accuracy using various data augmentation techniques and loss functions. Finally, the refined model is compressed using quantization and pruning techniques to minimize its size for efficient on-device real-time applications. Experimental results from implementing the RMS algorithm indicated that, within the required latency and size constraints, the IEBins model exhibited the most accurate REL (absolute RELative error) performance, achieving a 0.0480 REL. Furthermore, the data augmentation combination of the original dataset with Flip, Mask, and CutFlip, alongside the SigLoss loss function, displayed the best REL performance, with a score of 0.0461. The network compression technique using FP16 was analyzed as the most effective, reducing the model size by 83.4% compared to the original while maintaining the least impact on REL performance and latency. Finally, the performance of the RMS algorithm was validated on the on-device autonomous driving platform, NVIDIA Jetson AGX Orin, through which optimal deployment strategies were derived for various applications and scenarios requiring autonomous driving technologies.

A dynamic scale-mixture model of motion in natural scenes.

Some of the most important tasks of visual and motor systems involve estimating the motion of objects and tracking them over time. Such systems evolved to meet the behavioral needs of the organism in its natural environment, and may therefore be adapted to the statistics of motion it is likely to encounter. By tracking the movement of individual points in movies of natural scenes, we begin to identify common properties of natural motion across scenes. As expected, objects in natural scenes move in a persistent fashion, with velocity correlations lasting hundreds of milliseconds. More subtly, but crucially, we find that the observed velocity distributions are heavy-tailed and can be modeled as a Gaussian scale-mixture. Extending this model to the time domain leads to a dynamic scale-mixture model, consisting of a Gaussian process multiplied by a positive scalar quantity with its own independent dynamics. Dynamic scaling of velocity arises naturally as a consequence of changes in object distance from the observer, and may approximate the effects of changes in other parameters governing the motion in a given scene. This modeling and estimation framework has implications for the neurobiology of sensory and motor systems, which need to cope with these fluctuations in scale in order to represent motion efficiently and drive fast and accurate tracking behavior.

Research on a Machine Vision-based Blade Measurement Method

A high-precision visual measurement method for the geometric dimensions of oil pump blades is proposed, utilizing an auxiliary measurement mechanism to assist in sub-pixel edge positioning. Based on images of calibration boards, the camera distortion is corrected by partitioning the image into regions and establishing a mapping index between pixel coordinates and real-world coordinates. Under fixed object and image distances, images of the oil pump blades and the contact between the blades and the pump are separately captured. The Canny operator and Sigmoid function are employed to fit the edges, extracting sub-pixel coordinates, which are then mapped to real-world coordinates. Finally, a least squares edge fitting is conducted to compute the dimensional parameters. Experimental results indicate that the use of auxiliary measurement mechanisms effectively enhances the precision of blade measurements, as compared to measurements solely based on oil pump blade images and images of the blade in contact with the pump.

Enhancing 3D object detection through multi-modal fusion for cooperative perception

Fueled by substantial advancements in deep learning, the domain of autonomous driving is swiftly advancing towards more robust and effective intelligent systems. One of the critical challenges in this field is achieving accurate 3D object detection, which is often hindered by data sparsity and occlusion. To address these issues, we propose a method centered around a multi-modal fusion strategy that leverages vehicle-road cooperation to enhance perception capabilities. Our approach integrates label information from roadside perception point clouds to harmonize and enrich the representation of image and LiDAR data. This comprehensive integration significantly improves detection accuracy by providing a fuller understanding of the surrounding environment. Rigorous evaluations of our proposed method on two benchmark datasets, KITTI and Waymo Open, demonstrate its superior performance, with our model achieving 87.52% 3D Average Precision (3D AP) and 93.71% Bird’s Eye View Average Precision (BEV AP) on the KITTI val set. These results highlight the effectiveness of our method in detecting sparse and distant objects, contributing to the development of safer and more efficient autonomous driving solutions.

SRFAD-Net: Scale-Robust Feature Aggregation and Diffusion Network for Object Detection in Remote Sensing Images

The significant differences in target scales of remote sensing images lead to remarkable variations in visual features, posing significant challenges for feature extraction, fusion, regression, and classification. For example, models frequently struggle to capture features of targets across all scales, inadequately consider the weights and importance of features at different scales during fusion, and encounter accuracy limitations when detecting targets of varying scales. To tackle these challenges, we proposes a Scale-Robust Feature Aggregation and Diffusion Network (SRFAD-Net) for remote sensing target detection. This model includes a Scale-Robust Feature Network (SRFN), an Adaptive Feature Aggregation and Diffusion (AFAD) module, and a Focaler-GIoU Loss. SRFN extracts scale-robust features by constructing a multi-scale pyramid. It includes a downsampling (ADown) module that combines the advantages of average pooling and max pooling, effectively preserving background information and salient features. This further enhances the network’s ability to handle targets of varying scales and shapes. The introduced Deformable Attention(DAttention) mechanism captures target features effectively through adaptive adjustment of the receptive field’s shape and size, reducing background clutter and substantially enhancing the model’s performance in detecting distant objects. In the feature fusion stage, we propose the AFAD module, which utilizes a dimension-adaptive perceptual selection mechanism and parallel depthwise convolutional operations to precisely aggregate multi-channel information. It then employs a diffusion mechanism to spread contextual information across various scales, greatly improving the network’s ability to extract and fuse features across multiple scales. For the detection head, we adopt the Focaler-GIoU Loss, leveraging its advantages in handling non-overlapping bounding boxes, effectively alleviating the difficulty of localization caused by scale variations. We have undertaken experiments on two widely utilized aerial target datasets: the Remote Sensing Scene Object Detection Dataset (RSOD) and NWPU VHR-10, which is a high-resolution object detection dataset from Northwestern Polytechnical University. The findings of these experiments clearly illustrate that SRFAD-Net surpasses the performances of mainstream detectors.

Comparison of deviceless methods for distant object manipulation in mixed reality

Mixed Reality (MR) applications based on the current generation of Head-mounted displays (HMDs) support a deviceless manipulation of virtual objects based on finger tracking and control of the 3D transformation with gestures. However, when the object manipulation is performed at some distance, and when the transform includes scaling, it is not apparent how to remap the hand motions over the degrees of freedom of the object. The most popular software toolkits used for XR development provide specific solutions, but there are still usability issues and a need for clear guidelines for the interaction design.In this work, we compare three different solutions for the devices and remote translation, rotation, and scaling of virtual objects in a real environment in two user studies aimed at assessing the usability of the methods for different tasks. The tasks are a fast and rough docking of virtual cubes on a tangible shelf from varying distances and the accurate placement of cubes on the shelf in a fixed amount of time.The outcomes of these studies show that the usability of the manipulation methods is strongly affected by the use of separate or integrated control of the degrees of freedom, by the use of the hands in a symmetric or specialized way, by the visual feedback, and by the previous experience of the users and provides valuable guidelines for the design of interactive mixed environments.

MMFG: Multimodal-based Mutual Feature Gating 3D Object Detection

To address the problem that image and point cloud features are fused in a coarse fusion way and cannot achieve deep fusion, this paper proposes a multimodal 3D object detection architecture based on a mutual feature gating mechanism. First, since the feature aggregation approach based on the set abstraction layer cannot obtain fine-grained features, a point-based self-attention mechanism module is designed. This module is added to the extraction branch of point cloud features to achieve fine-grained feature aggregation while maintaining accurate location information. Second, a new gating mechanism is designed for the deep fusion of image and point cloud. Deep fusion is achieved by mutual feature weighting between the image and the point cloud. The newly fused features are then fed into a feature refinement network to extract classification confidence and 3D target bounding boxes. Finally, a multi-scale detection architecture is proposed to obtain a more complete object shape. The location-based encoding feature algorithm is also designed to focus the interest points in the region of interest adaptively. The whole architecture shows outstanding performance on the KITTI3D and nuSenece datasets, especially at the difficult level. It shows that the framework solves the problem of low detection rates in LiDAR mode due to the low number of surface points obtained from distant objects.

Finite-Time Synchronization of Neural Networks With Proportional Delays for RGB-D Image Protection.

Since the depth information of images facilitates the analysis of the spatial distance of objects in computer vision applications, it is necessary to protect the image depth information. Thus this article proposes a novel red-green-blue-depth (RGB-D) image protection algorithm, which is implemented with the finite-time synchronization (FTS) of neural networks (NNs) with proportional delays via the quantized intermittent control to derive the system synchronization criterion based on Lyapunov stability theory. The performance of RGB-D image protection depends on the synchronization error of the system by driving the system sequence to encrypt the RGB-D image and responding to the system sequence to decrypt the encrypted image. Subsequently, the validity of the proposed criteria is verified by simulation examples, and the practical application of RGB-D image protection is verified.

Deep Learning Based Monocular Depth Estimation for Object Distance Inference in 2D Images

Monocular depth estimation, a process of predicting depth from a single 2D image, has seen significant advancements due to the proliferation of deep learning techniques. This research focuses on leveraging deep learning for monocular depth estimation to infer object distances accurately in 2D images. We explore various convolutional neural network (CNN) architectures and transformer models to analyze their efficacy in predicting depth information. Our approach involves training these models on extensive datasets annotated with depth information, followed by rigorous evaluation using standard metrics. The results demonstrate substantial improvements in depth estimation accuracy, highlighting the potential of deep learning in enhancing computer vision tasks such as autonomous driving, augmented reality, and robotic navigation. This study not only underscores the importance of model architecture but also investigates the impact of training data diversity and augmentation strategies. The findings provide a comprehensive understanding of the current state-of-the-art in monocular depth estimation, paving the way for future innovations in object distance inference from 2D images. By providing a detailed analysis of various models and their performance, this research contributes to a better understanding of monocular depth estimation and its potential for real-world applications, paving the way for future advancements in object distance inference from 2D images.

A novel data-driven algorithm for object detection, tracking, distance estimation, and size measurement in stereo vision systems

A novel data-driven algorithm for object detection, tracking, distance estimation, and size measurement in stereo vision systems

Monocular 3D object detection for distant objects

Monocular 3D object detection for distant objects

Self-healing propagation of a longitudinally varying vector optical beam for distance measurement.

Based on the longitudinal manipulation of polarization, a special vector optical beam (VOB) with customized polarization variation in propagation direction can be generated, whose properties and applications remain to be studied. Here, the self-healing propagation behaviors of the longitudinally varying VOB after an opaque object are investigated, and the localized polarization responses on the object distance are revealed. On this basis, characteristic parameters are defined to measure the distance of object, achieving a minimum relative error of 0.63% in a longitudinal range of 300 mm. Besides, the correlations and uncoupling methods of object distance and size are discussed. Our studies open new ways to use the structural properties of VOB and may be instructive for laser measurement.

Distance-based integration method for human skin type identification

Although identifying human skin types is essential in dermatology, cosmetology, and facial recognition, the classification of human skin types is challenging due to the complex nature, varied characteristics, and the influence of external factors. Traditional methods for skin type identification often rely on subjective assessments, leading to inconsistent and inaccurate results. Therefore, this paper proposes a novel method named a distance-based integration method to identify skin types based on the Fitzpatrick skin scale, also known as the Fitzpatrick skin type. This study focuses on the objective distance measurement, integrated with the Fuzzy Analytic Hierarchy Process (AHP). The objective distance was utilized to determine the distance between each HEX color code for a clinical image and each target skin type. The Fuzzy AHP algorithm was employed to calculate the total score for each target class to identify human skin type. For this study, 1,022 images of human skin were used in the experiment. The results indicated that the proposed method achieved a high average accuracy of 93 %, precision of 80 %, and specificity of 96 %.

Simulations of galaxies in an expanding Universe with modified Newtonian dynamics (MOND) and with modified gravitational attractions (MOGA)

The stability of galaxies is either explained by the existence of dark matter or caused by a modification of Newtonian acceleration (MOND). Here, we show that the modification of the Newtonian dynamics can equally well be obtained by a modification of Newton’s law of universal gravitational attraction (MOGA) when Newton’s inverse square attraction from a distant object is replaced with an inverse attraction. This modification is often proposed in the standard model, and with the modification of the attraction caused by dark matter. The recently derived algorithm, Eur Phys J Plus, 137:99, 2022; Class Quantum Grav, 39:225006, 2022, for classical celestial dynamics is used to simulate models of the Milky Way in an expanding universe and with either MOND or MOGA. The simulations show that the galaxies with MOND dynamics are unstable, whereas MOGA stabilizes the galaxies. The rotation velocities for objects in galaxies with classical Newtonian dynamics decline inversely proportional to the square root of the distance r to the center of the galaxy. But the rotation velocities is relatively independent of r for MOGA and qualitatively in agreement with experimentally determined rotation curves for galaxies in the Universe. The modification of the attractions may be caused by the masses of the objects in the central part of the galaxy by the lensing of gravitational waves from far-away objects in the galaxy.

Cascaded combination of total variation regularization and contrast limited adaptive histogram equalization based image dehazing

ABSTRACT Haze and fog can significantly reduce the visibility of distant objects by scattering light and creating blurry, washed-out images lacking in detail. Image dehazing is a technique used in computer vision to enhance the clarity of such obscured images. This study examines the effectiveness of various dehazing methods using real hazy images and synthetic images with artificially created haze. Performance metrics such as PSNR, SSIM, MSE, CII, and computation time are used to evaluate the proposed method. The evaluation is carried out on datasets like RESIDE, GMAN, O-Haze, I-Haze, NH-Haze, and Dense haze to compare the proposed method with existing models. The proposed method attains 27.46%, 20.63% and 21.09% higher PSNR and 12.36%, 23.95% and 36.12% lower Natural Image Quality Evaluator for RESIDE dataset when analyzed to the existing models, such as strategic method towards contrast enhancement by 2D histogram equalization under TV decomposition (CE-TDHE-TVD), multiple level framework basis contrast enhancement for uniform with non-uniform back ground imageries utilizing appropriate histogram equalization (CE-VHE), and Contrast enhancement with brightness preservation of low light pictures with the help of combined CLAHE and BPDHE histogram equalization (CE-CLAHE-BPDHE) respectively.

Scope of Ayurveda treatment in Myopia: A systematic review of current trends

Abstract BACKGROUND: Though myopia is an ophthalmic refractive error disease that is commonly managed with refractive glasses and advanced surgeries, it still remains a refractive condition of great concern. Patients often resort to alternate methods to rectify or manage myopia and prevention of its progression. Ayurveda refers to myopia as Timira (errors of refraction), characterized by disturbances in vision; hence, it is considered to be a part of Drishtigata Rogas (eyesight disorders). According to the Ayurvedic perspective, myopia is primarily a result of vitiated Doshas, particularly the imbalance of the Vata Dosha, which impairs the eye muscles and lens, resulting in the inability to focus on distant objects. MATERIALS AND METHODS: This review adhered to the 2020 PRISMA guidelines and involved a comprehensive search of PubMed, Scopus, and UGC-CARE-listed Ayurveda journals from January 2000 to September 2023. The focus was on randomized controlled trials examining Ayurvedic interventions, including topical and oral therapies, for managing myopia or Timira. The search aimed to identify all relevant studies published within the specified timeframe. The Cochrane risk-of-bias tool for randomized trials (RoB 2) was utilized to evaluate the risk of bias. RESULTS: A total of six publications in credible journals were found and analyzed, which revealed that practices such as Netra Tarpana (retaining of medicated ghee over the eye), Nasya (medication through the nasal route), Anjana (collyrium), use of Triphala, Ayurvedic formulations, yoga, and specific eye exercises can enhance the strength of ocular muscles, promote better nourishment of ocular tissues, and foster overall eye health. CONCLUSION: By implementing prophylactic measures, followed by therapeutic and systemic therapies, myopia can be controlled with a multidimensional approach, but due to limited sources of evidence, the certainty can only be proven after extensive clinical trials.

Hubble diagrams in statistically homogeneous, anisotropic universes

We consider the form of Hubble diagrams that would be constructed by observers in universes that are homogeneous but anisotropic, when averaged over suitably large length-scales. This is achieved by ray-tracing in different directions on the sky in families of exact inhomogeneous cosmological solutions of Einstein's equations, in order to determine the redshifts and luminosity distances that observers in these space-times would infer for distant astrophysical objects. We compare the results of this procedure to the Hubble diagrams that would be obtained by direct use of the large-scale-averaged anisotropic cosmological models, and find that observables calculated in the averaged model closely agree with those obtained from ray-tracing in all cases where a statistical homogeneity scale exists. In contrast, we find that in cosmologies with spaces that contain no statistical homogeneity scale that Hubble diagrams inferred from the averaged cosmological model can differ considerably from those that observers in the space-time would actually construct. We hope that these results will be of use for understanding and interpreting recent observations that suggest that large-scale anisotropy may have developed in the late Universe.