Depth-Guided Vision Transformer With Normalizing Flows for Monocular 3D Object Detection

Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB images.Depth-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion learning.However,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with convolutions.Different from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth information.Then we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each other.Furthermore,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input tokens.Our method is the first Swin-Transformer-based backbone architecture for monocular 3D object detection.The experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.

Research on Vehicle Anti-collision Technique Based on Monocular Vision

Vehicle anti-collision technique is a hot topic in the research area of Intelligent Transport System. The research on preceding vehicles detection and the distance measurement, which are the key techniques, makes great contributions to safe-driving. This paper presents a method which can be used to detect preceding vehicles and get the distance between own car and the car ahead. Firstly, an adaptive threshold method is used to get shadow feature, and a shadow!area merging approach is used to deal with the distortion of the shadow border. Region of interest(ROI) is obtained using shadow feature. Then in the ROI, symmetry feature is analyzed to verify whether there are vehicles and to locate the vehicles. Finally, using monocular vision distance measurement based on camera interior parameters and geometrical reasoning, we get the distance between own car and the preceding one. Experimental results show that the proposed method can detect the preceding vehicle effectively and get the distance between vehicles accurately.

Autonomous Landing of Small Unmanned Aerial Rotorcraft Based on Monocular Vision in GPS-denied Area

Focusing on the low-precision attitude of a current small unmanned aerial rotorcraft at the landing stage, the present paper proposes a new attitude control method for the GPS-denied scenario based on the monocular vision. Primarily, a robust landmark detection technique is developed which leverages the well-documented merits of supporting vector machines(SVMs)to enable landmark detection. Then an algorithm of nonlinear optimization based on Newton iteration method for the attitude and position of camera is put forward to reduce the projection error and get an optimized solution. By introducing the wavelet analysis into the adaptive Kalman filter, the high frequency noise of vision is filtered out successfully. At last, automatic landing tests are performed to verify the method s feasibility and effectiveness.

Mobile Robot Hierarchical Simultaneous Localization and Mapping Using Monocular Vision

A hierarchical mobile robot simultaneous localization and mapping (SLAM) method that allows us to obtain accurate maps was presented. The local map level is composed of a set of local metric feature maps that are guaranteed to be statistically independent. The global level is a topological graph whose arcs are labeled with the relative location between local maps. An estimation of these relative locations is maintained with local map alignment algorithm, and more accurate estimation is calculated through a global minimization procedure using the loop closure constraint. The local map is built with Rao-Blackwellised particle filter (RBPF), where the particle filter is used to extending the path posterior by sampling new poses. The landmark position estimation and update is implemented through extended Kalman filter (EKF). Monocular vision mounted on the robot tracks the 3D natural point landmarks, which are structured with matching scale invariant feature transform (SIFT) feature pairs. The matching for multi-dimension SIFT features is implemented with a KD-tree in the time cost of O(lbN). Experiment results on Pioneer mobile robot in a real indoor environment show the superior performance of our proposed method.

Monocular Vision Based Boundary Avoidance for Non-Invasive Stray Control System for Cattle: A Conceptual Approach

Building fences to manage the cattle grazing can be very expensive;cost inefficient. These do not provide dynamic control over the area in which the cattle are grazing. Existing virtual fencing techniques for the control of herds of cattle, based on polygon coordinate definition of boundaries is limited in the area of land mass coverage and dynamism. This work seeks to develop a more robust and an improved monocular vision based boundary avoidance for non-invasive stray control system for cattle, with a view to increase land mass coverage in virtual fencing techniques and dynamism. The monocular vision based depth estimation will be modeled using concept of global Fourier Transform (FT) and local Wavelet Transform (WT) of image structure of scenes (boundaries). The magnitude of the global Fourier Transform gives the dominant orientations and textual patterns of the image;while the local Wavelet Transform gives the dominant spectral features of the image and their spatial distribution. Each scene picture or image is defined by features v, which contain the set of global (FT) and local (WT) statistics of the image. Scenes or boundaries distances are given by estimating the depth D by means of the image features v. Sound cues of intensity equivalent to the magnitude of the depth D are applied to the animal ears as stimuli. This brings about the desired control as animals tend to move away from uncomfortable sounds.

AB012. The effects of monocular deprivation do not accumulate across days in adults with normal vision

Background:We investigate whether changes in visual plasticity induced by monocular deprivation can be maintained across multiple days.It has been known that monocular deprivation strengthens the deprived eye in adults with normal vision for a short period of time(30-60 minutes).This has been shown through a variety of visual tasks such as binocular combination and rivalry.Methods:Ten subjects were recruited and patched for five consecutive days for two hours.We used a binocular phase combination task to measure the subjects’sensory eye balances.We initially measured their baseline of sensory eye balance,patched their dominant eye,and then conducted post-patching measurements at 0,3,6,12,24 and 48 minutes after patching.Results:We performed a 2-way ANOVA(Before vs.after patching×Day);we found that although the effect of monocular deprivation on the deprived eye was significant,F(1,9)=17.32,P=0.002,the effect of Day was not.Conclusions:Hence we found no accumulation of the patching effect across five days in healthy adults.This suggests that the degree of remnant neural plasticity in adult primary visual cortex may be too limited to be exploited therapeutically.

Mobile Robot Localization and Navigation System Based on Monocular Vision

A system for mobile robot localization and navigation was presented.With the proposed system,the robot can be located and navigated by a single landmark in a single image.And the navigation mode may be following-track,teaching and playback,or programming.The basic idea is that the system computes the differences between the expected and the recognized position at each time and then controls the robot in a direction to reduce those differences.To minimize the robot sensor equipment,only one omnidirectional camera was used.Experiments in disturbing environments show that the presented algorithm is robust and easy to implement,without camera rectification.The rootmean-square error(RMSE) of localization is 1.4,cm,and the navigation error in teaching and playback is within 10,cm.

Monocular vision based navigation method of mobile robot

A trajectory tracking method is presented for the visual navigation of the monocular mobile robot.The robot move along line trajectory drawn beforehand,recognized and stop on the stop-sign to finish special task.The robot uses a forward looking colorful digital camera to capture information in front of the robot,and by the use of HSI model partition the trajectory and the stop-sign out.Then the "sampling estimate" method was used to calculate the navigation parameters.The stop-sign is easily recognized and can identify 256 different signs.Tests indicate that the method can fit large-scale intensity of brightness and has more robustness and better real-time character.

基于Vision Transformer的小麦病害图像识别算法

小麦白粉病、赤霉病和锈病是危害小麦产量的三大病害。为提高小麦病害图像的识别准确率,构建一种基于Vision Transformer的小麦病害图像识别算法。首先,通过田间拍摄的方式收集包含小麦白粉病、赤霉病和锈病3种病害在内的小麦病害图像,并对原始图像进行预处理,建立小麦病害图像识别数据集;然后,基于改进的Vision Transformer构建小麦病害图像识别算法,分析不同迁移学习方式和数据增强对模型识别效果的影响。试验可知,全参数迁移学习和数据增强能明显提高Vision Transformer模型的收敛速度和识别精度。最后,在相同时间条件下,对比Vision Transformer、AlexNet和VGG16算法在相同数据集上的表现。试验结果表明,Vision Transformer模型对3种小麦病害图像的平均识别准确率为96.81%,相较于AlexNet和VGG16模型识别准确率分别提高6.68%和4.94%。

细粒度图像分类上Vision Transformer的发展综述

细粒度图像分类(fine-grained image classification,FGIC)一直是计算机视觉领域中的重要问题。与传统图像分类任务相比,FGIC的挑战在于类间对象极其相似,使任务难度进一步增加。随着深度学习的发展,Vision Transformer(ViT)模型在视觉领域掀起热潮,并被引入到FGIC任务中。介绍了FGIC任务所面临的挑战,分析了ViT模型及其特性。主要根据模型结构全面综述了基于ViT的FGIC算法,包括特征提取、特征关系构建、特征注意和特征增强四方面内容,对每种算法进行了总结,并分析了它们的优缺点。通过对不同ViT模型在相同公用数据集上进行模型性能比较,以验证它们在FGIC任务上的有效性。最后指出了目前研究的不足,并提出未来研究方向,以进一步探索ViT在FGIC中的潜力。

基于Vision Transformer和迁移学习的家庭领域哭声识别

针对SVM等传统机器学习算法准确率低和当前使用CNN处理家庭领域哭声识别在不同婴儿间出现泛化能力差的问题,提出了一种基于Vision Transformer和迁移学习的婴儿哭声音频分类算法。首先,为实现数据集样本的扩增,采用了包括梅尔频谱转换和数据增强的数据预处理技术,进而达到了增强模型鲁棒性的目的。而后,在微调后的Vision Transformer模型上进行迁移学习训练,同时,训练过程中利用了LookAhead优化器来不断调整模型参数以避免过拟合,最终实验实现了对婴儿哭声音频的自动分类。实验结果表明,本实验模型相比其他深度学习模型具有更高的精确率和更快的收敛速度,同时还能有效地学习到婴儿哭声中更具区分性的特征。可以在新生儿监护、听力筛查和异常检测等领域中发挥重要作用。

Artificial hawk-eye camera for foveated, tetrachromatic, and dynamic vision

With the rapid development of drones and autonomous vehicles, miniaturized and lightweight vision sensors that can track targets are of great interests. Limited by the flat structure, conventional image sensors apply a large number of lenses to achieve corresponding functions, increasing the overall volume and weight of the system.

基于Vision Transformer和卷积注入的车辆重识别

针对车辆重识别中提取特征鲁棒性不高的问题,本文提出基于Vision Transformer的车辆重识别方法。首先,利用注意力机制提出目标导向映射模块,并结合辅助信息嵌入模块,抑制由不同视角、相机拍摄及无效背景引入的噪声。其次,以Vision Transformer远距离建模能力为基础提出通道感知模块,通过并行设计模型能够同时获取图像块之间和图像通道之间的特征,在关注图像块之间关联的基础上,进一步构建通道之间的关联。最后,利用卷积神经网络的局部归纳偏置,将全局特征向量输入到卷积注入模块中进行细化,并与全局特征联合优化,以构建鲁棒性的车辆特征。为了验证提出方法的有效性,在Ve⁃Ri776、VehicleID和VeRi-Wild数据集上分别进行了实验验证。实验结果证明,本文的方法取得了良好的效果。

FPGA and computer-vision-based atom tracking technology for scanning probe microscopy

Atom tracking technology enhanced with innovative algorithms has been implemented in this study,utilizing a comprehensive suite of controllers and software independently developed domestically.Leveraging an on-board field-programmable gate array(FPGA)with a core frequency of 100 MHz,our system facilitates reading and writing operations across 16 channels,performing discrete incremental proportional-integral-derivative(PID)calculations within 3.4 microseconds.Building upon this foundation,gradient and extremum algorithms are further integrated,incorporating circular and spiral scanning modes with a horizontal movement accuracy of 0.38 pm.This integration enhances the real-time performance and significantly increases the accuracy of atom tracking.Atom tracking achieves an equivalent precision of at least 142 pm on a highly oriented pyrolytic graphite(HOPG)surface under room temperature atmospheric conditions.Through applying computer vision and image processing algorithms,atom tracking can be used when scanning a large area.The techniques primarily consist of two algorithms:the region of interest(ROI)-based feature matching algorithm,which achieves 97.92%accuracy,and the feature description-based matching algorithm,with an impressive 99.99%accuracy.Both implementation approaches have been tested for scanner drift measurements,and these technologies are scalable and applicable in various domains of scanning probe microscopy with broad application prospects in the field of nanoengineering.

基于改进Vision Transformer的蝴蝶品种分类

蝴蝶作为一种品类繁多且相似度极高的生物,具有重要的生态环境感知功能。不同品类蝴蝶对环境变化的敏感程度各不相同,因此在农学与生物学研究方向上对蝴蝶的研究具有十分重要的意义。近年来,计算机视觉技术的飞速发展为快速识别蝴蝶品类提供了强有力的技术支持。然而,传统的Vision Transformer模型存在着一些问题,例如缺乏卷积所具有的归纳偏置、局部信息提取能力不足、容易过拟合以及在小数据集上训练缓慢等。针对这些问题,提出了一种基于Vision Transformer改进的蝴蝶分类算法。引入VanillaNet卷积结构,并通过全局注意力机制改进了Class token的更新方式。实验结果显示,在100类蝴蝶数据集上,改进后的Vision Transformer模型的Top-1准确率达到了94.87%,比改进前提升了28.9%。在使用改进的Class token后,算法的Top-1准确率进一步提升至96.64%,相比改进前提升了30.44%。与原网络模型相比,改进后的模型更适用于蝴蝶品种分类任务。

Development and validation of a novel questionnaire regarding vision screening among preschool teachers in Malaysia

AIM:To develop and evaluate the validity and reliability of a knowledge,attitude,and practice questionnaire related to vision screening(KAP-VST)among preschool teachers in Malaysia.METHODS:The questionnaire was developed through a literature review and discussions with experts.Content and face validation were conducted by a panel of experts(n=10)and preschool teachers(n=10),respectively.A pilot study was conducted for construct validation(n=161)and test-retest reliability(n=60)of the newly developed questionnaire.RESULTS:Based on the content and face validation,71 items were generated,and 68 items were selected after exploratory factor analysis.The content validity index for items(I-CVI)score ranged from 0.8-1.0,and the content validity index for scale(S-CVI)/Ave was 0.99.Internal consistency was KR^(2)0=0.93 for knowledge,Cronbach’s alpha=0.758 for attitude,and Cronbach’s alpha=0.856 for practice.CONCLUSION:The KAP-VST is a valid and reliable instrument for assessing knowledge,attitude,and practice in relation to vision screening among preschool teachers in Malaysia.

Collaborative positioning for swarms:A brief survey of vision,LiDAR and wireless sensors based methods

As positioning sensors,edge computation power,and communication technologies continue to develop,a moving agent can now sense its surroundings and communicate with other agents.By receiving spatial information from both its environment and other agents,an agent can use various methods and sensor types to localize itself.With its high flexibility and robustness,collaborative positioning has become a widely used method in both military and civilian applications.This paper introduces the basic fundamental concepts and applications of collaborative positioning,and reviews recent progress in the field based on camera,LiDAR(Light Detection and Ranging),wireless sensor,and their integration.The paper compares the current methods with respect to their sensor type,summarizes their main paradigms,and analyzes their evaluation experiments.Finally,the paper discusses the main challenges and open issues that require further research.

Exploring Deep Learning Methods for Computer Vision Applications across Multiple Sectors:Challenges and Future Trends

Computer vision(CV)was developed for computers and other systems to act or make recommendations based on visual inputs,such as digital photos,movies,and other media.Deep learning(DL)methods are more successful than other traditional machine learning(ML)methods inCV.DL techniques can produce state-of-the-art results for difficult CV problems like picture categorization,object detection,and face recognition.In this review,a structured discussion on the history,methods,and applications of DL methods to CV problems is presented.The sector-wise presentation of applications in this papermay be particularly useful for researchers in niche fields who have limited or introductory knowledge of DL methods and CV.This review will provide readers with context and examples of how these techniques can be applied to specific areas.A curated list of popular datasets and a brief description of them are also included for the benefit of readers.

Clinical usefulness of the baby vision test in young children and its correlation with the Snellen chart

AIM:To investigate the efficacy of a new visual acuity(VA)screening method,the baby vision test for young children.METHODS:A total 105 eyes of 65 children aged 2-8y were included in the study.Acuity testing was conducted using a standardized recognition acuity chart(Snellen visual chart:at 3 m)and the baby vision model assessment.The baby vision device includes a screen,a near infrared camera and a computer.Children were seated at a measured distance of 33-40 cm from a display for testing.VA was estimated according to the highest resolution the children could follow.Decimal VA data were converted to logarithm of the minimum angle of resolution(logMAR)for statistical analysis.The VA results for each child were recorded and analyzed for consistency.RESULTS:The mean VA measured using the Snellen visual chart was 0.62±0.32,and that assessed using the baby vision test was 0.66±0.27.The 95%limit of agreement was-0.609 to 0.695,with 95.2%(100/105)plots within the 95%limits of agreement.VA values of the baby vision test were significantly correlated with those of the Snellen chart(R=0.274,P=0.005).CONCLUSION:The baby vision test can be used as a relatively reliable method for estimating VA in young children.This new acuity assessment might be a valid predictor of optotype-measured acuity later in preverbal children.

面向Vision Transformer模型的剪枝技术研究

本文针对Vision Transformer(ViT)模型开展剪枝技术研究,探索了多头自注意力机制中的QKV(Query、Key、Value)权重和全连接层(Fully Connected,FC)权重的剪枝问题。针对ViT模型本文提出了3组剪枝方案:只对QKV剪枝、只对FC剪枝以及对QKV和FC同时进行剪枝,以探究不同剪枝策略对ViT模型准确率和模型参数压缩率的影响。本文开展的研究工作为深度学习模型的压缩和优化提供了重要参考,对于实际应用中的模型精简和性能优化具有指导意义。