基于YOLOv5和LPRnet的车辆精细化识别研究

随着中国汽车数量的增加,市场上大规模车辆管理的复杂性也在增加。在采矿、建材运输等相对复杂的环境中,车辆的精细化管理变得更加困难,车牌识别技术在车辆管理中发挥着重要作用。传统车牌识别算法主要基于以下三个步骤:利用像素信息确定车牌的位置,将车牌标记从位置中分离出来,在定位的基础上进一步识别单个字符;这种方法可以处理生活中相对简单的车牌识别场景,但针对复杂的场景如矿山车辆、大部分车牌被灰尘覆盖、车牌变形等,传统车牌识别算法很难表现出很强的鲁棒性,并且经常识别错误。与传统的车牌检测方法相比,文章基于YOLOv5和LPRnet识别方法,利用几何校正原理改进算法,对车辆外观和车牌进行识别,实验结果充分体现了基于YOLOv5和LPRnet识别方法在复杂环境中精细化识别车辆的优势,车牌的综合识别率提高至95%。     

基于Haar-like特征和时空信息的交通状态区域检测

针对现有交通状态检测算法无法适应城市道路复杂交通的问题,提出一种新的基于Haar-like和时空信息的交通状态区域提取算法。该算法首先采用基于Haar-like特征的车辆检测算法、边缘检测法和帧差法分别提取路面车辆、空域纹理和时域纹理的三种信号;然后将提取到的三种信号进行统计分析,获得准确的交通状态区域。将该算法与基于车辆检测的交通状态检测算法和基于帧差法的交通状态检测算法在远距离小目标、遮挡车辆和混合交通的复杂交通场景中进行对比实验。实验结果表明,该算法在这些复杂交通场景中准确率平均达90.98%。     

融合多尺度信息的道路场景实时语义分割

道路场景语义分割是自动驾驶车辆实现环境感知的重要技术。针对道路场景实时语义分割中存在目标区域尺度不一、变化迅速的问题,在DABNet语义分割网络的基础上进行优化改进提出一种融合多尺度信息的道路场景实时语义分割网络。对于网络设计：首先引入带有自适应卷积核的卷积层优化DAB模块,自适应地引导网络学习最合适的特征图感受野,提高网络获取多尺度语义信息的能力;然后在编码阶段后引入了金字塔池化PSP模块来聚合特征图中不同尺度子区域的上下文信息,提高网络获取全局信息的能力。本网络提高了对大目标区域完整分割,避免小目标区域漏分割的能力,保证较高的道路场景实时语义分割精度。     

基于YOLOv5s和注意力机制的车辆检测改进算法

文中针对道路光线条件复杂、被遮挡目标物体特征不完整等问题,以 YOLOv5s 为车辆检测的基础模型,提出了一种融合 FunelCBAM 注意力机制的检测模型 FCBAMYOLOv5s。针对交通场景中车辆检测种类多、多尺度目标混杂、小目标易漏检等问题,文中还提出了一种融合加权双向跨尺度特征金字塔 BiFPN 与KLLoss损失函数的车辆检测方法。该方法可融合多尺度图像问题的特征,提高检测图像的鲁棒性,强化了网络对小物体的检测性能;然后在检测损失函数中融合 KLLoss,有效提高了模型的检测精度。实验结果表明,该方法的精度与实时性符合实际应用。     

基于多尺度小波边缘检测的车牌定位研究

车辆牌照的准确定位是车牌识别系统中的关键步骤,利用车牌区域丰富的边缘和纹理信息以及车牌自身的特征,提出一种基于多尺度小波边缘检测的车牌定位方法.该方法能够更好地解决在复杂背景和复杂光照下的车牌定位.首先用图像增强和多尺度小波算子提取出车牌图像的边缘,然后利用数学形态学和连通区域标记的方法对车牌进行初步特征提取去除伪车牌区域,最后采用水平垂直投影法进行车牌的精确定位.实验结果表明,该方法能够实现车牌的快速准确定位,对复杂背景下的车牌具有很好的鲁棒性和实时性.     

基于纹理特征与BP神经网络的运动车辆识别

在Gabor小波滤波器组与图像卷积值作为特征向量达到很高识别率的基础上,提出了一种特征值加权的Gabor小波纹理特征的提取方法.首先Gabor小波函数与纹理图像做卷积,然后加权处理尺度各不相同和方向各不相同的的卷积值,最后将均值和方差看作它们的特征向量,该方法使特征维数有所降低,并利用BP神经网络进行训练和仿真,实现运动车辆纹理图像的自动分类,达到运动图像的识别.实验结果表明此算法有效降低了图像的识别错误,增强了稳健性,对质量差的图像能够有效识别.     

野外场景分析与水体识别新方法的研究

 根据视觉认知规律,提出描述野外场景图像的三要素:地面、垂直物、天空,给出了单视角野外场景图像方程,通过采用基于独立图元函数码的三要素图像快速分类方法,实现对野外场景图像的分割,并且只在地面上去识别水体.本文重点讨论了野外场景中水体光照模型,分析了野外场景的相关物理特性,定义了水质参数、环境染色参数、图元、独立图元函数码、母图元等新概念,给出了野外场景分析与水体识别系统,提出基于位置、纹理、地质系数和环境染色等多特征参数的数据融合水体识别方法.实验表明该方法对于宽阔的道路场景分析和道路上的水体识别可以得到很好的效果.     

虚拟交通环境中的雨滴仿真

为实现虚拟交通场景中的降雨实时仿真,设计出一种基于OpenGL的降雨仿真模型。现有雨的仿真模型主要关注降雨过程,而在虚拟交通环境中,通常还需要对雨滴在挡风玻璃上的运动进行仿真。利用OpenGL将场景渲染到纹理,运用几何方法计算雨滴粒子并将其映射到网格化的虚拟挡风玻璃平面,采用贴纹理的方法将纹理映射到虚拟挡风玻璃平面,建立了雨滴在挡风玻璃平面的仿真模型。实践表明,该方法的时间开销与场景、光照等因素无关,仅与车辆挡风玻璃上的雨滴数量相关。该方法在普通PC实验平台上渲染场景的帧速率超过25帧／秒,能够成功实现雨滴的实时仿真。     

虚拟交通环境中的雨滴仿真

为实现虚拟交通场景中的降雨实时仿真,设计出一种基于OpenGL的降雨仿真模型.现有雨的仿真模型主要关注降雨过程,而在虚拟交通环境中,通常还需要对雨滴在挡风玻璃上的运动进行仿真.利用OpenGL将场景渲染到纹理,运用几何方法计算雨滴粒子并将其映射到网格化的虚拟挡风玻璃平面,采用贴纹理的方法将纹理映射到虚拟挡风玻璃平面,建立了雨滴在挡风玻璃平面的仿真模型.实践表明,该方法的时间开销与场景、光照等因素无关,仅与车辆挡风玻璃上的雨滴数量相关.该方法在普通PC实验平台上渲染场景的帧速率超过25帧/秒,能够成功实现雨滴的实时仿真.     

模拟驾驶器山区道路虚拟驾驶研究

针对山区道路模拟驾驶体验的特点,提出了模拟驾驶场景中预定义和路面感应计算相结合的实时控制虚拟车辆运行方法。在虚拟场景中预定义自走车辆运动轨迹,通过时间控制位置和方位的线性插补方法使其运行。对于驾驶车辆模型,文中用方向盘信号和车辆轮胎在路面的空间位置坐标实时计算车辆的位置和方位姿态,使车辆行驶与山区路面的坡度、弯道倾斜、粗糙度等状况等相吻合,增强了山区道路安全驾驶的真实体验感。     

机载激光雷达数据中道路中线的多尺度提取方法

机载激光雷达(LIDAR)技术的出现为道路特征的获取提供了新的途径.在分析现有道路提取现状的基础上,针对激光雷达数据的特点以及单一尺度下道路中线提取方法的不足,提出一种基于多尺度追踪的道路中线提取方法.该方法首先采用逐步约束的方法进行道路激光点的提取,包括高程约束、强度约束以及区域点密度和区域面积的约束等;然后基于道路点云生成的不同尺度距离影像的形态学细化结果,采用多尺度追踪的方法实现道路中线的提取,其中多尺度追踪方法由大尺度道路中线的迭代追踪以及小尺度道路中线的启发式追踪两部分组成.最后采用实地数据进行验证,结果表明:该方法能有效地从LIDAR点云中提取道路中线信息,并具有较好的精度.     

Toward Accurate Road Detection in Challenging Environments Using 3D Point Clouds

In this paper, we propose a novel method for road recognition using 3D point clouds based on a Markov random field (MRF) framework in unstructured and complex road environments. The proposed method is focused on finding a solution for an analysis of traversable regions in challenging environments without considering an assumption that has been applied in many past studies; that is, that the surface of a road is ideally flat. The main contributions of this research are as follows: (a) guidelines for the best selection of the gradient value, the average height, the normal vectors, and the intensity value and (b) how to mathematically transform a road recognition problem into a classification problem that is based on MRF modeling in spatial and visual contexts. In our experiments, we used numerous scans acquired by an HDL‐64E sensor mounted on an experimental vehicle. The results show that the proposed method is more robust and reliable than a conventional approach based on a quantity evaluation with ground truth data for a variety of challenging environments.     

基于道路信息的知识辅助空时自适应处理

主波束中的车辆回波信号会污染空时自适应处理(STAP)的训练样本,导致空时自适应处理时的目标自相消,引起漏警。针对这一问题,该文提出一种基于道路信息的知识辅助(KA)空时自适应处理方法。该方法首先根据主波束中道路相对于雷达的位置估计道路上车辆相对于雷达的径向速度,然后得到可能含有主波束车辆回波信号的距离-多普勒单元,接着根据训练样本与杂波导向矢量和主波束导向矢量的匹配程度判断这些训练样本是否包含主波束车辆回波信号,最后在进行空时自适应处理估计杂波协方差矩阵时剔除被主波束车辆回波信号污染的训练样本。理论分析及实验结果表明该方法可以提高道路密集环境中空时自适应处理的信杂噪比输出,改善空时自适应处理雷达的性能。     

Real-time background subtraction-based video surveillance of people by integrating local texture patterns

This paper presents a real-time surveillance system for detecting and tracking people, which takes full advantage of local texture patterns, under a stationary monocular camera. A novel center-symmetric scale invariant local ternary pattern feature is put forward to combine with pattern kernel density estimation for building a pixel-level-based background model. The background model is then used to detect moving foreground objects on every newly captured frame. A variant of a fast human detector that utilizes local texture patterns is adopted to look for human objects from the foreground regions, and it is assisted by a head detector, which is proposed to find in advance the candidate locations of human, to reduce computational costs. Each human object is given a unique identity and is represented by a spatio-color-texture object model. The real-time performance of tracking is achieved by a fast mean-shift algorithm coupled with several efficient occlusion-handling techniques. Experiments on challenging video sequences show that the proposed surveillance system can run in real-time and is quite robust in segmenting and tracking people in complex environments that include appearance changes, abrupt motion, occlusions, illumination variations and clutter.     

Vonn distribution of relative phase for statistical image modeling in complex wavelet domain

With the assumptions of Gaussian as well as Gaussian scale mixture models for images in wavelet domain, marginal and joint distributions for phases of complex wavelet coefficients are studied in detail. From these hypotheses, we then derive a relative phase probability density function, which is called Vonn distribution, in complex wavelet domain. The maximum-likelihood method is proposed to estimate two Vonn distribution parameters. We demonstrate that the Vonn distribution fits well with behaviors of relative phases from various real images including texture images as well as standard images. The Vonn distribution is compared with other standard circular distributions including von Mises and wrapped Cauchy. The simulation results, in which images are decomposed by various complex wavelet transforms, show that the Vonn distribution is more accurate than other conventional distributions. Moreover, the Vonn model is applied to texture image retrieval application and improves retrieval accuracy.     

3D surface profile equipment for the characterization of the pavement texture – TexScan

Loads from vehicles alter the functional and structural characteristics of road pavements that directly affect the loss of resistance of the pavement and the users’ comfort and safety. Those alterations require constant observation and analysis of an extensive area of road surface with high precision. For such it was developed a new scanning prototype machine capable of acquiring the 3D road surface data and characterize the road texture through two algorithms that allows calculate the Estimated Texture Depth (ETD) and Texture Profile Level (L) indicators. The experimental results obtained from nine road samples validate the developed algorithms for the texture analysis and showed good agreement between the scanning prototype equipment and the traditional Sand Patch Method.     

基于水平集方法的多源遥感数据融合及城区道路提取

该文发展了一种将多光谱遥感图像和雷达遥感图像进行特征融合,实现城区道路半自动提取的方法。通过水平集(Level Set, LS)快速行进 (Fast Marching, FM) 算法中的速度函数,将道路在多光谱图像中的光谱和纹理特征与其在雷达图像中后向散射和空间自相关尺度相结合。雷达图像中的道路信息弥补了多光谱图像中城市道路受高大建筑物、植被等地物阴影的覆盖而使图像容易断裂的缺点,而多光谱图像的道路信息则有助于降低雷达图像中噪声的干扰以及线性水体与道路的混淆。该文方法分别用于上海市不同区域、不同分辨率、不同极化方式的卫星遥感雷达图像(ERS-2, Radarsat-1 SAR)与陆地卫星多光谱图像(Landsat ETM+)的融合,进行道路信息的提取,取得了较好的效果。     

A survey of advanced ethernet forwarding approaches

The higher transmission rates currently supported by Ethernet lead to the possibility of expanding Ethernet beyondthe Local Area Network scope, bringing it into the core of large scale networks, of which a Metropolitan Area Network (MAN) is a significant example. However, originally Ethernet was not devised to scale in such environments: its design does not contemplate essential requirements of larger and more complex networks, such as the need for resilience, scalability, or even integrated control features. Furthermore, its spanning-tree based forwarding results in slow convergence and weak resource efficiency. Specifically focusing on Ethernet's forwarding behaviour, this survey covers solutions that enhance the Ethernet?s path computation, allowing it to scale in larger, more complex environments. General notions concerning the application of Ethernet in Metro areas are also provided, as a specific example of Ethernet's application in large scale networks.     

EMOS: Enhanced moving object detection and classification via sensor fusion and noise filtering

Dynamic object detection is essential for ensuring safe and reliable autonomous driving. Recently, light detection and ranging (LiDAR)-based object detection has been introduced and shown excellent performance on various benchmarks. Although LiDAR sensors have excellent accuracy in estimating distance, they lack texture or color information and have a lower resolution than conventional cameras. In addition, performance degradation occurs when a LiDAR-based object detection model is applied to different driving environments or when sensors from different LiDAR manufacturers are utilized owing to the domain gap phenomenon. To address these issues, a sensor-fusion-based object detection and classification method is proposed. The proposed method operates in real time, making it suitable for integration into autonomous vehicles. It performs well on our custom dataset and on publicly available datasets, demonstrating its effectiveness in real-world road environments. In addition, we will make available a novel three-dimensional moving object detection dataset called ETRI 3D MOD.     

The effect of speckle filtering on scale-dependent textureestimation of a forested scene

Spatial fluctuations in microwave backscatter may be an important piece of information in discriminating tree stands. However, the presence of speckle in synthetic aperture radar (SAR) image data is a barrier to the exploitation of image texture. The authors explored a new methodology that combines a recent adaptive speckle reduction algorithm by Lopes et al. (1990) with a generic texture estimation scheme. They investigated the claim that this filter was capable of preserving backscatter texture. To understand if speckle reduction was destroying backscatter texture, they compared the strength of the relationship between forest inventory parameters and image texture as a function of spatial scale for both filtered and unfiltered images. They used Radarsat Fine mode image data: single look resolution is approximately 8.5 m, and pixel spacing is 3 m. Their study area was northern Vancouver Island, B.C., on the west coast of Canada. For the unfiltered data, they found that the ability of image texture to predict the forest parameters decreased as the texture scale increased from 3 to 13 m, suggesting greater information content in the small scale texture. For the filtered data, this relationship was much weaker at small scales and was not a function of distance. Their results suggest that the speckle filter was not retaining small scale texture, which is consistent with the theoretical hypotheses underlying its multiplicative noise model. They also show that there is significant information in small state SAR image texture that may be used as an adjunct to other spatial information for discriminating tree stands in the temperate rain forest