基于改进最小二乘法拟合的车道线检测

提出了一种新的适用于自主驾驶系统的车道线检测——基于改进最小二乘法拟合的车道线检测。算法首先将摄像头采集的一帧帧图像,截取感兴趣的下半部分进行灰度变换,得到灰度图像;其次采取高通滤波,小波变换,来进行边缘增强与检测;之后采取最小阀值二值化得到二值化图像,采用最小二乘法拟合车道线;最后车道线的跟踪采用粒子滤波。实验表明,该算法简单、鲁棒性强,能准确地检测到车道标识线。     

车道线实时检测与偏离预警系统设计与研究

为保证交通安全,设计了一种基于单目视觉的车道偏离检测系统,利用 车载前视摄像 头获取图像,实时对动态图像进行处理,在驾驶员非主观偏离车道时进行报警。首先研 究了图像预处 理技术,包括灰度化、截取有效区域、滤波去噪、图像灰度增强、边缘检测和边缘修复功能 。其次对预处 理后的图像进行车道线检测,为有效识别具有车道线特征的图像,提出了一种改进的Hough 变换算法;对 没有车道线特征或车道线特征不明显的图像,采用了动态检测方法。在此基础上,提出 了一种车道线 纠正算法,即四点标定逆透视变换,将车道图像转化为俯视图,建立图像坐标系与实际俯视 坐标系之间的 关系,得到实际车辆的位置和偏移角度,判断该车辆的情况并作出指示。最后,在实际道路 中对设计中关 键技术以及整个系统进行了实验,大量实验结果表明,本文系统能在多种环境的道路中实现 车道线的准确识别和偏移判断,具有良好的实时性和鲁棒性。     

基于改进逆透视变换的车道线检测算法

针对智能车辆在不同环境条件下识别道路车道线出现偏移的问题,提出了一种基于改进逆透视变换的车道线检测算法.首先利用HSL和Lab融合模型提取车道线颜色特征,经过二值化处理后利用透视变换将图像转换为鸟瞰图,然后根据二值图建立直方图,进行车道线位置的粗定位.最终通过滑动窗口算法以及直线拟合等处理,实现对车道线的精准识别.通过实验结果对比分析,提出的车道线检测算法能够解决车道线识别偏移问题.     

一种基于多重衡量标准共检的车道线检测方法

针对当前传统车道线检测算法较复杂,适应性及鲁棒性较差,且直-弯车道线检测的准确度较差的情况,提出一种基于多重标准共检的车道线识别方法。对原图像进行灰度化处理后双重设定感兴趣区域(ROI),利用脊度量和Canny检测算子进行边缘特征的提取,双重标准确定直-弯车道线的分界线,利用直-弯车道线模型进行车道线检测。通过实际道路图像对所提方法进行实验验证,车道线检测准确度和拟合程度较高,场景适应能力强,且能够满足实际道路的需要。     

基于扩展卡尔曼滤波器的车道线检测算法

提出一种将道路结构模型信息与扩展卡尔曼滤波器(EKF,extended Kalman filter)相结合的车道线检测算法。基于扫描线的自适应边缘检测算子进行边缘点的检测,针对车道模型建立了适合算法的自定义参数空间,进行边缘点的投票,提取出候选车道线,解决了传统Hough变换中处理速度慢的问题。根据道路几何学和车辆动力学建立新的车道模型,增加了车道信息待估计的参数,并利用车道线的特征约束排除干扰线得到车道线的内边界,结合EKF对车道线边界点坐标参数进行跟踪估计,以保证算法的稳定性与鲁棒性。实验结果表明,本文算法能够处理绝大多数的复杂车道情况,在实时性、鲁棒性和检测率上都取得很好的效果。     

复杂环境下道路车道线识别算法的研究

针对不同光照、雨雪天、大雾天等恶劣环境下道路车道线识别难的问题,研究其识别算法。弱光照下,通过面积算子选取合适阈值进而实现边缘增强;夜间光照更弱的情况下,通过改进SUSAN算子实现夜间昏暗道路的边缘增强,解决了道路信息模糊、周围因素影响等造成的噪声干扰;强光照下,通过强光滤波算法可以消除伪边缘干扰,实现车道线的准确识别。雨雪天下,道路积水造成路面复杂,不能准确找到车道线特征点,通过建立路面积水反射模型,去除光的反射影响,增强路面和车道信息对比度,实现车道线信息的准确提取。大雾天,道路信息模糊不清,通过逆透视原理、差值分离建立道路识别模型,对道路特征进行加强分析,增强车道信息,提高识别效果。实验验证了所提出和改进的复杂环境下道路车道线识别算法的有效性,并且具有较强的鲁棒性和抗扰能力,可应用到智能交通系统中。     

基于参数优化支持向量机的火焰图像识别

图像型火灾探测的主要问题是关于火焰和干扰物的识别。通过提取火灾图像特征,利用支持向量机来进行识别。为提高火灾准确预报率,用参数优化后的支持向量机来预报。提出一种混沌粒子群算法对支持向量机进行参数优化。实验表明,改进的粒子群算法比传统方法的火灾准确预报率有大幅提高,可以进一步降低火灾探测系统的误报。     

基于改进蚁群边缘检测的车道线检测算法

文章提出了一种基于改进蚁群边缘检测的车道线检测算法。文章使用一种基于细菌趋化性的蚁群优化边缘检测算法对灰度图像进行边缘提取,该算法能够得到更好的边缘连续性和清晰性。通过寻找边缘点最多的一行作为感兴趣区域(Region of Interest,ROI)的上界,经过Hough变换检测直线特征。过滤离群值后通过最小二乘法拟合出车道线。利用真实道路驾驶视频对车道检测算法进行仿真实验,实验结果表明本算法有较好的鲁棒性和抗干扰能力。     

参数自适应混沌粒子群算法在盲源分离中的应用

独立分量分析(ICA)是盲源信号分离中应用最为广泛技术,其应用过程需要对目标函数进行优化,传统粒子算法(PSO)对其进行优化时,存在易陷入局部最优、稳定性差等缺陷,针对此问题,提出采用参数自适应混沌粒子群算法对ICA进行优化.首先采用对PSO的参数进行自适应调整,提高粒子的搜索能力,然后对粒子群进行混沌扰动,提高算法收敛速度.仿真结果表明,使用参数自适应混沌粒子群算法可以有效解决ICA的目标函数优化问题,极大提高了盲源信号的分离效果.     

基于视觉的车道线检测算法探讨

对基于视觉图像的车道线检测技术进行研究,针对智能车在视觉导航过程中车道线检测的鲁棒性问题提出一种改进算法。首先对道路图像进行中值滤波去噪,然后利用改进的OTSU算法分割图像,使目标区域更加清晰。划分图像中车道检测的感兴趣区域(ROI)对目标信息进行骨架处理,减少计算量提高实时性。最后运用改进的Hough变换计算车道标识线参数得到车道标识线方程,并进行车道线的拟合。     

Real-time road surface and semantic lane estimation using deep features

In this article, we present a robust real-time road surface and semantic lane marker estimation algorithm using the deconvolution neural network and extra trees-based decision forest. Our proposed algorithm simultaneously performs three environment perception tasks on colour and depth images, even under challenging conditions, namely road surface estimation, lane marker localization, and lane marker semantic information estimation. The lane marker semantic information implies the lane marker type such as dotted lane marker or continuous lane marker. The task of road surface estimation is performed with a trained deconvolution neural network. For the lane marker localization task, a scene-based extra trees regression framework is used to localize the lane markers in the given road. To account for the variations in the number and characteristics of the lane markers in the road scene, multiple regression models indexed with scene labels are used. The pre-defined scene labels correspond to the lane marker variations in a given scene, and an extra trees-based classification model is trained to estimate them from the road features. The road features, given as an input to the extra trees frameworks, are extracted from the road image using the trained filters of the deconvolution network. The proposed algorithm is validated using multiple acquired datasets. A comparative analysis is also conducted with baseline algorithms, and an improved accuracy is reported. Moreover, a detailed parameter evaluation is also performed. We report a computational time of 90 ms per frame.     

Quality-guided lane detection by deeply modeling sophisticated traffic context

Lane detection is a useful technique in modern autonomous vehicles systems, which assists vehicle to accurately localize itself according to detected road lines. Traditional methods leveraged edge detection and Hough transform based algorithms to plot lines along the detected lane. Noticeably, they did not take the informative feature road gradient into account. In addition, most previous deep learning-based algorithms consider lane detection as pixel-wise lane segmentation, where only fixed number of lanes can be detected. In order to solve these limitations, we propose a quality guided lane detection algorithm by modeling the sophisticated traffic context, where variable number of lanes can be satisfactorily handled. Specifically, we first leverage chessboard images for camera calibration to calculate correspondence between real world and image coordinate system. Subsequently, we capture image regions of interest that only contains lane information by leveraging the prior knowledge and image quality scores. Afterwards, we design an end-to-end two-stage CNN architecture for lane detection, where binary lane mask is utilized for lane matching. Comprehensive experiments have demonstrated that our proposed method can cope with variable number of lanes effectively.     

Moment-based multi-lane detection and tracking

Lane-detection methods are still facing robustness issues when confronted with challenging road surfaces, road markings and illumination conditions. Such combined challenges occur infrequently but are crucial for driving safety. Although advanced learning-based methods (using deep learning) demonstrate an impressive performance, they rely on plenty of training images for varying scenes and their performance is limited for scenes not covered by the training data. Also, multi-lane detection is indispensable for determining the exact position of both ego-car and surrounding vehicles as well as lane changing behavior on the road. In this paper we propose a new multi-lane detection algorithm, detecting all visible lane boundaries in front of the ego-car. In contrast to the Hough transforms often used for lane boundaries detection, our approach uses moments to calculate the deflection angles and the centroids of lane segments, achieving more precise lane boundaries. We propose a novel algorithm based on moments and Kalman filtering to achieve lane tracking. State-of-the-art neural-network-based methods are compared with the proposed method concretely. Experimental results show that our method outperforms other (recently published) multi-lane detection algorithms regarding detection rate as well as accuracy.     

A model-oriented road detection approach using fuzzy SVM

This paper presents an approach of model-oriented road detection based on trapezoidal model proposed by H. Jeong, et al and fuzzy Support Vector Machine (SVM). Firstly, the frames extracted from the video are preprocessed by Pulse Coupled Neural Network (PCNN), and then handled by Kalman filter and Expectation Maximization (EM) algorithms. Next, according to the road’s different feathers, using fuzzy algorithm chooses a corresponding SVM for further lane detection, and then using morphological filters obtains the final detecting result. For different types of roads, this method uses fuzzy algorithm to choose different SVMs. Furthermore, in preprocessing using PCNN removes the shadow in the road to reduce the effect of illumination variations. Experimental results show that our method can receive better lane detecting results than the trapezoidal model and BP proposed by H. Jeong, et al..     

三目标柯西粒子群算法的电力系统无功优化

通过建立有功网损最小、电压偏差最小和静态稳定电压裕度最大的三目标无功优化模型。提出柯西粒子群算法,并针对IEEE14节点系统进行三目标电力系统无功优化。当种群多样性较差时,通过对交叉的粒子进行柯西变异从而扩大搜索空间,提高种群多样性,防止出现过早的收敛,进而避免了算法陷入局部最优解的问题,同时也提高了收敛速度。通过数据测试和比较柯西粒子群算法在收敛速度、精度、全局搜索能力上均优于常规差分进化算法和常规粒子群算法。其结果验证了该模型和算法的有效性,为电力系统安全经济运行提供了参考。     

Synthesis of linear array using Taylor distribution and Particle Swarm Optimisation

In this article, non-uniformly excited linear arrays are optimised using Taylor distribution and classical particle swarm optimisation (CPSO) algorithm for obtaining desired equal side lobe level (SLL). Elements of the array are considered to be isotropic in nature with uniform interelement spacing. Excitation amplitudes of each element are taken as optimisation parameters. Taylor distribution defines the range of excitation amplitude in which CPSO algorithm searches for the optimum value of excitation amplitude, with the objective of obtaining desired equal SLL. The proposed method eliminates the initial randomness of defining search space for CPSO algorithm. Comparison with other methods has been made whenever possible. The results reveal that the proposed method can be used to obtain the desired SLL.     

Stereo vision-based road estimation assisted by efficient planar patch calculation

A robust and accurate road model estimation algorithm can greatly improve the performance of many Advanced Driver Assistance Systems applications such as lane detection, obstacle detection and road marking recognition. To estimate the road model, the proposed algorithm employs a stereo vision camera system. In this paper, local planar patches are efficiently estimated in the disparity domain rather than conventionally in the Euclidean domain. Then, the estimated planar patch orientations are integrated to the fitting stage, and orientation differences are minimized along with height differences. Moreover, patch orientation differences are exploited for weighting data points. Thus, outliers become insignificant in the fitting stage, and the road model is estimated robustly and accurately without any prior knowledge of any extrinsic camera parameters. Experiments have been carried out for a free space calculation application, and the road is segmented with a true positive rate (TPR) of 88 %.     

基于文化粒子群算法的广义OPM测向

在引入合成导向矢量和合成导向矩阵的基础上建立了一种更通用的阵列数据模型,提出了广义正交传播算子测向算法。该方法在不损失阵列孔径的前提下可有效估计相干信源和独立信源。为快速求解所提基于四阶累积量的广义OPM算法,在文化算法中使用和粒子群演进进化机制,提出了一种多维搜索的文化粒子群算法。Monte-Carlo仿真试验证明了所设计的测向算法可有效解决使用高阶累积量不能直接测相干信源的局限,所提算法在检测性能上与现有一些算法比较有较大的优势。     

基于小波分解的弯道识别技术

为了保障车辆安全有效的通过弯道,准确识别弯道曲率尤为重要。因此,文中提出一种基于小波分解的弯道识别技术,该算法通过车载CCD实时采集自车前方的车道线的图像信息,对采集的图像进行小波去噪以及小波边缘检测,最终准确辨识车道线,通过曲线拟合确定道路的曲率半径。经试验验证,该算法能准确辨识出弯道的曲率半径。