基于卡尔曼滤波算法的城市交叉路口车辆检测及分类

为了向相关部门提供更多的过往车辆信息以满足道路交通的需求,设计了一个基于卡尔曼滤波算法的城市交叉路口车辆检测及分类系统,用于对过往的车辆进行检测、计数和分类.首先采用背景差分法和卡尔曼滤波算法对在检测区的车辆进行检测和跟踪;然后使用经过检测、处理的被测车辆图像触发距其最近的相机进行图形分割;最后,通过LDA分类器对分段车辆的几何形状及外观特征进行正确地分类.所提系统的有效性在摄取的3400帧视频序列上得到了验证,实验结果表明,系统的检测率可达97.44％,正确分类率可达88.0％,与先进的方法相比,取得了更好的检测性能.     

Monocular precrash vehicle detection: features and classifiers.

Robust and reliable vehicle detection from images acquired by a moving vehicle (i.e., on-road vehicle detection) is an important problem with applications to driver assistance systems and autonomous, self-guided vehicles. The focus of this work is on the issues of feature extraction and classification for rear-view vehicle detection. Specifically, by treating the problem of vehicle detection as a two-class classification problem, we have investigated several different feature extraction methods such as principal component analysis, wavelets, and Gabor filters. To evaluate the extracted features, we have experimented with two popular classifiers, neural networks and support vector machines (SVMs). Based on our evaluation results, we have developed an on-board real-time monocular vehicle detection system that is capable of acquiring grey-scale images, using Ford's proprietary low-light camera, achieving an average detection rate of 10 Hz. Our vehicle detection algorithm consists of two main steps: a multiscale driven hypothesis generation step and an appearance-based hypothesis verification step. During the hypothesis generation step, image locations where vehicles might be present are extracted. This step uses multiscale techniques not only to speed up detection, but also to improve system robustness. The appearance-based hypothesis verification step verifies the hypotheses using Gabor features and SVMs. The system has been tested in Ford's concept vehicle under different traffic conditions (e.g., structured highway, complex urban streets, and varying weather conditions), illustrating good performance.     

Road sign tracking for adaptive cruise control under nonlinear conditions

A vision-based system is described for adaptive cruise control to track road signs from within a moving vehicle. The proposed system has the standard architecture with a particle filter due to its robust tracking performance in a complex environment. In the case of tracking road signs in a real environment, it has great difficulty in predicting time series data by reason of its nonlinear characteristics. To overcome this problem, proposed is a state transition model to which the differences of affine parameters and a fuzzy-autoregressive model are applied. Also, to make an observation model, the Parzen window is used at a measurement step in the particle filter.     

一种基于视频的道路行人检测方法

提出了一种基于交通视频的道路行人检测方法。首先,采用具有自适应背景更新的背景差法提取运动目标。其次,利用行人的轮廓特征和行人在图像上的像素高度与实际距离的线性变化关系特征进一步分割行人目标,并依据行人位置特征对其做多帧匹配跟踪。最后,结合行人速度特征,实现行人目标检测。实验结果表明,该方法能准确地检测交通场景中出现的行人目标,有效地解决运动车辆的遮挡和光照等对行人目标检测的影响,具有良好的实时性和稳健性。     

Vehicle detection and inter-vehicle distance estimation using single-lens video camera on urban/suburb roads

This paper presents a driver assistance system for vehicle detection and inter-vehicle distance estimation using a single-lens video camera on urban/suburb roads. The task of vehicle detection on urban/suburb roads is more challenging due to their high scene complexity. In this work, the still area of frame inside the host vehicle is first removed using temporal differencing, followed by detecting vanishing point. Segmentation of road regions is then conducted using vanishing point and road’s edge lines. Shadow regions at the bottoms of vehicles verified using the HOG feature and an SVM classifier are utilized to detect vehicle positions. The distances between the host and its front vehicles are estimated based on the locations of detected vehicles and vanishing point. Experimental results show varied performance of vehicle detection with different scenes of urban/suburb roads and the detection rate can achieve up to 94.08%, indicating the feasibility of the proposed method.     

Efficient User Based Authentication Protocol for Location Based Services Discovery Over Road Networks

In road network, the decision accuracy of event message under location privacy-enhanced scheme, fast forwarding falsification message, and collusion attacks are all knotty problems that arise in event trust management. In this paper, we proposed protocol verification to check vehicles activity in privacy manner. We proposed a new method to adjusted vehicles speed which reduces the vehicle delay suffers from network gap problem. We established privacy preserving authentication protocol to verify vehicle activities in the term of privacy preserving manner. Vehicles moving trend, velocity differences, and distance differences are taken into consideration so, to maintain as many common users as possible to reduce the cost. The cost analysis and performance evaluation indicate that our frame-work can reduced cost factor and achieve good performance. The proposed model achieved reliably and efficiently with packet rate information. The evaluation experiments based on NS-3 to our improve user’s authenticated key establishment protocol has comparatively shorter time response, reduce cost, less packet lost information and enhanced privacy preservation compared with existing methods.     

Video traffic analysis using scene and vehicle models

This paper presents a complete system for analyzing a vehicle׳s behavior in the context of real-time traffic video surveillance applications. To obtain the best possible results, it is fundamental to exploit the scene characteristics and the predefined traffic rules. For that purpose, an initial training step is performed that involves estimating the geometrical structure of the road, i.e., the depth relative to the camera, the vanishing points, the road areas itself, the road decomposition (into normal and forbidden traffic lanes or areas), the traffic rules, the typical vehicle trajectories and speeds, and the lane-changing rules. This process leads to a scene model, which is used together with a simple vehicle geometrical model during the vehicle detection, tracking and trajectory estimation phases to improve the robustness against the perspective and occlusion effects. Shadow effects are also accounted for during the moving object detection phase. Finally, this spatio-temporal analysis is used to obtain information that concerns the vehicles׳ behaviors. Experiments show that the information obtained is reliable and can be computed in real time.     

Quaternion attitude and disturbance observer mass estimation with low-cost sensors for industrial vehicles with trailers

Information about the vehicle mass and ground slope is important for many assistance functions in road and logistics vehicles. In intralogistics, safe speed limits for tractors depend on both slope and trailer mass.This work presents an estimation procedure for the attitude of a vehicle and the mass of a trailer attached to it. The estimator works in two steps. First, the attitude is estimated using an extended Kalman filter based on acceleration and angular rate measurements complemented by a single track vehicle model. In the second step, this information is used together with velocity and motor torque data to estimate the trailer mass and friction coefficient. A Kalman filter based disturbance observer for parameter estimation is compared to a recursive least squares identification. The mass estimation is extended by a structural break test to detect sudden mass changes when hitching and unhitching trailers.Multiple variants of the estimation scheme are implemented on an intralogistics vehicle. The performance of the proposed attitude and mass estimation solutions is demonstrated in comparison to state of the art reference algorithms in a large number of experiments. Compared to state of the art estimators, the proposed estimator yields a median 54 % reduction of pitch estimation RMSE and 40 % reduction of the mass estimation error. The structural break detection is able to detect all instances of hitching and unhitching of trailers with few false positives.     

Vehicle detection using normalized color and edge map.

This paper presents a novel vehicle detection approach for detecting vehicles from static images using color and edges. Different from traditional methods, which use motion features to detect vehicles, this method introduces a new color transform model to find important "vehicle color" for quickly locating possible vehicle candidates. Since vehicles have various colors under different weather and lighting conditions, seldom works were proposed for the detection of vehicles using colors. The proposed new color transform model has excellent capabilities to identify vehicle pixels from background, even though the pixels are lighted under varying illuminations. After finding possible vehicle candidates, three important features, including corners, edge maps, and coefficients of wavelet transforms, are used for constructing a cascade multichannel classifier. According to this classifier, an effective scanning can be performed to verify all possible candidates quickly. The scanning process can be quickly achieved because most background pixels are eliminated in advance by the color feature. Experimental results show that the integration of global color features and local edge features is powerful in the detection of vehicles. The average accuracy rate of vehicle detection is 94.9%.     

一种稳健的视频SAR动目标阴影检测与跟踪处理方法

视频合成孔径雷达(VideoSAR)可获取观测场景高帧率图像序列,利用车辆等地面运动目标在图像序列中形成的阴影能够实现动目标状态感知,该方法具有定位精度高、检测概率高、无最小可检测速度限制等优点。针对视频SAR动目标阴影变化剧烈、信杂噪比低、多普勒模糊干扰等特有的图像特征,该文充分利用帧图像空间域和时间域信息,研究了视频SAR数据预处理、动目标阴影检测和视频SAR多目标跟踪方法。实测数据全流程处理结果验证了该文方法的有效性。     

Using uncorrupted neighborhoods of the pixels for impulsive noise suppression with ANFIS.

In this paper, a novel adaptive network-based fuzzy inference system (ANFIS)-based filter, ABF, is presented for the restoration of images corrupted by impulsive noise (IN). The ABF is performed in two steps. In the first step, impulse detection is realized by using statistical tools. In the second step, a nonlinear filtering scheme based on ANFIS is performed for only the corrupted pixels detected in the first step. To demonstrate the effectivity of ABF at the removal of high-level IN, extensive simulations were realized for ABF and nine different comparison filters. Empirical results indicate that the proposed filter achieves a better performance than the comparison filters in terms of noise suppression and detail preservation, even when the images are highly corrupted by IN.     

基于车底阴影的车前障碍物检测

基于计算机视觉的道路车辆检测是智能车辆导航的核心问题,实时准确地检测前方运动车辆的位置信息是车辆安全驾驶的前提。文中采用车底阴影的前方运动车辆检测算法,在基于车道线检测的基础上,通过车底阴影检测,实时准确地检测前方车辆。该算法通过使用Otsu阈值分割提取出车道线,生成AOI区域,再进行两次自适应阈值分割提取车底与路面的交线,从而检测出前方运动车辆。经过在高速公路上对运动车辆检测实验证明,该算法基本满足车辆安全驾驶的需求,并能准确实时地检测出前方运动车辆,进而减少了交通事故的发生。     

基于道路的运动车辆检测

基于图像的运动车辆检测是智能交通系统中一个重要而又困难的问题，它通常受到光照、路边摇晃树木、以及各种恶劣天气等的影响。提出了一种基于道路的车辆检测方法，在道路的入口处只利用背景差，对非入口处运动背景和不同道路上运动车辆的运动向量分别进行高斯建模，并利用贝叶斯准则和多帧信息来检测出运动车辆和运动背景。实验结果显示该方法取得了很好的效果。     

An ANFIS controller for the car-following collision preventionsystem

This paper presents a controller based on an adaptive network fuzzy inference system (ANFIS) for the car-following collision prevention system to nonlinearly control the speed of the vehicle. The distance and speed relative to the car in front are measured by a radar sensor and applied to the controller. The output acceleration or deceleration rate of the controller is based on the characteristics of the vehicles. The initial input and output membership functions and 25 rules of ANFIS are constructed by a fuzzy inference system (FIS). The design method of the reference signals, which is used to update on-line the consequent parameters of ANFIS according to recursive least square (RLS) algorithm, are proposed. The presented ANFIS controller can solve the problems of the oscillations for final distance between the leading vehicle (LV) and the following vehicle (FV) and relative speed. The required processing time to achieve safe distance between the LV and the FV is about 7-8 s, which is faster than the other models. The ANFIS controller of the car-following collision prevention system proposed in this paper can provide a safe, reasonable, and comfortable drive     

State Machine and Downhill Simplex Approach for Vision‐Based Nighttime Vehicle Detection

In this paper, a novel vision‐based nighttime vehicle detection approach is presented, combining state machines and downhill simplex optimization. In the proposed approach, vehicle detection is modeled as a sequential state transition problem; that is, vehicle arrival, moving, and departure at a chosen detection area. More specifically, the number of bright pixels and their differences, in a chosen area of interest, are calculated and fed into the proposed state machine to detect vehicles. After a vehicle is detected, the location of the headlights is determined using the downhill simplex method. In the proposed optimization process, various headlights were evaluated for possible headlight positions on the detected vehicles; allowing for an optimal headlight position to be located. Simulation results were provided to show the robustness of the proposed approach for nighttime vehicle and headlight detection.     

Analysis of Acoustic Signatures from Moving Vehicles Using Time-Varying Autoregressive Models

Time-varying autoregressive (TVAR) modeling approach for the analysis of acoustic signatures from moving vehicles is presented in this paper. Acoustic signatures from moving vehicles are nonstationary, and features extracted under the stationary assumption often result unsatisfactory performance. In TVAR modeling approach, the time-varying parameters are expanded as a linear combination of deterministic time functions. In this paper, the TVAR parameters are expanded by a low-order discrete cosine transform (DCT), since DCT is known to be close to the optimal Kahrunen-Loève transform when the signal is Markov. The maximum likelihood estimation and order selection in TVAR models are also discussed. Many attributes of vehicle activities, such as vehicle type, engine speed, loading, road condition, etc., may be inferred from the estimated model parameters. The performance of the TVAR modeling approach is tested with both synthetic and real acoustic signatures. A synthetic signal containing multiple time-varying sinusoids are used to compare the performances in the estimation of time-frequency distribution with other approaches. In the experiment with acoustic signatures from moving vehicles, it is shown that the TVAR models can be effectively used to determine vehicle activities and types at close range and cruising speed.     

山区弯道智能会车提示系统的设计

介绍了以微处理器STC89C52作为核心控制芯片和单片射频收发器nRF905芯片组成的山区弯道智能会车提示系统的特点和工作原理,给出了系统的软硬件实现方案。通过实验考虑会车所能出现的各种状况得到的实验结果表明该系统车辆检测率较高,数据显示准确,达到了山区弯道智能会车提示系统的要求,能够确保山区弯道会车安全,降低事故率。     

On-line vehicle and pedestrian detections based on sign pattern

Real time detection methods of moving vehicles and pedestrians for navigation of the mobile robot are proposed. The method is based on a locomotion strategy, viz. signature-based stereotype motion. Signature of the moving vehicle is the shadow underneath the vehicle which is darker than any other parts of the asphalt paved road. Signature of the pedestrian is rhythm of walking. Rhythm of walking is unique to the pedestrian, and not influenced by time, weather, sunlight, shadow, and distance. Moreover, it is independent from clothes the pedestrian puts on. The result of experiments verify the validity of the methods     

Efficient method of moving shadow detection and vehicle classification

Moving shadow detection and removal from the extracted foreground regions of video frames, aim to limit the risk of misconsideration of moving shadows as a part of moving objects. This operation thus enhances the rate of accuracy in detection and classification of moving objects. With a similar reasoning, the present paper proposes an efficient method for the discrimination of moving object and moving shadow regions in a video sequence, with no human intervention. Also, it requires less computational burden and works effectively under dynamic traffic road conditions on highways (with and without marking lines), street ways (with and without marking lines). Further, we have used scale-invariant feature transform-based features for the classification of moving vehicles (with and without shadow regions), which enhances the effectiveness of the proposed method. The potentiality of the method is tested with various data sets collected from different road traffic scenarios, and its superiority is compared with the existing methods.     

高分辨力极化SAR图像城市区域车辆目标检测

研究基于高分辨力极化合成孔径雷达(SAR)图像的城市区域车辆目标自动检测方法。城市区域具有复杂的地物,这给在城市区域进行车辆目标检测工作带来困难。首先采用Freeman-Durden分解、极化白化滤波器(PWF)和相似性参数3种方法来提取图像数据的极化信息;在此基础上,采用深度卷积神经网络来对车辆目标和其他地物进行二分类,实现对城市区域车辆目标的检测。基于机载分米级分辨力极化SAR数据的实验结果验证了该方法的有效性,在较低的虚警率下获得较高的检测率。将3种极化特征融合时,能够在虚警率为2.82%时获得95.65%的检测率。