A vehicle detection and tracking method for traffic video based on faster R-CNN

Multimedia Tools and Applications - In this paper we present a vehicle detection and tracking method for traffic video analysis based on deep learning technology. Indeed, with the rapid development...     

视频流量中基于小波的Hurst参数估计研究

小波变换具有低计算量和尺度不变性等特点,广泛应用于Hurst参数的估计中.针对H.263编码的视频序列进行实验,应用基于小波变换的Hurst参数估计,并与R/S分析法进行比较,两者产生的Hurst参数不同.实验结果的分析表明,由于视频流量中存在长相关和尺度指数的可变性,基于小波的估计方法存在不可靠性.     

基于监控视频的运动车辆检测优化方法

为满足实时性处理需要,提出了一种基于监控视频的运动车辆检测优化方法.运用自适应ROI(region of interest)提取算法,在获取可能出现运动车辆的区域后,基于帧间差分法与分块处理思想,提出了一种改进的背景提取算法,有效地提取运动目标区城.对提取的多目标运动区域进行分离,分别提取可能是车辆的区域后,提出了一种简单、快捷的阴影去除算法,有效地去除阴影,获得准确的运动目标区城.实验结果表明,该方法速度快、准确率高,能很好地满足实时性要求.     

Real-time multiple vehicle detection and tracking from a moving vehicle

Abstract. A real-time vision system has been developed that analyzes color videos taken from a forward-looking video camera in a car driving on a highway. The system uses a combination of color, edge, and motion information to recognize and track the road boundaries, lane markings and other vehicles on the road. Cars are recognized by matching templates that are cropped from the input data online and by detecting highway scene features and evaluating how they relate to each other. Cars are also detected by temporal differencing and by tracking motion parameters that are typical for cars. The system recognizes and tracks road boundaries and lane markings using a recursive least-squares filter. Experimental results demonstrate robust, real-time car detection and tracking over thousands of image frames. The data includes video taken under difficult visibility conditions. Received: 1 September 1998 / Accepted: 22 February 2000     

公路视频实时车辆检测分类与车流量统计算法

公路视频实时车辆检测分类与车流量统计是计算机视觉领域的一个经典问题。传统设置检测带法,易漏检复检,自动化性不好。基于深度网络的one-stage算法实时性好,但是经常会把变化的背景、运动的非车辆物体纳入其中,同时对光照变化敏感,夜间分类效果不好。因此,提出采用one-stage做目标检测,并不直接获取分类结果,而是根据标注框将物体切割出来,去除背景,提升抗背景扰动性能和分类效果;再送入一个经过迁移学习的浅层神经网络;将分类输出和目标检测网络的位置输出合并送入一个全图匹配算法,进行车流量统计。该方法在保障实时性的同时降低了漏检和复检率。     

基于边界矢量场的视频运动目标检测与跟踪

提出了一种新的视频运动目标检测与跟踪方法.该方法首先采用自适应帧间差分法对视频序列图像的运动目标进行粗检测,进而采用BVF(边界矢量场)Snake方法准确地检测出运动目标轮廓;其次获得轮廓质心后,对传统的α-β-γ滤波器进行了改进,实现对运动目标的实时跟踪;最后根据预测的质心位置来自动完成下一帧轮廓初始化.实验结果表明,该方法具有良好的实时性和准确性.     

Moving vehicle detection and tracking at roundabouts using deep learning with trajectory union

Multimedia Tools and Applications - The number of vehicles and turning movements at roundabouts provide important information for planning, design and operational analysis of roundabouts. The...     

交通运动目标检测、跟踪及轨迹生成研究

提出一种基于视频的车辆检测,跟踪和轨迹生成算法.该算法由改进的车辆检测方法,快速跟踪算法和新的车辆轨迹生成算法3部分组成.基于区域和车辆间的相互关系,在视频序列中,车辆被视为可自主运动团块.在对该团块实现有效跟踪及获取运动轨迹的基础上,运用相关的数学手段可获得团块其它运动信息.在高速公路上的实验结果表明,该车辆检测,跟踪算法切实可行,轨迹生成技术可用于交通流检测.     

Face detection and tracking in a video by propagating detection probabilities

This paper presents a new probabilistic method for detecting and tracking multiple faces in a video sequence. The proposed method integrates the information of face probabilities provided by the detector and the temporal information provided by the tracker to produce a method superior to the available detection and tracking methods. The three novel contributions of the paper are: 1) Accumulation of probabilities of detection over a sequence. This leads to coherent detection over time and, thus, improves detection results. 2) Prediction of the detection parameters which are position, scale, and pose. This guarantees the accuracy of accumulation as well as a continuous detection. 3) The representation of pose is based on the combination of two detectors, one for frontal views and one for profiles. Face detection is fully automatic and is based on the method developed by Schneiderman and Kanade (2000). It uses local histograms of wavelet coefficients represented with respect to a coordinate frame fixed to the object. A probability of detection is obtained for each image position and at several scales and poses. The probabilities of detection are propagated over time using a Condensation filter and factored sampling. Prediction is based on a zero order model for position, scale, and pose; update uses the probability maps produced by the detection routine. The proposed method can handle multiple faces, appearing/disappearing faces as well as changing scale and pose. Experiments carried out on a large number of sequences taken from commercial movies and the Web show a clear improvement over the results of frame-based detection (in which the detector is applied to each frame of the video sequence).     

Exploiting temporal and spatial constraints in traffic sign detection from a moving vehicle

This paper addresses detection, tracking and recognition of traffic signs in video. Previous research has shown that very good detection recalls can be obtained by state-of-the-art detection algorithms. Unfortunately, satisfactory precision and localization accuracy are more difficultly achieved. We follow the intuitive notion that it should be easier to accurately detect an object from an image sequence than from a single image. We propose a novel two-stage technique which achieves improved detection results by applying temporal and spatial constraints to the occurrences of traffic signs in video. The first stage produces well-aligned temporally consistent detection tracks by managing many competing track hypotheses at once. The second stage improves the precision by filtering the detection tracks by a learned discriminative model. The two stages have been evaluated in extensive experiments performed on videos acquired from a moving vehicle. The obtained experimental results clearly confirm the advantages of the proposed technique.     

基于车载视频的压线检测与车道偏移预警

车辆压线检测系统可对车辆运行过程中发生的压线行为进行检测并做出警告,避免由于司机注意不集中、疲劳驾驶、驾驶陋习等原因导致车辆偏移而造成交通事故。对此提出一种基于车载视频的压线检测与车道偏移预警方法。首先,利用合成数据方法构造丰富多样的压线检测数据集;然后,结合图像语义分割方法完成车道线检测;最后,利用当前车道双边线多个几何参数对车辆压线行为作出检测并做出预警。实验表明,单帧平均压线检测准确率为93. 7%,耗时78 ms,车道偏移预警召回率为93. 5%,该方法具备一定的实际应用价值。     

Efficient multi-camera vehicle detection,tracking, and identification in a tunnel surveillance application

This paper presents an integrated solution for the problem of detecting, tracking and identifying vehicles in a tunnel surveillance application, taking into account practical constraints including real-time operation, poor imaging conditions, and a decentralized architecture. Vehicles are followed through the tunnel by a network of non-overlapping cameras. They are detected and tracked in each camera and then identified, i.e. matched to any of the vehicles detected in the previous camera (s). To limit the computational load, we propose to reuse the same set of Haar-features for each of these steps. For the detection, we use an AdaBoost cascade. Here we introduce a composite confidence score, integrating information from all stages of the cascade. A subset of the features used for detection is then selected, optimizing for the identification problem. This results in a compact binary ‘vehicle fingerprint’, requiring minimal bandwidth.Finally, we show that the same subset of features can also be used effectively for tracking. This Haar-features based ‘tracking-by-identification’ yields surprisingly good results on standard datasets, without the need to update the model online. The general multi-camera framework is validated using three tunnel surveillance videos.     

Visual vehicle detection and tracking based on the 'sign pattern'

Real-time vehicle detection and tracking applicable for outdoor mobile robots on a structured road is proposed. The method is based on a locomotion strategy known as 'sign pattern based stereotyped motion'. The sign pattern of a vehicle is the shadow underneath. The robot detects a vehicle from a distance of 30 m with a domestic video camera and extracts its front shape in real-time processing. The distance between the robot and vehicle, and the velocity and width of the vehicle are estimated during the tracking process. In addition, the center of the vehicle in two-dimensional imaging is determined during the tracking process to estimate the type of motion. The accuracy rate of vehicle width measurement based on the shadow underneath is better than 90% in practice, which can be adequately used for vehicle avoidance applications. The applied method has been tested on roads covered with different types of shadows as well as under different weather conditions. The results of the experiments verify the validity of the method.     

基于视频传感器网络和交通信号的路口前景检测

针对传统背景减法并不完全适合路口前景检测的需要,提出一种利用交通信号增强背景减法性能的前景检测新方法.该方法将交通信号与视频传感器网络相结合,通过传感器网络感知环境变化,从而获取实时准确的交通视频信号,并为各像素分配自适应学习率.新旧方法的对比测试实验结果表明,新方法提高了检测精度,具有广阔的应用前景.     

基于特征匹配预估的Mean Shift运动检测与跟踪

针对传统Mean Shift跟踪算法在目标存在背景干扰或遇到遮挡时,目标跟踪不准确的问题,提出了一种基于特征匹配运动检测预估的Mean Shift跟踪方法.采用Harris算法提取跟踪目标特征点进行运动定位检测,通过Kalman滤波器估计每一帧中目标迭代的起始位置,由Mean Shift算法从预估位置开始迭代搜索,最终实现目标跟踪.实验证明:提出的算法能够在遮挡的情况下对目标进行精准的定位检测,有效改善了复杂条件下的跟踪效果,具有较好的鲁棒性.     

Eyelid contour detection and tracking for startle research related eye-blink measurements from high-speed video records

Using the positions of the eyelids is an effective and contact-free way for the measurement of startle induced eye-blinks, which plays an important role in human psychophysiological research. To the best of our knowledge, no methods for an efficient detection and tracking of the exact eyelid contours in image sequences captured at high-speed exist that are conveniently usable by psychophysiological researchers.     

Building facade detection,segmentation, and parameter estimation for mobile robot stereo vision

Building facade detection is an important problem in computer vision, with applications in mobile robotics and semantic scene understanding. In particular, mobile platform localization and guidance in urban environments can be enabled with accurate models of the various building facades in a scene. Toward that end, we present a system for detection, segmentation, and parameter estimation of building facades in stereo imagery. The proposed method incorporates multilevel appearance and disparity features in a binary discriminative model, and generates a set of candidate planes by sampling and clustering points from the image with Random Sample Consensus (RANSAC), using local normal estimates derived from Principal Component Analysis (PCA) to inform the planar models. These two models are incorporated into a two-layer Markov Random Field (MRF): an appearance- and disparity-based discriminative classifier at the mid-level, and a geometric model to segment the building pixels into facades at the high-level. By using object-specific stereo features, our discriminative classifier is able to achieve substantially higher accuracy than standard boosting or modeling with only appearance-based features. Furthermore, the results of our MRF classification indicate a strong improvement in accuracy for the binary building detection problem and the labeled planar surface models provide a good approximation to the ground truth planes.     

改进GM(1,1)模型的前车检测与跟踪研究

提出了一种改进灰色预测模型GM(1,1)的前方车辆检测与跟踪方法,利用Hough变换识别两侧车道标识线,缩小前方车辆检测与跟踪区域,完成对前方车辆的检测之后,通过改进GM(1,1)模型的持续更新,搜索其运动规律,并对前方车辆的运动轨迹进行预测,根据预测结果实现对前方车辆的跟踪。实验结果表明,该方法不需要对随机噪声序列和目标运动规律进行假设,克服了随机噪声和分离合并的影响,具有较好的实时性和鲁棒性,适合于范围较小的前方车辆检测与跟踪。