基于车载视频监控的乘客检测及跟踪算法

针对公交车上乘客相互遮挡及光照变化明显的问题,提出一种基于头肩部边缘特征和局部不变特征的人体检测及跟踪算法。首先对待检测图像进行自适应阈值背景差分,实现乘客目标分割;然后用样本的梯度方向直方图(HOG)特征训练支持向量机(SVM)基础分类器,结合自适应增强(AdaBoost)算法提炼出最终的强分类器,对前景图像进行扫描实现乘客目标检测;最后提取目标区域和当前搜索区域的快速鲁棒性特征(SURF),通过特征点匹配实现乘客目标跟踪。实验表明,在乘客相互遮挡及光照变化明显的情况下,该算法仍具有高于80%的检测率和跟踪率,且满足系统实时性的要求,可用于客流计数。     

Detection of passenger flow on and off buses based on video images and YOLO algorithm

Bus passenger flow information is very important as a reference data for bus company line optimization, schedule scheduling basis, and passenger travel mode arrangement. With the development of image processing technology, it has become a current research trend to count passenger flow with the help of surveillance video of passengers getting on and off the bus. The specific research contents of this paper based on video image detection and statistics of passengers are as follows:(1) Collect head target image samples through a variety of ways, including 3960 positive head target samples and 4150 negative head target samples, which together constitute the head target feature database. (2) Established a head target detection model based on deep learning. First, the labeling of the head target training data set is completed. Then, after 15,000 iterations of model training, the YOLOv3 head target detection network model was obtained, with a recall rate of 92.12% and an accuracy rate of 89.71%. (3) A multi-target matching tracking algorithm based on the combination of Cam-shift and YOLOv3 is proposed. First, the Cam-shift algorithm is used to track the head target. Secondly, the head target tracking data and the YOLOv3 detection data are combined to solve the problem of drift during the tracking of the Cam-shift algorithm through the data association matching method based on the minimum distance, and then combined with the time constraint, a passenger location information judgment rule is proposed. Optimize the error and missed detection in the process of head target detection and tracking, and improve the reliability of passenger trajectory tracking. (4) A statistical algorithm for the detection of passengers getting on and off the bus is proposed. First, the trajectory of passengers in the bus boarding and disembarking area is analyzed, and a process for judging passengers’ boarding and boarding behavior is proposed. At the same time, a passenger position information judgment rule is proposed according to the different situations of whether there are new passengers or missing passengers, so as to optimize the problem of wrong detection and missing detection in the process of head target detection and tracking. (5) Finally, experiments are carried out in actual bus scenes and simulation scenes. The experiment proves that the statistical algorithm for the detection of passengers getting on and off the bus proposed in this paper has good detection, tracking and statistics effects in bus scenes and simulation scenes.

     

Passenger flow prediction in bus transportation system using deep learning

The forecasting of bus passenger flow is important to the bus transit system’s operation. Because of the complicated structure of the bus operation system, it’s difficult to explain how passengers travel along different routes. Due to the huge number of passengers at the bus stop, bus delays, and irregularity, people are experiencing difficulties of using buses nowadays. It is important to determine the passenger flow in each station, and the transportation department may utilize this information to schedule buses for each region. In Our proposed system we are using an approach called the deep learning method with long short-term memory, recurrent neural network, and greedy layer-wise algorithm are used to predict the Karnataka State Road Transport Corporation (KSRTC) passenger flow. In the dataset, some of the parameters are considered for prediction are bus id, bus type, source, destination, passenger count, slot number, and revenue These parameters are processed in a greedy layer-wise algorithm to make it has cluster data into regions after cluster data move to the long short-term memory model to remove redundant data in the obtained data and recurrent neural network it gives the prediction result based on the iteration factors of the data. These algorithms are more accurate in predicting bus passengers. This technique handles the problem of passenger flow forecasting in Karnataka State Road Transport Corporation Bus Rapid Transit (KSRTCBRT) transportation, and the framework provides resource planning and revenue estimation predictions for the KSRTCBRT.

     

An enhanced text detection technique for the visually impaired to read text

An enhanced text detection technique (ETDT) is proposed, which is expected to aid the visually impaired to overcome their reading challenges. This work enhances the edge-preserving maximally stable extremal regions (eMSER) algorithm using the pyramid histogram of oriented gradients (PHOG). Histogram of oriented gradients (HOG) derived from different pyramid levels is important while detecting maximally stable extremal regions (MSER) in the ETDT approach because it gives more spatial information when compared to HOG information from a single level. To group text, a four-line, text-grouping method is newly designed for this work. Also, a new text feature, Shapeness Score is proposed, which significantly identifies text regions when combined with the other features based on morphology and stroke widths. Using the feature vector of dimension 10, the J48 decision tree and AdaBoost machine learning algorithms identify the text regions in the images. The algorithm yields better results than the existing benchmark algorithms for the ICDAR 2011 born-digital dataset and must be improved with respect to the scene text dataset.     

半监督SVM分类算法的交通视频车辆检测方法

针对交通场景运动车辆检测中车辆数目统计准确率不高、自适应性不强等问题,提出了一种基于半监督支持向量机(SVM)分类算法的交通视频车辆检测方法。利用人工标记的少量样本,分别训练2个基于方向梯度直方图(HOG)特征与基于局部二值模式(LBP)特征的不同核函数的SVM分类器;结合半监督算法的思想,构建SVM的半监督分类方法(SEMI-SVM),标记未知样本并加入到原样本库中,该方法支持样本库动态更新,避免了繁重的人工标记样本的工作,提高了自适应性;最后,通过三帧差分法提取运动区域,加载分类器在该区域进行多尺度检测,标记检测出来的运动车辆,统计车辆数目。实验结果表明:该方法在具有一定的自适应性的同时,有较高的车辆检测准确率,即使在复杂交通情况下,对运动车辆依然有很好的检测效果。     

基于时空关系模型的交通信号灯的实时检测与识别

交通信号灯的检测与识别是无人驾驶汽车和高级驾驶辅助系统(ADAS)的重要组成部分。针对城市道路复杂环境下的交通信号灯的检测和识别需求,依据多帧视频图像序列的时空连续变化关系构建多帧视频图像的时空关系模型(Time-Space Model,TSM),提出了一种新的基于多帧视频图像序列的交通信号灯的检测和识别算法。算法包含3部分:基于颜色的视频图像快速分割压缩算法,用于提高计算效率;引入多帧视频图像序列的时空关系模型,以提高交通信号灯检测的准确性 ;根据图像的HOG(Histogram of Oriented Gradient)特征,通过SVM(Support Vector Machine)分类器对信号灯进行识别。实验结果表明,算法的鲁棒性强、检测识别速度快、准确率高。     

组合SVM分类器在行人检测中的研究

在基于HOG特征的SVM行人检测算法的基础上,提出了组合分类器的改进算法。该算法首先采用多尺度滑动窗口提取HOG特征,并对单个SVM分别进行训练,再将训练好的SVM分别采用串联、并联结构形成新分类器后对行人进行检测。为解决用多尺度滑动窗口提取特征时产生的目标候选区域重叠问题,采用非极大值抑制算法对重叠区域进行融合,进而得到准确候选区。实验表明,组合的SVM分类器可以有效降低误检率和漏检率。     

基于HOG和SVM的双眼虹膜图像的人眼定位算法

针对近红外光下现有的人眼定位算法普遍存在准确性不高、泛化能力不佳等问题，提出了一种基于方向梯度直方图（HOG）和支持向量机（SVM）相结合的双眼虹膜图像的人眼定位算法。利用HOG提取虹膜图像的人眼特征，并结合SVM分类器对HOG特征进行训练从而实现人眼的精确定位。为了减少漏检和误检，进一步提高定位准确率，又提出了多级级联SVM分类器算法；另外针对近红外光线下虹膜图像独特的灰度分布特点，设计了一种图像预处理方法，能够显著提高人眼定位速度。在MIR2016和CASIA-IRIS-Distance数据集上的实验结果表明，基于HOG和SVM的双眼虹膜图像的人眼定位算法具有高准确率、强泛化能力和高实时性。     

基于人流量检测的改进CN算法

为实现在行人严重遮挡时人流量的精确统计,研究一种基于人流量检测的改进CN算法。结合背景差分与三帧差分提取运动目标前景;通过梯度方向直方图与支持向量机判断头肩特征;在Kalman滤波器预测下一帧图像中目标位置的周围选取检测窗口,利用融合HOG与CN(颜色名)特征的改进CN算法实现目标跟踪;以感兴趣区域计数线为准,结合目标运动轨迹实现人流量统计。实验结果表明,该算法在有行人严重遮挡的情况下具有较高的检测效率。     

基于PCA降维的多特征级联的行人检测

在行人检测中,针对梯度方向直方图(HOG)冗余信息过多、检测速度慢等不足,提出了运用PCA降维的多特征级联的行人检测。首先利用PCA对HOG特征进行降维,其次将HOG特征和Gabor特征、颜色特征级联作为行人检测的特征,最后使用SVM的径向基(RBF)核函数进行分类。在INRIA行人库上的实验表明,该方法不但提高了分类的速度,而且提高了检测的准确率。     

基于SSD卷积神经网络的公交车下车人数统计

传统典型的公交车人数统计方法在准确率和速度方面存在一些不足,且提取目标特征的效果较差.本文提出了基于深度卷积神经网络的公交车人数统计系统解决人群计数问题.首先制作数据集,难点在于所有用于训练的数据集均是手工标注.并且公交车摄像头角度比以往文献覆盖更广区域.本文首先比较了多种不同的深度卷积神经网络模型对乘客进行全身检测的效果.综合考虑检测速率、准确率等方面,最终采用单次检测器深度卷积神经网络模型对乘客进行人头目标检测,在线实时目标追踪算法实现人头的多目标追踪,跨区域人群计数方法统计公交车下车人数.系统准确率达到78.38%,运行速率约为每秒识别19.79帧.实现了人群计数.     

随身物品特征提取乘客计数方法研究

提出了一种基于随身物品特征识别的自动乘客计数方法,其目的在于实现公交线路上任意两站间的客流统计。该算法的原理是通过提取乘客身高体型特征、随身物品的颜色位置特征来对乘客进行识别和跟踪。针对公交车自动乘客计数的特点,本算法引入特殊的中值滤波、腐蚀膨胀和相关性分析等操作,能有效地辨识出乘客目标及其随身物品信息。并通过分区域处理进一步简化运算。最后通过公交车视频的图像处理实验,证明该算法切实可行。     

基于NSCT和支持向量机的SAR图像识别

针对传统的合成孔径雷达图像（SAR）识别算法识别精度低,用时长等问题,提出一种基于非下采样轮廓波变换（NSCT）和支持向量机（SVM）的SAR图像识别算法。首先通过非下采样轮廓波变换将目标图像分解成不同的尺度,然后得到目标图像的低频分量和高频分量;接着在高频分量中提取方向梯度直方图特征（HOG）,在低频分量中利用局部二值化算法（Local Binary Pattern,LBP）提取纹理特征;然后将提取的梯度方向直方图特征和局部二值化特征空间连结,并使用支持向量机（SVM）作为分类器;最后对算法进行了测试。实验结果表明,该方法不仅能够有效地提高了SAR图像目标分类的精度,在MSTAR数据库上的准确率达到90.7%,而且对相干斑的影响具有较高的鲁棒性。     

A bus passenger re-identification dataset and a deep learning baseline using triplet embedding

Bus passenger re-identification is a special case of person re-identification, which aims to establish identity correspondence between the front door camera and the back door camera. In bus environment,it is hard to capture the full body of the passengers. So this paper proposes a bus passenger re-identification dataset,which contains 97,136 head images of 1,720 passengers obtained from hundreds of thousands of video frames with different lighting and perspectives. We also provide a evaluation applied to the dataset based on deep learning and triplet loss. After data augmentation,using ResNet with trihard loss as benchmark network and pre-training on pedestrian re-identification dataset Market-1501, we achieve mAP accuracy of 55.79% and Rank-1 accuracy of 67.91% on passenger re-identification dataset.

     

基于公共交通智能卡数据的可视化分析

针对现有公共交通数据的可视分析方法很难在不同空间粒度下对乘客时空分布、客流时空分布、区域间客流时序变化进行多任务分析的问题,设计实现了一个多视图融合的可视化分析系统。该系统结合城市公共交通的智能卡数据、车辆GPS数据、地铁和公交线路信息,利用出行链路模型和基于出行时空特征的回归模型完成了乘客起讫点（origin-destination,OD）推断;然后,设计了层次聚类的地图可视化方法,结合了融合方位信息的玫瑰图和动态对比堆叠折线流图来分析各区域间的客流时序特点、关联关系;最后,利用真实的深圳市公共交通数据的可视分析结果验证了系统的有效性。     

局部二次加权与多特征融合的行人检测算法

针对复杂背景下采用单一特征进行行人检测时的局限性,提出了一种融合多种特征并运用模板弹性模型与局部二次加权的算法,将梯度直方图（HOG）、肤色、发色与曲率有效融合,建立了适用行人检测的各特征模型。第一级采用改进HOG特征结合模板弹性模型利用SVM分类器初次检测;第二级提取局部模板感兴趣区域（ROI）进行头部肤色、发色与腿部曲率检测。实验表明,该算法弥补了单一特征的不足,有效检测了行人整体与局部关键特征,提高了识别性能。     

液晶字符识别的CNN和SVM组合分类器

针对仪表液晶显示字符识别问题,提出一种结合了卷积神经网络(CNN)和支持向量机(SVM)的字符识别方法.分别采用具有并联结构的CNN模型和基于梯度方向直方图(HOG)特征的SVM方法构建基本分类器,当2个分类器的结果存在冲突时,利用CNN的softmax输出最大值判决最终结果,当其大于设定阈值时采用CNN分类器的结果,...     

遗传算法在公交调度中的应用

针对泰州市公交智能化建设方面存在的技术问题,提出将遗传算法(Genetic Algorithms,GA)应用到公交调度优化中。以公交公司和乘客费用最少、社会效益最大为目标函数建立公交调度优化的数学模型,并应用遗传算法实现对模型的求解,通过对模型设置不同的参数,利用Matlab模拟实验验证模型的合理性、科学性。实验证明,优化的调度模型可降低公交公司的运营成本,提高乘客的满意度,确保社会效益和经济效益得到最大满足。     

智能交通动态调度优化模型与评价方法

为了降低大城市市民出行成本,缓解公交企业运力压力,提出一种智能交通出行OD(Origin Destination,出行地和目的地)的公交调度优化算法,以公交出行OD客流预测和计划排班发车时间间隔为出发点,运用公交出行OD客流推导理论,构建智能交通出行OD的公交调度优化模型。通过获取个人OD数据,利用单条线路公交OD方法,实现全市公交OD矩阵推算。根据全市公交出行OD推算结果,求解公交调度模型,解决智能交通调度多目标规划和公交线网优化问题。通过仿真模拟试验,分析智能公交排班计划评价指标,计算车辆营运效率占比:自动排班仿真数据为79%,实际运营数据为73%;统计车辆高峰时段与全天营运车次占比:自动排班仿真数据为36.75%,实际运营数据为37.37%,满足智能公交计划排班评价指标的要求,实例证明模型和算法具有实用性和可靠性。     

光照变化情况下的静态头部姿态估计

针对图像光照的变化对静态头部姿态估计的影响,该文提出一种基于有向梯度直方图和主成分分析的姿态特征,并利用SVM分类器进行分类。该算法分别在CMU姿态、光照、表情数据库和CVL人脸图像库上进行了测试。实验表明,即使图像光照变化很大,该算法仍可准确地估计头部姿态,识别率达到90％以上。