Directional pedestrian counting with a hybrid map-based model

Detection-based pedestrian counting methods produce results of considerable accuracy in non-crowded scenes. However, the detection-based approach is dependent on the camera viewpoint. On the other hand, map-based pedestrian counting methods are performed by measuring features that do not require separate detection of each pedestrian in the scene. Thus, these methods are more effective especially in high crowd density. In this paper, we propose a hybrid map-based model that is a new directional pedestrian counting model. Our proposed model is composed of direction estimation module with classified foreground motion vectors, and pedestrian counting module with principal component analysis. Our contributions in this paper have two aspects. First, we present a directional moving pedestrian counting system that does not depend on object detection or tracking. Second, the number and major directions of pedestrian movements can be detected, by classifying foreground motion vectors. This representation is more powerful than simple features in terms of handling noise, and can count the moving pedestrians in images more accurately.

     

结合运动信息与表观特征的行人检测方法

提出一种结合运动信息与表观特征的行人检测方法.在对通过表观检测子获得的候选检测窗口执行分割验证的框架中,将运动信息融入到基于图像序列的对象分割算法中,通过获取更准确的分割结果来提高对候选检测窗口的检测准确率.该方法利用运动信息更新运动对象的前景/背景分布模型,将颜色信息间接地融入行人检测中,并通过形状特征表现出来,与行人表观检测子形成互补的特性,获得更好的检测结果.上述结论在CAVIAR视频以及行人检测视频中得到了实验验证.     

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。     

结合对象分割的运动行人检测

目标检测大量应用于监控系统的行人检测以及人脸识别,是当前深度学习的研究热点.监督学习利用人工标注大量数据集训练出针对特定场景的行人检测器.但是人工标注方法费时费力,本文针对监督学习需要人工标注数据集的缺点,研究了一种半自动标注行人的方法.针对静止的单目摄像机拍摄的监控视频,利用光流信息提供的初始前景可能性,以及跨越时间的视觉相似性来迭代地更新初始的前景可能性,分割出运动的行人,根据分割的前景对象,提出了一种半自动标注行人的方法.实验结果显示,本文的方法可以为行人检测系统提供大量数据集,且效率上明显优于传统人工标注的方法.     

采用截面流量统计的高密度人群行人计数

利用摄像头实现行人计数在智能视频监控领域有着重要的价值,但是行人互相遮挡、噪声、摄像机透视效果和图像背景等问题影响了人群计数的准确性.针对高密度人群场景的行人计数准确率的问题,提出了基于截面流量统计的行人计数方法,该方法基于梯度运动历史图像检测前景,并用有效运动图像改进了基于特征提取的行人计数方法,结合运动速度提取方法实现了行人计数.实验结果表明,提出的计数方法在高密度人群场景中具有较高的准确率和实时性,是一种针对高密度人群有效的行人计数方法.     

第一人称视角下的社会力优化多行人跟踪

目的 多行人跟踪一直是计算机视觉领域最具挑战性的任务之一,然而受相机移动、行人频繁遮挡和碰撞影响导致第一人称视频中行人跟踪存在效率和精度不高的问题。对此,本文提出一种基于社会力模型优化的第一人称视角下的多行人跟踪算法。方法 采用基于目标检测的跟踪算法,将跟踪问题简化为检测到的目标匹配问题,并且在初步跟踪之后进行社会力优化,有效解决频繁遮挡和碰撞行为导致的错误跟踪问题。首先,采用特征提取策略和宽高比重新设置的单步多框检测器（single shot multi-box detector,SSD）,对输入的第一人称视频序列进行检测,并基于卷积神经网络（convolutional neural network,CNN）模型提取行人的表观特征,通过计算行人特征相似度获得初步的行人跟踪结果;然后,进行跟踪结果的社会力优化,一是定义行人分组行为,对每个行人跟踪目标进行分组计算,并通过添加分组标识,实现同组行人在遮挡的情况下的准确跟踪;二是通过定义的行人领域,对行人分组进行排斥计算,实现避免碰撞后的准确跟踪。结果 在公用数据集ETH（eidgenössische technische hochschule）、MOT16（multi-object tracking 16）和ADL（adelaide）的6个第一人称视频序列上与其他跟踪算法进行对比实验,本文算法的运行速度达到准实时的20.8帧/s,同时相比其他准实时算法,本文算法的整体跟踪性能MOTA（multiple object tracking accuracy）提高了2.5%。结论 提出的第一人称视频中社会力优化的多行人跟踪算法,既能准确地在第一人称场景中跟踪多个行人,又能较好地满足实际应用需求。     

Shadow removal for pedestrian detection and tracking in indoor environments

This paper presents a method of shadow removal to improve the accuracy of pedestrian detection and tracking in indoor environments. The proposed method can be divided into four steps: building a background model which can be automatically updated, extract moving objects region, eliminating moving objects shadows, classifying and track pedestrians. The background model is built with pixel value and the updating of Gussian. The approach for real time background-foreground extraction is used to extract pedestrian region that may contains multiple shadows. In the gray histogram space, based on the depth value of the gray images, a reasonable threshold is set to remove shadows from various pedestrians. In this work, we propose a methodology using the foreground frames without shadows to detect and track the pedestrians across training datasets. Comparative experimental results show that our method is capable of dealing with shadows and detecting moving pedestrians in cluttered environments.     

双摄像机协同人脸鹰眼检测与定位方法

现代视频监控系统需要获取大范围场景中感兴趣目标的清晰图像,这在目标距离较远并且不断移动时单纯采用摄像机调焦方式通常有一定的困难。为了获取宽范围监控场景中远距离行人的主要面部特征,采用广角静止—窄视场运动双摄像机协同工作方式可以同时获得远距离目标的全局和细节信息。首先采用改进的Codebook背景减法从广角摄像机中检测运动目标,然后指引运动摄像机近距离跟踪观察;若行人停止运动,则利用运动摄像机对其进行放大,然后从中检测人脸,并将人脸置于视野中心放大得到清晰图像。当行人再次运动时,广角相机将初始位置再次传递给运动摄像机,由其再对行人进行跟踪。通过实验室内和室外真实场景的实验表明,广角相机的检测算法具有一定的鲁棒性,运动相机能跟踪放大行人人脸图像,算法运行速度满足实时性要求。     

基于双阈值运动区域分割的AdaBoost行人检测算法

结合单目摄像机静止拍摄的视频序列使用背景差法或AdaBoost算法检测行人时分别存在易受噪声干扰或检测速度慢的问题,提出一种双阈值运动区域分割的AdaBoost快速行人检测算法。首先建立背景帧,利用前景帧与背景帧的差分图像拟合噪声曲线,提取噪声与亮暗运动目标的阈值,消除噪声,分割出运动区域;然后通过AdaBoost学习算法选择少量有效的Haar-like弱矩形特征构造强分类器;最后在运动区域利用强分类器检测是否包含行人。实验结果表明,该方法迅速缩小了检测范围,加快了检测速度,降低了误检率。     

多线索融合的无视野重叠跨摄像机行人跟踪算法

针对单个摄像机视野有限而无法满足日益扩大的监控范围的现象,此文对无视野重叠的跨摄像机行人跟踪算法进行了研究,并提出了一种融合时空线索和外观线索的无视野重叠跨摄像机行人跟踪算法。文章在对已有摄像机网络拓扑结构估计算法分析的基础上提出了一种基于加权时间窗口的无视野重叠摄像机网络拓扑结构估计算法。然后利用朴素贝叶斯完成两种线索融合,实现不同摄像机间行人匹配和跟踪信息的传递,最终实现无视野重叠区域的跨摄像机行人跟踪。该算法在公开的MCT数据集上进行对比实验并取得了优于其它算法的结果。     

域通用和域分离字典对学习的行人重识别算法

为克服不同相机视角之间的域偏移问题,提出一种基于域通用和域分离字典对学习的跨视角行人重识别算法。具体地,基于来自同一相机视角下的行人共享相同的域,并且同一视角中每个行人图像所携带的域信息在短时间内具有一致性,将同一视角下的行人图像分解为特定视角的域信息分量和域分离的行人外观特征分量,提出一个判别字典学习模型以创建用于描述域信息分量的域通用字典和描述行人外观分量的域分离字典。由于来自同一相机视角下的图像具有域相似性,因此通过低秩正则化来细化用于表示域信息的字典。为了进一步提高学习字典的判别能力,在算法中约束相同视角、相同身份的多幅图像的编码系数具有很强的相似性。此外,采用一种新颖的扩展正则化方法来解决不同行人相似外貌特征和同一行人不同外貌特征的视觉外观歧义问题。在四个具有挑战性的数据集上进行实验,结果表明域通用和域分离字典对学习的算法相对于一些现有最新算法更具有效性和优越性。     

Online visual tracking with histograms and articulating blocks

We propose an algorithm for accurate tracking of articulated objects using online update of appearance and shape. The challenge here is to model foreground appearance with histograms in a way that is both efficient and accurate. In this algorithm, the constantly changing foreground shape is modeled as a small number of rectangular blocks, whose positions within the tracking window are adaptively determined. Under the general assumption of stationary foreground appearance, we show that robust object tracking is possible by adaptively adjusting the locations of these blocks. Implemented in MATLAB without substantial optimization, our tracker runs already at 3.7 frames per second on a 3 GHz machine. Experimental results have demonstrated that the algorithm is able to efficiently track articulated objects undergoing large variation in appearance and shape.     

结合形状约束的Graph Cut行人分割

传统的Graph Cut算法没有对目标的形状予以限制,很难得到语义化的分割结果,即无法保证分割出来的是“行人”。针对该问题提出一种结合形状和底层特征的Graph Cut算法。对于行人分割,用大量真实行人轮廓来表达“行人”的先验形状,对Graph Cut分割算法予以约束,同时构建一个行人模板的层次树以减少匹配时间;并且提出一种区分性的外观模型来替换原来的外观模型。实验结果证明,该算法的分割结果明显优于传统Graph Cut算法的分割结果,所得到的轮廓与真实的行人轮廓比较吻合。     

Multiple human tracking in high-density crowds

In this paper, we introduce a fully automatic algorithm to detect and track multiple humans in high-density crowds in the presence of extreme occlusion. Typical approaches such as background modeling and body part-based pedestrian detection fail when most of the scene is in motion and most body parts of most of the pedestrians are occluded. To overcome this problem, we integrate human detection and tracking into a single framework and introduce a confirmation-by-classification method for tracking that associates detections with tracks, tracks humans through occlusions, and eliminates false positive tracks. We use a Viola and Jones AdaBoost detection cascade, a particle filter for tracking, and color histograms for appearance modeling. To further reduce false detections due to dense features and shadows, we introduce a method for estimation and utilization of a 3D head plane that reduces false positives while preserving high detection rates. The algorithm learns the head plane from observations of human heads incrementally, without any a priori extrinsic camera calibration information, and only begins to utilize the head plane once confidence in the parameter estimates is sufficiently high. In an experimental evaluation, we show that confirmation-by-classification and head plane estimation together enable the construction of an excellent pedestrian tracker for dense crowds.     

Experiment and analysis on microscopic characteristics of pedestrian movement in building bottleneck

In this paper, evacuation experiments are carried out to study pedestrian movement behaviors in building bottleneck. An image processing method based on mean-shift algorithm is used to extract pedestrian movement trajectory. Based on the extracted trajectory, we analyze the microscopic movement characteristics of pedestrians such as lane formation, change of velocity and distance between two sequential pedestrians. A pedestrian lane is a group of pedestrians moving in a column. The lane formation is verifie...     

A shape-based voting algorithm for pedestrian detection and tracking

This paper presents the MOUGH (mixture of uniform and Gaussian Hough) Transform for shape-based object detection and tracking. We show that the edgels of a rigid object at a given orientation are approximately distributed according to a Gaussian mixture model (GMMs). A variant of the generalized Hough transform is proposed, voting using GMMs and optimized via Expectation-Maximization, that is capable of searching images for a mildly-deformable shape, based on a training dataset of (possibly noisy) images with only crude estimates of scale and centroid of the object in each image. Further modifications are proposed to optimize the algorithm for tracking. The method is able to locate and track objects reliably even against complex backgrounds such as dense moving foliage, and with a moving camera. Experimental results indicate that the algorithm is superior to previously published variants of the Hough transform and to active shape models in tracking pedestrians from a side view.     

Deep infrared pedestrian classification based on automatic image matting

Infrared pedestrian classification plays an important role in advanced driver assistance systems. However, it encounters great difficulties when the pedestrian images are superimposed on a cluttered background. Many researchers design very deep neural networks to classify pedestrian from cluttered background. However, a very deep neural network associated with a high computational cost. The suppression of cluttered background can boost the performance of deep neural networks without increasing their depth, while it has received little attention in the past. This study presents an automatic image matting approach for infrared pedestrians that suppresses the cluttered background and provides consistent input to deep learning. The domain expertise in pedestrian classification is applied to automatically and softly extract foreground objects from images with cluttered backgrounds. This study generates trimaps, which must be generated manually in conventional approaches, according to the estimated positions of pedestrian’s head and upper body without the need for any user interaction. We implement image matting by adopting the global matting approach and taking the generated trimap as an input. The representation of pedestrian is discovered by a deep learning approach from the resulting alpha mattes in which cluttered background is suppressed, and foreground is enhanced. The experimental results show that the proposed approach improves the infrared pedestrian classification performance of the state-of-the-art deep learning approaches at a negligible computational cost.     

基于多任务CNN的监控视频中异常行人快速检测

在近年来社会公共安全受到广泛关注的情况下,如何利用监控视频对异常行人进行监督,预防危险事件的发生成为了一个热门课题.异常行人是指与普通行人在外观上有明显异常性区别的人,例如用头盔大面积遮挡面部或低头躲避摄像头,考虑到异常行人的特征主要集中在头面部,本文提出一种基于多任务卷积神经网络和单类支持向量机的针对头面部特征的异常行人快速检测方法.首先进行头面部区域的检测,然后使用多任务卷积神经网络提取头面部区域的特征,之后使用单类支持向量机判断是正常行人还是异常行人.此外,本文还针对卷积神经网络设计了一种卷积核拆分方法,加快了特征提取的速度,最终实验表明,本文提出的算法能够快速有效的检测出监控视频中的异常行人.     

基于道路环境上下文的行人跟踪方法

针对目前城市交通中人车混行场景中行人跟踪效果不佳的问题,提出了一种基于道路环境上下文的行人跟踪方法。首先通过对道路环境上下文进行分析,建立道路模型;其次在道路模型的约束下建立行人与环境的交互运动模型;最后利用该模型进行行人的跟踪。在真实场景中的实验表明使用了道路上下文信息的跟踪方法与连续离散连续能量最小化的多行人跟踪方法相比,多目标跟踪准确度从47.6%提升至63.2%,多目标跟踪精度从68.8%提升至74.3%。数值结果表明道路上下文信息对于提高人车混行场景中行人跟踪效果的有效性。