基于粒子视频的高密度人群主流运动检测

采用粒子视频流获得视频序列中的特征点运动轨迹,并对获得的运动轨迹进行提取,然后利用最长共同子序列LCS(Longest Common Subsequence)聚类轨迹,得到运动的主流方向。该算法可以有效检测实际场景中的主流运动方向。     

Exploring Temporal Structure of Trajectory Components for Action Recognition

Action recognition is one of the most important components for video analysis. In addition to objects and atomic actions, temporal relationships are important characteristics for many actions and are not fully exploited in many approaches. We model the temporal structures of midlevel actions (referred to as components) based on dense trajectory components, obtained by clustering individual trajectories. The trajectory components are a higher level and a more stable representation than raw individual trajectories. Based on the temporal ordering of trajectory components, we describe the temporal structure using Allen's temporal relationships in a discriminative manner and combine it with a generative model using bag of components. The main idea behind the model is to extract midlevel features from domain‐independent dense trajectories and classify the actions by exploring the temporal structure among these midlevel features based on a set of relationships. We evaluate the proposed approach on public data sets and compare it with a bag‐of‐words–based approach and state‐of‐the‐art application of the Markov logic network for action recognition. The results demonstrate that the proposed approach produces better recognition accuracy.     

自然环境视频中基于显著鲁棒轨迹的行为识别

目的人类行为识别是计算机视觉领域的一个重要研究课题。由于背景复杂、摄像机抖动等原因,在自然环境视频中识别人类行为存在困难。针对上述问题,提出一种基于显著鲁棒轨迹的人类行为识别算法。方法该算法使用稠密光流技术在多尺度空间中跟踪显著特征点,并使用梯度直方图(HOG)、光流直方图(HOF)和运动边界直方图(MBH)特征描述显著轨迹。为了有效消除摄像机运动带来的影响,使用基于自适应背景分割的摄像机运动估计技术增强显著轨迹的鲁棒性。然后,对于每一类特征分别使用Fisher Vector模型将一个视频表示为一个Fisher向量,并使用线性支持向量机对视频进行分类。结果在4个公开数据集上,显著轨迹算法比Dense轨迹算法的实验结果平均高1%。增加摄像机运动消除技术后,显著鲁棒轨迹算法比显著轨迹算法的实验结果平均高2%。在4个数据集(即Hollywood2、You Tube、Olympic Sports和UCF50)上,显著鲁棒轨迹算法的实验结果分别是65.8%、91.6%、93.6%和92.1%,比目前最好的实验结果分别高1.5%、2.6%、2.5%和0.9%。结论实验结果表明,该算法能够有效地识别自然环境视频中的人类行为,并且具有较低的时间复杂度。     

Learning motion patterns in unstructured scene based on latent structural information

ContextAs trajectory analysis is widely used in the fields of video surveillance, crowd monitoring, behavioral prediction, and anomaly detection, finding motion patterns is a fundamental task for pedestrian trajectory analysis.ObjectiveIn this paper, we focus on learning dominant motion patterns in unstructured scene.MethodsAs the invisible implicit indicator to scene structure, latent structural information is first defined and learned by clustering source/sink points using CURE algorithm. Considering the basic assumption that most pedestrians would find the similar paths to pass through an unstructured scene if their entry and exit areas are fixed, trajectories are then grouped based on the latent structural information. Finally, the motion patterns are learned for each group, which are characterized by a series of statistical temporal and spatial properties including length, duration and envelopes in polar coordinate space.ResultsExperimental results demonstrate the feasibility and effectiveness of our method, and the learned motion patterns can efficiently describe the statistical spatiotemporal models of the typical pedestrian behaviors in a real scene. Based on the learned motion patterns, abnormal or suspicious trajectories are detected.ConclusionThe performance of our approach shows high spatial accuracy and low computational cost.     

Matching Trajectories between Video Sequences by Exploiting a Sparse Projective Invariant Representation

Identifying correspondences between trajectory segments observed from nonsynchronized cameras is important for reconstruction of the complete trajectory of moving targets in a large scene. Such a reconstruction can be obtained from motion data by comparing the trajectory segments and estimating both the spatial and temporal alignments. Exhaustive testing of all possible correspondences of trajectories over a temporal window is only viable in the cases with a limited number of moving targets and large view overlaps. Therefore, alternative solutions are required for situations with several trajectories that are only partially visible in each view. In this paper, we propose a new method that is based on view-invariant representation of trajectories, which is used to produce a sparse set of salient points for trajectory segments observed in each view. Only the neighborhoods at these salient points in the view--invariant representation are then used to estimate the spatial and temporal alignment of trajectory pairs in different views. It is demonstrated that, for planar scenes, the method is able to recover with good precision and efficiency both spatial and temporal alignments, even given relatively small overlap between views and arbitrary (unknown) temporal shifts of the cameras. The method also provides the same capabilities in the case of trajectories that are only locally planar, but exhibit some nonplanarity at a global level.     

Classifying spatiotemporal object trajectories using unsupervised learning in the coefficient feature space

This paper proposes a novel technique for clustering and classification of object trajectory-based video motion clips using spatiotemporal function approximations. Assuming the clusters of trajectory points are distributed normally in the coefficient feature space, we propose a Mahalanobis classifier for the detection of anomalous trajectories. Motion trajectories are considered as time series and modelled using orthogonal basis function representations. We have compared three different function approximations – least squares polynomials, Chebyshev polynomials and Fourier series obtained by Discrete Fourier Transform (DFT). Trajectory clustering is then carried out in the chosen coefficient feature space to discover patterns of similar object motions. The coefficients of the basis functions are used as input feature vectors to a Self- Organising Map which can learn similarities between object trajectories in an unsupervised manner. Encoding trajectories in this way leads to efficiency gains over existing approaches that use discrete point-based flow vectors to represent the whole trajectory. Our proposed techniques are validated on three different datasets – Australian sign language, hand-labelled object trajectories from video surveillance footage and real-time tracking data obtained in the laboratory. Applications to event detection and motion data mining for multimedia video surveillance systems are envisaged.     

Motion codeword generation using selective subsequence clustering for human action recognition

The understanding of human activity is one of the key research areas in human-centered robotic applications. In this paper, we propose complexity-based motion features for recognizing human actions. Using a time-series-complexity measure, the proposed method evaluates the amount of useful information in subsequences to select meaningful temporal parts in a human motion trajectory. Based on these meaningful subsequences, motion codewords are learned using a clustering algorithm. Motion features are then generated and represented as a histogram of the motion codewords. Furthermore, we propose a multiscaled sliding window for generating motion codewords to solve the sensitivity problem of the performance to the fixed length of the sliding window. As a classification method, we employed a random forest classifier. Moreover, to validate the proposed method, we present experimental results of the proposed approach based on two open data sets: MSR Action 3D and UTKinect data sets.     

Crowd behaviors analysis and abnormal detection based on surveillance data

Crowd analysis and abnormal trajectories detection are hot topics in computer vision and pattern recognition. As more and more video monitoring equipments are installed in public places for public security and management, researches become urgent to learn the crowd behavior patterns through the trajectories obtained by the intelligent video surveillance technology. In this paper, the FCM (Fuzzy c-means) algorithm is adopted to cluster the source points and sink points of trajectories that are deemed as critical points into several groups, and then the trajectory clusters can be acquired. The feature information statistical histogram for each trajectory cluster which contains the motion information will be built after refining them with Hausdorff distances. Eventually, the local motion coherence between test trajectories and refined trajectory clusters will be used to judge whether they are abnormal.     

时空域融合的骨架动作识别与交互研究

在人体骨架结构动作识别方法中,很多研究工作在提取骨架结构上的空间信息和运动信息后进行融合,没有对具有复杂时空关系的人体动作进行高效表达。本文提出了基于姿态运动时空域融合的图卷积网络模型(PM-STFGCN)。对于在时域上存在大量的干扰信息,定义了一种基于局部姿态运动的时域关注度模块(LPM-TAM),用于抑制时域上的干扰并学习运动姿态的表征。设计了基于姿态运动的时空域融合模块(PM-STF),融合时域运动和空域姿态特征并进行自适应特征增强。通过实验验证,本文提出的方法是有效性的,与其他方法相比,在识别效果上具有很好的竞争力。设计的人体动作交互系统,验证了在实时性和准确率上优于语音交互系统。     

View-Invariant Representation and Recognition of Actions

Analysis of human perception of motion shows that information for representing the motion is obtained from the dramatic changes in the speed and direction of the trajectory. In this paper, we present a computational representation of human action to capture these dramatic changes using spatio-temporal curvature of 2-D trajectory. This representation is compact, view-invariant, and is capable of explaining an action in terms of meaningful action units called dynamic instants and intervals. A dynamic instant is an instantaneous entity that occurs for only one frame, and represents an important change in the motion characteristics. An interval represents the time period between two dynamic instants during which the motion characteristics do not change. Starting without a model, we use this representation for recognition and incremental learning of human actions. The proposed method can discover instances of the same action performed by differentpeople from different view points. Experiments on 47 actions performed by 7 individuals in an environment with no constraints shows the robustness of the proposed method.     

Particle Video: Long-Range Motion Estimation Using Point Trajectories

This paper describes a new approach to motion estimation in video. We represent video motion using a set of particles. Each particle is an image point sample with a long-duration trajectory and other properties. To optimize particle trajectories we measure appearance consistency along the particle trajectories and distortion between the particles. The resulting motion representation is useful for a variety of applications and cannot be directly obtained using existing methods such as optical flow or feature tracking. We demonstrate the algorithm on challenging real-world videos that include complex scene geometry, multiple types of occlusion, regions with low texture, and non-rigid deformations.     

Spatiotemporal bag-of-features for early wildfire smoke detection

Wildfire smoke detection is particularly important for early warning systems, because smoke usually rises before flames arise. Therefore, this paper presents an automatic wildfire smoke detection method using computer vision and pattern recognition techniques. First, candidate blocks are identified using key-frame differences and nonparametric smoke color models to detect smoke-colored moving objects. Subsequently, three-dimensional spatiotemporal volumes are built by combining the candidate blocks in the current key-frame with the corresponding blocks in previous frames. A histogram of oriented gradient (HOG) is extracted, and a histogram of oriented optical flow (HOOF) is extracted as a temporal feature based on the fact that the direction of smoke diffusion is upward owing to thermal convection. From spatiotemporal features of training data, a visual codebook and a bag-of-features (BoF) histogram are generated using our proposed weighting scheme. For smoke verification, a random forest classifier is built during the training phase using the BoF histogram. The random forest with the BoF histogram can increase the detection accuracy performance when compared with related methods and allow smoke detection to be carried out in near real time.     

基于密集轨迹和光流二值化图的行为识别算法

针对改进的密集轨迹算法（improved dense trajectories,iDT）提取的轨迹数量较为庞大的问题,提出了一种轨迹滤除方法。密集采样兴趣点,利用光流图计算每个兴趣点下一帧的位置进而组成轨迹,对每帧光流图进行最大值归一化以及二值化,得到光流二值化图,以此反映该点的运动是否相对显著。利用光流二值化图统计轨迹上各点的有效性从而判断轨迹是否满足有效条件,并将不满足条件的轨迹滤除,得到提纯的轨迹。为了验证算法的有效性,使用了行为识别领域的常用数据集KTH和UCF sports对算法进行验证,实验结果表明,该算法能在保证准确率的同时减少轨迹数量,并且计算量较小。     

融合RGB-D多模特征和半径边缘约束超限学习的动作识别

针对单模态特征鉴别行为动作类别的能力有限问题,提出基于RGB-D视频中多模态视觉特征融合和实例化多重核超限学习(Exemplars-MKL-ELM)的动作分类方法.首先,利用骨架表面拟合和密集轨迹提取稳健的密集运动姿态特征,以稠密点云法平面感知人体3维几何的稀疏化有向主成分直方图特征,提取外观纹理嵌入身体节点空-时邻域的三维梯度直方图特征.然后,采用半径边缘约束多重核超限学习机融合多模态视觉特征,并利用对比数据法挖掘每个行为类别的代表性实例集合.最后,每个样本结合融合视觉特征和即得实例集合,采用Exemplars-MKL-ELM模型和贪婪预测思想分层分类识别行为.实验表明,文中方法在分类准确度和计算效率上都较优.     

Human action recognition with salient trajectories and multiple kernel learning

Action recognition in videos plays an important role in the field of computer vision and multimedia, and there exist lots of challenges due to the complexity of spatial and temporal information. Trajectory-based approach has shown to be efficient recently, and a new framework and algorithm of trajectory space information based multiple kernel learning (TSI-MKL) is exploited in this paper. First, dense trajectories are extracted as raw features, and three saliency maps are computed corresponding to color, space, and optical flow on frames at the same time. Secondly, a new method combining above saliency maps is proposed to filter the achieved trajectories, by which a set of salient trajectories only containing foreground motion regions is obtained. Afterwards, a novel two-layer clustering is developed to cluster the obtained trajectories into several semantic groups and the ultimate video representation is generated by encoding each group. Finally, representations of different semantic groups are fed into the proposed kernel function of a multiple kernel classifier. Experiments are conducted on three popular video action datasets and the results demonstrate that our presented approach performs competitively compared with the state-of-the-art.     

基于运动方向的异常行为检测

提出了一种基于运动方向的异常行为检测方法. 根据不同行为的运动方向具有不同的规律性, 该方法采用块运动方向描述不同的动作, 并利用支持向量机(Support vector machine, SVM)对实时监控视频进行异常行为检测. 为了减少噪声运动的影响, 同时有效保留小幅度运动的前景目标, 在行为描述之前, 本文采用了背景边缘模型对每一视频帧进行前景帧(有目标出现的视频帧)判断. 在行为描述时, 先提取相应视频段的所有前景帧的块运动方向, 然后对这些运动方向进行归一化直方图统计得到该视频段的行为特征. 在走廊等公共场景中的实验结果表明, 该方法能够对单人以及多人的复杂行为进行有效检测, 对运动过程中目标大小的变化、光照的变化以及噪声等具有较好的鲁棒性, 而且计算复杂度小, 能够实现实时监控.