Unusual human behavior recognition using evolutionary technique

The vision for surveillance is an important task in many computer vision applications. The monitoring system concerns the tracking and recognition of people, and more generally, the understanding of human behaviors, from image sequences involving humans. Several methods for human tracking and human behavior recognition have been proposed by various researchers. But most of those do not have versatility and flexibility. In this paper, we propose an efficient and robust object tracking algorithm which use the color features, the distance features and count feature based on an evolutionary techniques to measure the observation similarity. And then we will track each person and classify their behavior properties by analyzing their trajectory pattern. We propose multi-layer perceptron based on hybrid genetic algorithm using Gaussian synapse make the recognition algorithm very efficient and robust for classify human behavior by trajectory pattern.     

Constrained self-organizing feature map to preserve feature extraction topology

In many classification problems, it is necessary to consider the specific location of an n-dimensional space from which features have been calculated. For example, considering the location of features extracted from specific areas of a two-dimensional space, as an image, could improve the understanding of a scene for a video surveillance system. In the same way, the same features extracted from different locations could mean different actions for a 3D HCI system. In this paper, we present a self-organizing feature map able to preserve the topology of locations of an n-dimensional space in which the vector of features have been extracted. The main contribution is to implicitly preserving the topology of the original space because considering the locations of the extracted features and their topology could ease the solution to certain problems. Specifically, the paper proposes the n-dimensional constrained self-organizing map preserving the input topology (nD-SOM-PINT). Features in adjacent areas of the n-dimensional space, used to extract the feature vectors, are explicitly in adjacent areas of the nD-SOM-PINT constraining the neural network structure and learning. As a study case, the neural network has been instantiate to represent and classify features as trajectories extracted from a sequence of images into a high level of semantic understanding. Experiments have been thoroughly carried out using the CAVIAR datasets (Corridor, Frontal and Inria) taken into account the global behaviour of an individual in order to validate the ability to preserve the topology of the two-dimensional space to obtain high-performance classification for trajectory classification in contrast of non-considering the location of features. Moreover, a brief example has been included to focus on validate the nD-SOM-PINT proposal in other domain than the individual trajectory. Results confirm the high accuracy of the nD-SOM-PINT outperforming previous methods aimed to classify the same datasets.

     

基于HMM的车辆行驶状态实时判别方法研究

对交通视频车辆轨迹时序特征下的车辆行驶状态进行研究,提出了一种基于隐马尔科夫模型（Hidden Markov model,HMM）的车辆行驶状态实时判别方法.首先对轨迹序列进行了基于轨迹长度的去不完整轨迹序列、对车辆轨迹点序列的线 性平滑滤波和最小二乘线性拟合的预处理操作,保证了所获得轨迹序列的有效性;其次,提出一种基于车辆运行轨迹点序列方向角的车辆轨迹特征值表示方法和基于方向角区间划分的HMM观察值序列生成方法,该方法以方向角的区间变化来区分不同轨迹模式的特征;最后,采用多观察值序列下的Baum-Welch 算法训练得到相关交通场景轨迹模式类的最优HMM 参数,并通过实时获取车辆行驶轨迹段与相应模型的匹配,实现对车辆行驶状态的实时判别. 仿真实验验证了本文方法的有效性和稳定性.     

一种基于Kalman滤波的视频对象跟踪方法

为了更加准确地预测对象的位置和运动，利用刚体运动模型导出最佳Kalman系数，通过Kalman反馈滤波器对Moscheni等人提出的视频对象分割与跟踪算法进行改进，提出了一种将离散Kalman滤波技术用于视频序列的对象跟踪方法。这种方法可用于有关场景描述的各种应用领域中，如在机器视觉的研究中，对动态场景进行分析与理解；在基于对象的视频编码中（如MPEG-4），对视频对象进行分割后，分别进行编码，从而改善编码的可分级性及编码效率。实验结果表明，采用这种方法可以有效地改善时间-空间分割和目标跟踪，有助于更好地理解动态场景，并表现出良好的鲁棒性。     

Human action recognition based on scene semantics

Like outdoors, indoor security is also a critical problem and human action recognition in indoor area is still a hot topic. Most studies on human action recognition ignored the semantic information of a scene, whereas indoors contains varieties of semantics. Meanwhile, the depth sensor with color and depth data is more suitable for extracting the semantics context in human actions. Hence, this paper proposed an indoor action recognition method using Kinect based on the semantics of a scene. First, we proposed a trajectory clustering algorithm for a three-dimensional (3D) scene by combining the different characteristics of people such as the spatial location, movement direction, and speed. Based on the clustering results and scene context, it concludes a region of interest (ROI) extraction method for indoors, and dynamic time warping (DTW) is used to study the abnormal action sequences. Finally, the color and depth-data-based 3D motion history image (3D–MHI) features and the semantics context of the scene were combined to recognize human action. In the experiment, two datasets were tested and the results demonstrate that our semantics-based method performs better than other methods.

     

Detection and Recognition of Periodic,Nonrigid Motion

The recognition of nonrigid motion, particularly that arising from human movement (and by extension from the locomotory activity of animals) has typically made use of high-level parametric models representing the various body parts (legs, arms, trunk, head etc.) and their connections to each other. Such model-based recognition has been successful in some cases; however, the methods are often difficult to apply to real-world scenes, and are severely limited in their generalizability. The first problem arises from the difficulty of acquiring and tracking the requisite model parts, usually specific joints such as knees, elbows or ankles. This generally requires some prior high-level understanding and segmentation of the scene, or initialization by a human operator. The second problem, with generalization, is due to the fact that the human model is not much good for dogs or birds, and for each new type of motion, a new model must be hand-crafted. In this paper, we show that the recognition of human or animal locomotion, and, in fact, any repetitive activity can be done using low-level, non-parametric representations. Such an approach has the advantage that the same underlying representation is used for all examples, and no individual tailoring of models or prior scene understanding is required. We show in particular, that repetitive motion is such a strong cue, that the moving actor can be segmented, normalized spatially and temporally, and recognized by matching against a spatio-temporal template of motion features. We have implemented a real-time system that can recognize and classify repetitive motion activities in normal gray-scale image sequences. Results on a number of real-world sequences are described.     

MyWay: Location prediction via mobility profiling

Forecasting the future positions of mobile users is a valuable task allowing us to operate efficiently a myriad of different applications which need this type of information. We propose MyWay, a prediction system which exploits the individual systematic behaviors modeled by mobility profiles to predict human movements. MyWay provides three strategies: the individual strategy uses only the user individual mobility profile, the collective strategy takes advantage of all users individual systematic behaviors, and the hybrid strategy that is a combination of the previous two. A key point is that MyWay only requires the sharing of individual mobility profiles, a concise representation of the user׳s movements, instead of raw trajectory data revealing the detailed movement of the users. We evaluate the prediction performances of our proposal by a deep experimentation on large real-world data. The results highlight that the synergy between the individual and collective knowledge is the key for a better prediction and allow the system to outperform the state-of-art methods.     

Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

In this paper, we propose a computational model of the recognition of real world scenes that bypasses the segmentation and the processing of individual objects or regions. The procedure is based on a very low dimensional representation of the scene, that we term the Spatial Envelope. We propose a set of perceptual dimensions (naturalness, openness, roughness, expansion, ruggedness) that represent the dominant spatial structure of a scene. Then, we show that these dimensions may be reliably estimated using spectral and coarsely localized information. The model generates a multidimensional space in which scenes sharing membership in semantic categories (e.g., streets, highways, coasts) are projected closed together. The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.     

运动序列的时空结构特征表示模型

运动序列是一种与运动信号相关的多维时间序列,各个维度序列之间具有高耦合性的特点。现有的多维序列表征方法大多基于维度间相互独立的假设或缺乏可解释性,为此,提出一种适用于运动序列的时空结构特征表示模型及其两阶段构造方法。首先,基于空间变化事件的转换方法,将多维时间序列变换成一维事件序列,以保存序列中的空间结构特性。接着,定义了一种时空结构特征的无监督挖掘算法。基于新定义的表示度度量,该算法从事件序列中提取一组具有代表性的低冗余变长事件元组为时空结构特征。在多个人类行为识别数据集上的实验结果表明,与现有多维时间序列表示方法相比,新模型的特征集更具代表性,在运动序列模式识别领域可以有效提升分类精度。     

genEnsemble: A new model for the combination of classifiers and integration of biological knowledge applied to genomic data

In the last years, microarray technology has become widely used in relevant biomedical areas such as drug target identification, pharmacogenomics or clinical research. However, the necessary prerequisites for the development of valuable translational microarray-based diagnostic tools are (i) a solid understanding of the relative strengths and weaknesses of underlying classification methods and (ii) a biologically plausible and understandable behaviour of such models from a biological point of view. In this paper we propose a novel classifier able to combine the advantages of ensemble approaches with the benefits obtained from the true integration of biological knowledge in the classification process of different microarray samples. The aim of the current work is to guarantee the robustness of the proposed classification model when applied to several microarray data in an inter-dataset scenario. The comparative experimental results demonstrated that our proposal working with biological knowledge outperforms other well-known simple classifiers and ensemble alternatives in binary and multiclass cancer prediction problems using publicly available data.     

Individual recognition using gait energy image

In this paper, we propose a new spatio-temporal gait representation, called gait energy image (GEI), to characterize human walking properties for individual recognition by gait. To address the problem of the lack of training templates, we also propose a novel approach for human recognition by combining statistical gait features from real and synthetic templates. We directly compute the real templates from training silhouette sequences, while we generate the synthetic templates from training sequences by simulating silhouette distortion. We use a statistical approach for learning effective features from real and synthetic templates. We compare the proposed GEI-based gait recognition approach with other gait recognition approaches on USF HumanID Database. Experimental results show that the proposed GEI is an effective and efficient gait representation for individual recognition, and the proposed approach achieves highly competitive performance with respect to the published gait recognition approaches.     

Activity based surveillance video content modelling

This paper tackles the problem of surveillance video content modelling. Given a set of surveillance videos, the aims of our work are twofold: firstly a continuous video is segmented according to the activities captured in the video; secondly a model is constructed for the video content, based on which an unseen activity pattern can be recognised and any unusual activities can be detected. To segment a video based on activity, we propose a semantically meaningful video content representation method and two segmentation algorithms, one being offline offering high accuracy in segmentation, and the other being online enabling real-time performance. Our video content representation method is based on automatically detected visual events (i.e. ‘what is happening in the scene’). This is in contrast to most previous approaches which represent video content at the signal level using image features such as colour, motion and texture. Our segmentation algorithms are based on detecting breakpoints on a high-dimensional video content trajectory. This differs from most previous approaches which are based on shot change detection and shot grouping. Having segmented continuous surveillance videos based on activity, the activity patterns contained in the video segments are grouped into activity classes and a composite video content model is constructed which is capable of generalising from a small training set to accommodate variations in unseen activity patterns. A run-time accumulative unusual activity measure is introduced to detect unusual behaviour while usual activity patterns are recognised based on an online likelihood ratio test (LRT) method. This ensures robust and reliable activity recognition and unusual activity detection at the shortest possible time once sufficient visual evidence has become available. Comparative experiments have been carried out using over 10 h of challenging outdoor surveillance video footages to evaluate the proposed segmentation algorithms and modelling approach.     

边缘与灰度检测相结合的场景图像文本定位

自然场景图像中包含大量的图像和文本信息,其文本字符能够提供重要的语义信息。利用计算机自动检测并识别自然场景中的文本信息,是模式识别和文字信息处理领域重要的研究内容。本文提出一种有效的从场景图像中定位文本的方法,其原理为：首先基于边缘检测进行文本区域粗定位,对定位到的区域进行灰度检测,来确定文本域中的字符位置,其后对所得到的检测区域进行筛选,去掉噪声区域,获取到目标文本域。实验结果表明,本文提出的方法对字体的大小、样式、颜色、以及排布方向具有较强的鲁棒性, 能够准确定位并提取自然场景下的文本信息。     

无需跟踪的场景事件识别

提出了一种用于视觉监控中行为识别的新颖方法.该方法将相应于目标行为的场景事件建模为一组使用PCH(Pixel Cllange Histories)检测的自治像素级事件.结合基于改进的MDL (Minimum DescrlptIon Length)的自动模型规则选择,EM(Expectation-Maximisation)算法被采用来聚类这些像素级的自治事件成为语义上更有意义的区域级的场景事件.该方法是计算上有效的,实验结果验证了它在不需匹配目标轨迹的情况下自动识别场景事件的有效性.     

People Watching: Human Actions as a Cue for Single View Geometry

We present an approach which exploits the coupling between human actions and scene geometry to use human pose as a cue for single-view 3D scene understanding. Our method builds upon recent advances in still-image pose estimation to extract functional and geometric constraints on the scene. These constraints are then used to improve single-view 3D scene understanding approaches. The proposed method is validated on monocular time-lapse sequences from YouTube and still images of indoor scenes gathered from the Internet. We demonstrate that observing people performing different actions can significantly improve estimates of 3D scene geometry.     

Video behavior profiling for anomaly detection

This paper aims to address the problem of modelling video behaviour captured in surveillancevideos for the applications of online normal behaviour recognition and anomaly detection. A novelframework is developed for automatic behaviour profiling and online anomaly sampling/detectionwithout any manual labelling of the training dataset. The framework consists of the followingkey components: (1) A compact and effective behaviour representation method is developed basedon discrete scene event detection. The similarity between behaviour patterns are measured basedon modelling each pattern using a Dynamic Bayesian Network (DBN). (2) Natural grouping ofbehaviour patterns is discovered through a novel spectral clustering algorithm with unsupervisedmodel selection and feature selection on the eigenvectors of a normalised affinity matrix. (3) Acomposite generative behaviour model is constructed which is capable of generalising from asmall training set to accommodate variations in unseen normal behaviour patterns. (4) A run-timeaccumulative anomaly measure is introduced to detect abnormal behaviour while normal behaviourpatterns are recognised when sufficient visual evidence has become available based on an onlineLikelihood Ratio Test (LRT) method. This ensures robust and reliable anomaly detection and normalbehaviour recognition at the shortest possible time. The effectiveness and robustness of our approachis demonstrated through experiments using noisy and sparse datasets collected from both indoorand outdoor surveillance scenarios. In particular, it is shown that a behaviour model trained usingan unlabelled dataset is superior to those trained using the same but labelled dataset in detectinganomaly from an unseen video. The experiments also suggest that our online LRT based behaviourrecognition approach is advantageous over the commonly used Maximum Likelihood (ML) methodin differentiating ambiguities among different behaviour classes observed online.