Crowd Scene Analysis Encounters High Density and Scale Variation.

Crowd scene analysis is the certification tasks in crowded scene understanding. Crowd is a same or different set of people arranged in one group. Generally crowd form in the way of pedestrians, supermarket, and marathons. In this paper introduce Convolution Neural Networks and deep learning model is used for the analysis of crowd scene. In these paper propose, findings the number of people arrived in one group and also finds the crowd density map. People counting in extremely dense crowds are an important step for video surveillance and anomaly warning. The above mentioned works, Several problems becomes especially more challenging due to the lack of training samples, severe blockages, disorder scenes, and modification of perspective. In existing methods estimating crowd count using handcrafted features such as SIFTS and HOG. In current vision most suited method is to predict the better performance of estimating crowd density and crowd count based on deep learning network. Lucas kanade optical flow can finds the displacement vector between two consecutive frames. 3D volumes video slices can be arranged in sequential manner. In this crowd scene analysis represents convolutional crowd dataset as 100 videos from 800 crowd scenes and build an attribute set with 94 attributes.

Crowd counting based on density maps is generally regarded as a regression task. Deep learning is used to learn the mapping between image content and crowd density distribution. Although great success has been achieved, some pedestrians far away from the camera are difficult to be detected. And the number of hard examples is often larger. Existing methods with simple Euclidean distance algorithm indiscriminately optimize the hard and easy examples so that the densities of hard examples are usually incorrectly predicted to be lower or even zero, which results in large counting errors. To address this problem, we are the first to propose the hard example focusing (HEF) algorithm for the regression task of crowd counting. The HEF algorithm makes our model rapidly focus on hard examples by attenuating the contribution of easy examples. Then higher importance will be given to the hard examples with wrong estimations. Moreover, the scale variations in crowd scenes are large, and the scale annotations are labor-intensive and expensive. By proposing a multiscale semantic refining strategy, lower layers of our model can break through the limitation of deep learning to capture semantic features of different scales to sufficiently deal with the scale variation. We perform extensive experiments on six benchmark datasets to verify the proposed method. Results indicate the superiority of our proposed method over the state-of-the-art methods. Moreover, our designed model is smaller and faster.

Automated people counting in crowd scenes is challenging due to large variations in scale, density, and background clutter. To tackle them, we propose a novel cross-level parallel network (CLPNet) by extracting multiple low-level features from VGG16 and fusing them with specific scale aggregation modules in the high-level stage. To deal with scale variation, we design five different aggregation modules for multiscale fusion. Furthermore, the ground truth is processed skillfully to eliminate the mismatches caused by the scale variation between heads and density maps. To cope with background clutter, cross-level feature fusion is implemented. Higher-level semantic information could effectively separate head from background and regain the lost low-level detailed information. To address the variation of density, we design a parallel network, in which two separate channels focus on different density-level estimation, and attain more accurate counting results. Finally, we evaluate the proposed CLPNet on four representative crowd counting datasets, i.e., ShanghaiTech, UCF_CC_50, WorldExpo'10, and UCF_QNRF. The experimental results demonstrate that with the cross-level and multiscale structure CLPNet achieves superior performance compared with the state-of-the-art crowd counting methods.

In this paper, we propose a new approach for recognizing group events and abnormality detection in a crowded scene. A manifold learning algorithm with temporal-constraints is proposed to embed a video of a crowded scene in a low-dimensional space. Our low dimensional representation of a video preserves the spatial temporal property of a video as well as the characteristic of the video. Recognizing video events and abnormality detection in a crowded scene is achieved by studying the video trajectory in the manifold space. We evaluate our proposed method on the state-of-the-art public data-sets containing different crowd events. Qualitative and quantitative results show the promising performance of the proposed method.

Head detection-based crowd counting is of great importance and serves as a preprocessing step in many visual applications, for example, counting, tracking, and crowd dynamics understanding. Despite significant importance, limited amount of work is reported in the literature to detect human heads in high-density crowds. The problem of detecting heads in crowded scenes is challenging due to significant scale variations in the scene. In this paper, we tackle this problem by exploiting contextual constraints offer by the crowded scenes. For this purpose, we propose two networks, i.e., sparse-scale convolutional neural network (SS-CNN) and dense-scale convolutional neural network (DS-CNN). SS-CNN detects human heads with coarse information about the scales in the image. DS-CNN utilizes detection obtained from SS-CNN and generates dense scalemap by globally reasoning the coarse scales of detections obtained from SS-CNN via Markov Random Field (MRF). The dense scalemap has unique property that it captures all scale variations in image and provides an aid in generating scale-aware proposals. We evaluated our framework on three challenging state-of-the-art datasets, i.e., UCF-QNRF, WorldExpo’10, and UCF_CC_50. Experiment results show that proposed framework outperforms existing state-of-the-art methods.

In this paper, we target on the problem of estimating the statistic of pedestrian travel time within a period from an entrance to a destination in a crowded scene. Such estimation is based on the global distributions of crowd densities and velocities instead of complete trajectories of pedestrians, which cannot be obtained in crowded scenes. The proposed method is motivated by our statistical investigation into the correlations between travel time and global properties of crowded scenes. Active regions are created for each source-destination pair to model the probable walking regions over the corresponding source-destination traffic flow. Two sets of scene features are specially designed for modeling moving and stationary persons inside the active regions and their influences on pedestrian travel time. The estimation of pedestrian travel time provides valuable information for both crowd scene understanding and pedestrian behavior analysis, but was not sufficiently studied in literature. The effectiveness of the proposed pedestrian travel time estimation model is demonstrated through several surveillance applications, including dynamic scene monitoring, localization of regions blocking traffics, and detection of abnormal pedestrian behaviors. Many more valuable applications based on our method are to be explored in the future.

Video analysis of crowded scenes is challenging due to the complex motion of individual people in the scene. The collective motion of pedestrians form a crowd flow, but individuals often largely deviate from it as they anticipate and react to each other. Deviations from the crowd decreases the pedestrian’s efficiency: a sociological concept that measures the difference of actual motion from the intended speed and direction. In this paper, we derive a novel method for estimating pedestrian efficiency from videos. We first introduce a novel crowd motion model that encodes the temporal evolution of local motion patterns represented with directional statistics distributions. This model is then used to estimate the intended motion of pedestrians at every space-time location, which enables visual measurement of the pedestrian efficiency. We demonstrate the use of this pedestrian efficiency to detect unusual events and to track individuals in crowded scenes. Experimental results show that the use of pedestrian efficiency leads to state-of-the-art accuracy in these critical applications.KeywordsAnomaly DetectionEmergent BehaviorIntended MotionSocial Force ModelCrowded SceneThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Spatio-temporal context analysis within video volumes for anomalous-event detection and localization

In this paper, a new method for detecting abnormal events in public surveillance systems is proposed. In the first step of the proposed method, candidate regions are extracted, and the redundant information is eliminated. To describe appearance and motion of the extracted regions, HOG-LBP and HOF are calculated for each region. Finally, abnormal events are detected using two distinct one-class SVM models. To achieve more accurate anomaly localization, the large regions are divided into non-overlapping cells, and the abnormality of each cell is examined separately. Experimental results show that the proposed method outperforms existing methods based on the UCSD anomaly detection video datasets.

Anomaly event detection in crowd scenes is extremely important; however, the majority of existing studies merely use hand-crafted features to detect anomalies. In this study, a novel unsupervised deep learning framework is proposed to detect anomaly events in crowded scenes. Specifically, low-level visual features, energy features, and motion map features are simultaneously extracted based on spatiotemporal energy measurements. Three convolutional restricted Boltzmann machines are trained to model the mid-level feature representation of normal patterns. Then a multimodal fusion scheme is utilized to learn the deep representation of crowd patterns. Based on the learned deep representation, a one-class support vector machine model is used to detect anomaly events. The proposed method is evaluated using two available public datasets and compared with state-of-the-art methods. The experimental results show its competitive performance for anomaly event detection in video surveillance.

A method of estimating the number of people in crowded scenes was proposed based on energy of the foreground image in the frequency domain. Firstly, the foreground image including the target area was obtained by background subtraction. And furthermore, with the second order wavelet decomposition of the foreground image, the energy of high frequency sub-band was computed. Finally, by analyzing the relation between population size and high frequency sub-band energy, the mathematical model was established and the model was solved by the least square method. The experimental results show that the proposed method is highly effective for estimating the number of moving people in crowded scenes.

A crowd is a gathering of a huge number of individuals in a confined area. Early identification and detection of unusual behaviors in terms of panic occurring in crowded scenes are very important. Panic detection comprises of formulating normal scene behaviors and detecting and identifying non-matching behaviors. However, panic detection and recognition is a very difficult problem, especially when considering diverse scenes. Many methods proposed to cope with these problems have limited robustness as the density of the crowd varies. In order to handle this challenge, this paper proposes the integration of different features into a unified model. Discriminant binary patterns and neighborhood information are used to model complex and unique motion patterns in order to characterize different levels of features for diverse types of crowd scenes, focusing in particular on the detection of panic and non-pedestrian entities. The proposed method was evaluated considering two benchmark datasets and outperformed five existing methods.

In this paper, we propose a novel method for global abnormal events detection in crowded scenes. Each video is described as the set of overlapping space-time cubes. The histogram of optical flow orientation and motion magnitude are used as global feature descriptor to capture the motion magnitude and orientation of the normal and abnormal events. The motion-rich space-time cubes are selected to enhance the computational speed of the algorithm and omit background subtraction step, forms the proposed approach novel and unique. Simple and cost-effective one-class SVM classifier is used to distinguish between normal and abnormal events in a video. The one-class SVM classifier is trained with normal events from the training data. The proposed method is tested on benchmark UMN and PETS2009 dataset. The improved results are reported to evaluate the performance of the proposed method.

Anomaly detection in crowd scene has attracted an increasing attention in video surveillance, but a precise detection still remains a challenge. This paper presents a novel online learning method to automatically detect abnormal behaviors in crowd scene. Our focus is mainly on the deviation between the real motion and the predicted one. Through online defining experts, analyzing their motions, and dynamically updating the learned model, anomaly can be identified by the final expert joint decision. The outputs are represented as the anomaly probability of an examined frame. Compared with most of existing methods, the proposed one needs neither tracking each individual straight to the end nor requires any complex training procedure. We test the proposed method on public datasets, and the results show its effectiveness.

This paper describes accurate position control in an object coordinate system. When motion control of an industrial robot placed in a global coordinate system is taken to be in an object coordinate system, it is preferable and convenient to decide its motion by having the operator teach the robot. However, the teaching procedure requires considerable time and effort. Moreover, whenever the relative position between the robot and the object is changed, the operator needs to teach the operation again. To improve the above issue, a strategy that decides the robot motion without the teaching must be developed. This paper proposes a control strategy that does not require teaching and enables the creation of the desired motion without affecting the relative position error between the robot and the target object in object coordinate space defined by a PSD (Position Sensor Detector). In the proposed approach, the estimation algorithm of the kinetic transformation between the global and the object coordinates is introduced by using PSD output, and the error of coordinate transformation estimated by the proposed approach is compensated for in the global coordinate system. The validity of the proposed method is shown using simulations and experiments. © 2006 Wiley Periodicals, Inc. Electr Eng Jpn, 155(3): 53–61, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.20354