A Cognitive Semantic-Based Approach for Human Event Detection in Videos

Anomaly detection in video is a challenging computer vision problem. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without full supervision. In this paper, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level. We first utilize a pre-trained detector to detect objects. Then, we train a 3D convolutional neural network to produce discriminative anomaly-specific information by jointly learning multiple proxy tasks: three self-supervised and one based on knowledge distillation. The self-supervised tasks are: (i) discrimination of forward/backward moving objects (arrow of time), (ii) discrimination of objects in consecutive/intermittent frames (motion irregularity) and (iii) reconstruction of object-specific appearance information. The knowledge distillation task takes into account both classification and detection information, generating large prediction discrepancies between teacher and student models when anomalies occur. To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture. Our lightweight architecture outperforms the state-of-the-art methods on three benchmarks: Avenue, ShanghaiTech and UCSD Ped2. Additionally, we perform an ablation study demonstrating the importance of integrating self-supervised learning and normality-specific distillation in a multi-task learning setting.

With rapid growth of egocentric videos from wearable devices, the need for instant video event detection is emerging. Different from conventional video event detection, it requires more considerations on real-time event detection and immediate video recording due to the computational cost on wearable devices (e.g., Google Glass). Conventional work of video event detection analyzed video content in an offline process and it is time-consuming for visual analysis. Observing that wearable devices are usually along with sensors, we propose a novel approach for instant event detection in egocentric videos by leveraging sensor-based motion context. We compute statistics of sensor data as features. Next, we predict the user's current motion context by a hierarchical model, and then choose the corresponding ranking model to rate the importance score of the timestamp. With importance score provided in real-time, camera on the wearable device can dynamically record micro-videos without wasting power and storage. In addition, we collected a challenging daily-life dataset called EDS (Egocentric Daily-life Videos with Sensor Data), which contains both egocentric videos and sensor data recorded by Google Glass of different subjects. We evaluate the performance of our system on the EDS dataset, and the result shows that our method outperforms other baselines.

Unsupervised anomaly detection defines an abnormal event as an event that does not conform to expected behavior. In the field of unsupervised anomaly detection, it is a pioneering work that leverages the difference between a future frame predicted by a generative adversarial network and its ground truth to detect an abnormal event. Based on the work, we improve the ability of video prediction framework to detect abnormal events by enhancing the difference between prediction results for normal and abnormal events. We incorporate super-resolution and self-attention mechanism to design a generative adversarial network. We propose an auto-encoder as a generator, which incorporates dense residual networks and self-attention. Moreover, we propose a new discriminator, which introduces self-attention on the basis of a relativistic discriminator. To predict a future frame with higher quality for normal events, we impose a constraint on the motion in video prediction by fusing optical flow and gradient difference between frames. We also introduce a perception constraint in video prediction to enrich the texture details of a frame. The AUC of our method on CUHK Avenue and Shanghai Tech datasets reaches 89.2% and 75.7% respectively, which is better than most existing methods. In addition, we propose a processing flow that can realize real-time anomaly detection in videos. The average running time of our video prediction framework is 37 frames per second. Among all real-time methods for abnormal event detection in videos, our method is competitive with the state-of-the-art methods.

Anomaly detection in crowd surveillance videos is a critical task for ensuring public safety and security. In this research paper, we propose a comprehensive framework for anomaly detection using deep learning techniques, specifically Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), and Generative Adversarial Networks (GANs). Our objective is to narrow the gap between computational complexity and detection effectiveness while satisfying the demand for explainability in anomaly detection systems. The proposed framework leverages the UCSD Ped2 dataset and focuses on incorporating spatial constraints to enhance anomaly detection performance. We introduce novel approaches for feature extraction and anomaly detection using GANs, aiming to capture essential spatial and temporal information while reducing computational complexity. Specifically, we develop encoders within the GAN framework to map input data to a lower-dimensional latent space and perform anomaly detection based on the similarity between latent codes. Through extensive experimentation and evaluation, we compare the performance of RNNs, CNNs, and GANs in detecting anomalies in crowd surveillance videos. Various evaluation metrics, including precision, recall, F1 score, ROC-AUC, and PR-AUC, is considered to assess the effectiveness of each approach. Additionally, they studied hyperparameters such as learning rate, batch size, network architecture, and GAN-specific parameters to optimize anomaly detection performance. Our results demonstrate the usefulness of the proposed framework in achieving robust and explainable anomaly detection in crowd surveillance videos. By combining advanced deep learning techniques with spatial constraints and explainability considerations, our research contributes to the development of more reliable and interpretable anomaly detection systems for real-world applications.

iSurveillance: Intelligent framework for multiple events detection in surveillance videos

The paper presents a novel approach for event detection in sports videos by topic based graphical model learning. The characteristics features defining various sport events are extracted by contextual grouping of low-level video and audio features using topic modeling. Event detection is performed by learning the structure of context based distribution of characteristic features by CRF based graphical model. Experimental evaluation of the proposed concept is presented on recorded video of Handball and Soccer game.

The thesis addresses the following challenging problems of detecting and tracking humans in the presence of occlusions in typical surveillance videos: (1) adaptation of semantic-part-based human detectors to new surveillance video sequence when trained detectors using other video data not performing well on the new video data; (2) tracking of humans with person identification minimizing identification errors over longer tracking periods; and (3) hierarchical spatial and temporal analysis for discriminative tracking of human targets. The thesis aims to improve the state-of-the-art performance in human detection and tracking by studying the human detectors, extended tracking of track segments (tracklets) generated from short term tracking of detection responses. For the adaptation of semantic-part-based human detectors to new surveillance video sequence, a uni ed deep CNN model for joint learning of features, semantic pedestrian part detectors and a transfer learning model is developed. The components within this deep CNN model interact with each other in the learning process, which facilitates the optimization of the learned components during the co-operative learning. In particular, an adaptation layer is proposed to embed the capability of knowledge transfer into the CNN model. As a result, the proposed transferred CNN (T-CNN) model is able to transfer the visual knowledge of the semantic pedestrian parts from the source data to target data. Extensive experimental evaluations show that the proposed method is better than other deep learning based methods in terms of detection performance. Moreover, the adaptive deep features can be complementary to the pre-defined features used by other state-of-the-art methods. For tracking of humans with person identification minimizing identification errors over longer tracking periods, a novel method, based on online target-specific metric learning and coherent dynamics estimation, for tracklet association by network flow optimization is developed. The proposed framework aims to exploit appearance and motion cues to prevent identity switches during tracking and also to recover missed detections. The target-specific metrics (appearance cue) and motion dynamics (motion cue) are proposed to be learned and estimated online, i.e. during the tracking process. Furthermore, a learning algorithm to learn the weights of motion and appearance tracking cues for tracklet affinity models is proposed to handle some difficult situations. Extensive evaluations following state-of-the-art practices have been conducted and the results from these evaluations show the improvements by the proposed method over some existing state-of-the-art methods. In hierarchical spatial and temporal analysis for discriminative tracking of human targets, inspired by recent advances in convolutional neural network (CNN) architectures, a novel uni ed deep model for tracklet association, which can jointly learn the CNNs and temporally constrained metrics, is developed. Furthermore, a novel loss function incorporating temporally constrained multi-task learning mechanism is developed to make the deep model more effective in solving the tracklet association problem. Extensive experimental results comparing with the state-of-the-art methods demonstrate the effectiveness and superiority of the proposed unified deep model.

Brightness guided preprocessing for automatic cold steel weapon detection in surveillance videos with deep learning

More than 80% of video surveillance systems are used for monitoring people. Old human detection algorithms, based on background and foreground modelling, could not even deal with a group of people, to say nothing of a crowd. Recent robust and highly effective pedestrian detection algorithms are a new milestone of video surveillance systems. Based on modern approaches in deep learning, these algorithms produce very discriminative features that can be used for getting robust inference in real visual scenes. They deal with such tasks as distinguishing different persons in a group, overcome problem with sufficient enclosures of human bodies by the foreground, detect various poses of people. In our work we use a new approach which enables to combine detection and classification tasks into one challenge using convolution neural networks. As a start point we choose YOLO CNN, whose authors propose a very efficient way of combining mentioned above tasks by learning a single neural network. This approach showed competitive results with state-of-the-art models such as FAST R-CNN, significantly overcoming them in speed, which allows us to apply it in real time video surveillance and other video monitoring systems. Despite all advantages it suffers from some known drawbacks, related to the fully-connected layers that obstruct applying the CNN to images with different resolution. Also it limits the ability to distinguish small close human figures in groups which is crucial for our tasks since we work with rather low quality images which often include dense small groups of people. In this work we gradually change network architecture to overcome mentioned above problems, train it on a complex pedestrian dataset and finally get the CNN detecting small pedestrians in real scenes.

Palm print scanning is a widespread method for biometric identity detection which has some advantages over other methods including its simplicity and relatively lower cost. In this study, a novel methods for biometric verification and identification by contactless palm scanning technique is proposed. In the study, Ripplet-I Transform (R-IT) which is a generalized form of Curvelet Transform (CuT), have been used in addition to multi-resolution transforms which were previously used in the literature as palm print verification and identification methods such as Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), Contourlet Transform (CoT). In addition, Principal Component Analysis (PCA) and Local Binary Pattern (LBP) have been utilized to increase the algorithm diversity. In order to investigate the effect of classification methods on the study results and the processing times, Artificial Neural Network (ANN), Euclidean Distance (ED) and Support Vector Machine (SVM) have been used separately for matching in the verification part of study. The performance of Convolutional Neural Network (CNN) as a classifier has also been examined. Verification and identification algorithms proposed in the study have been tested using palm print images of Hong Kong Polytechnic University Contact-free 3D/2D Hand Images Database (Version 1.0). The studies, that were carried out under two main sections yielded interesting results. At the end of the study, AUC (Area Under the ROC Curve) values ranging from 0.550 (Equal Error Rate (EER)= 0.4594) to 0.9875 (EER= 0.0336) were obtained for palm print verification. The highest AUC value without using LBP was obtained as 0.9563 (EER= 0.1096) using R-IT/CuT+DCT+CNN. Study results were showed that CNN is more successful than other classifiers without using LBP. It also has pointed out that the R-IT/CuT provides better results than the DWT and CoT. Using LBP in algorithms has increased success for ED, SVM and ANN. However, it has reduced overall for CNN. The highest AUC value (0.9875 and EER= 0.0336) was provided by the LBP+DWT+ED algorithm for palm print verification. The highest Identification Rate (IR) was achieved by using the LBP+CoT+ED algorithm with 84.444% for for palm print identification.

In order to overcome the effects of posture, illumination, expression and other factors on face recognition, this paper proposes an algorithm which is based on local binary pattern (LBP) and convolutional neural network (CNN). LBP is a texture description method which describes the local texture features of an image. It has good robustness of illumination and posture. CNN can effectively extract the spatial features of images and reduce the dimensions of features. This paper combines the advantages of LBP and CNN to improve the accuracy of face recognition. The CNN in this algorithm has four convolution layers, two max-pooling layers, one activation layer, one fully connected layer, and one output layer. In order to optimize the network structure, batch normalization layer is added after the convolution layer. We get the local binary pattern coded images and put the images as the input of the CNN and train the network. Hence, we can use the well-trained CNN for classification and identification. The Experiments on the CMU-PIE face database show that our algorithm can effectively improve the rate of face recognition.

In fuzzy C-means (FCM) clustering, each data point belongs to a cluster to a degree specified by a membership grade. FCM partitions a collection of vectors in c fuzzy groups and finds a cluster center in each group such that the dissimilarity measure is minimized. This paper presents a training algorithm for the radial basis function (RBF) network using symmetry-based Fuzzy C-means (SFCM) clustering method which is the modified version of FCM clustering method based on point symmetry distance measure. The training algorithm which uses SFCM clustering method to train the network has a number of advantages such as faster training time, more accurate predictions and reduced network architecture compared to the standard RBF networks. The proposed training algorithm has been implemented in the RBF networks created by the newrb function of MATLAB which uses gradient based iterative method as learning strategy, therefore the new network will undergo a hybrid learning process. The networks called Symmetry-based Fuzzy C-means Clustering–Radial Basis Function Network (SFCM/RBF) has been tested against the standard RBF network and the networks called standard Fuzzy C-means Clustering (FCM)-RBF network (FCM/RBF) in forecasting. The experimental models has been tested on three real world application problems, particularly in Air pollutant problem, Biochemical Oxygen Demand (BOD) problem, and Phytoplankton problem. Keywords: Fuzzy c-means clustering; SFCM; Radial basis function network; point symmetry distance; forecasting.

This paper describes a new approach for eventdetection in video sequences. A tracking algorithm for obliquecamera setups is initially used to extract trajectories in a trainingperiod, and a map of spatial occupancy of the scene is built. In thetest stage, Voronoi Diagrams are used to obtain some informationregarding interpersonal relationships, such as distances fromneighbors, formation and classification of groups. A variety ofcomplex events can be detected through a query formulated bythe user, that may combine concurrent or sequential occurrencesof simpler events based on either spatial occupancy or interpersonalrelationships (e.g. group formation in a region with smallspatial occupancy). These queries can be used to detect eventson-the-fly as the video is processed, or applied to stored videodatabases.

In this paper, global abnormal events detection in the crowded scene is proposed. The proposed algorithm is based on a hierarchical approach. The method uses the histogram of optical flow orientation as a feature descriptor along with the magnitude of the optical flow to capture the motion. The nonlinear one-class support vector machine (SVM) classification algorithm is used to learn the normal events from the training data. After learning, one-class SVM detects abnormal events in the frame. The algorithm is fast with improved accuracy since it omits the background subtraction step and adopts hierarchy. The proposed method is tested on benchmark UMN unusual crowd activity dataset which contain global abnormal events. Promising results are reported which evaluates the performance of the proposed method.

Crowd Event Detection in Surveillance Video - An Approach based on Optical Flow High-frequency Feature Analysis