Inflated 3D ConvNet context analysis for violence detection

According to the Wall Street Journal, one billion surveillance cameras will be deployed around the world by 2021. This amount of information can be hardly managed by humans. Using a Inflated 3D ConvNet as backbone, this paper introduces a novel automatic violence detection approach that outperforms state-of-the-art existing proposals. Most of those proposals consider a pre-processing step to only focus on some regions of interest in the scene, i.e., those actually containing a human subject. In this regard, this paper also reports the results of an extensive analysis on whether and how the context can affect or not the adopted classifier performance. The experiments show that context-free footage yields substantial deterioration of the classifier performance (2% to 5%) on publicly available datasets. However, they also demonstrate that performance stabilizes in context-free settings, no matter the level of context restriction applied. Finally, a cross-dataset experiment investigates the generalizability of results obtained in a single-collection experiment (same dataset used for training and testing) to cross-collection settings (different datasets used for training and testing).

Multi-Level Two-Stream Fusion-Based Spatio-Temporal Attention Model for Violence Detection and Localization

Detection of violent human behavior is necessary for public safety and monitoring. However, it demands constant human observation and attention in human-based surveillance systems, which is a challenging task. Autonomous detection of violent human behavior is therefore essential for continuous uninterrupted video surveillance. In this paper, we propose a novel method for violence detection and localization in videos using the fusion of spatio-temporal features and attention model. The model consists of Fusion Convolutional Neural Network (Fusion-CNN), spatio-temporal attention modules and Bi-directional Convolutional LSTMs (BiConvLSTM). The Fusion-CNN learns both spatial and temporal features by combining multi-level inter-layer features from both RGB and Optical flow input frames. The spatial attention module is used to generate an importance mask to focus on the most important areas of the image frame. The temporal attention part, which is based on BiConvLSTM, identifies the most significant video frames which are related to violent activity. The proposed model can also localize and discriminate prominent regions in both spatial and temporal domains, given the weakly supervised training with only video-level classification labels. Experimental results evaluated on different publicly available benchmarking datasets show the superior performance of the proposed model in comparison with the existing methods. Our model achieves the improved accuracies (ACC) of 89.1%, 99.1% and 98.15% for RWF-2000, HockeyFight and Crowd-Violence datasets, respectively. For CCTV-FIGHTS dataset, we choose the mean average precision (mAp) performance metric and our model obtained 80.7% mAp.

Development of 3D convolutional neural network to recognize human activities using moderate computation machine

Human activity recognition (HAR) is recently used in numerous applications including smart homes to monitor human behavior, automate homes according to human activities, entertainment, falling detection, violence detection, and people care. Vision-based recognition is the most powerful method widely used in HAR systems implementation due to its characteristics in recognizing complex human activities. This paper addresses the design of a 3D convolutional neural network (3D-CNN) model that can be used in smart homes to identify several numbers of activities. The model is trained using KTH dataset that contains activities like (walking, running, jogging, handwaving handclapping, boxing). Despite the challenges of this method due to the effectiveness of the lamination, background variation, and human body variety, the proposed model reached an accuracy of 93.33%. The model was implemented, trained and tested using moderate computation machine and the results show that the proposal was successfully capable to recognize human activities with reasonable computations.

Deep Learning and Mel-spectrograms for Physica Violence Detection in Audio

Há um crescente interesse em sistemas de detecção de violência de forma automática por meio do áudio ambiente. Neste trabalho, construímos e avaliamos 4 classificadores com essa proposta. Porém, em vez de processar diretamente os sinais de áudio, nós os convertemos para imagens, conhecidas como mel-spectrograms, e em seguida utilizamos Redes Neurais Convolucionais (CNN) para tratar como um problema de classificação de imagens utilizando-se de redes pre-treinadas neste contexto. Testou-se as arquiteturas Inception v3, VGG-16, MobileNet v2 e ResNet152 v2, tendo o classificador oriundo da arquitetura MobileNet obtido os melhores resultados de classificação, quando avaliado no HEAR Dataset, criado para a realização desta pesquisa.

Violence Detection in Ranches Using Computer Vision and Convolution Neural Network

This study engaged the convolutional neural network in curbing losses in terms of resources that farmers spends in treating animals where injuries must have emancipated from violence among other animals and in worst case scenario could eventually lead to death of animals. Animals in a ranch was the target and the study proposed a method that detects and reports activities of violence to ranchers such that farmers are relieved of the stress of close supervision and monitoring to avoid violence among animals. The scope of the study is limited to violence detection in cattle, goat, horse and sheep. Different machine learning models were built for each animal. The models yielded good results; the horse violence detection model had an outstanding performance of 93% accuracy, 93% accuracy for the sheep model, 88% accuracy for the goat model and 84% accuracy for the cattle model.

Effectiveness of Synthetic Images in Violence Detection

This paper shows that using synthetic images for violence detection is a feasible option for training deep models, they aid in quick convergence and perform better.

Effectiveness of Synthetic Images in Violence Detection

This paper shows that using synthetic images for violence detection is a feasible option for training deep models, they aid in quick convergence and perform better.