The traffic accident is one of the most frequent cause of death in the world; and an important cause of the traffic accident is the fatigue of the driver, who falls asleep during driving. To overcome this problem in this paper, we propose a real-time driver drowsiness detection system, in which the driver's face region is extracted and introduced into a specific designed shallow convolutional neural network (SS-CNN). The SS-CNN detects the state of driver drowsiness using “eye closure” or “eye open” state. To distinguish between the “eye closed” state caused by normal eye blinking and that caused by drowsiness, the proposed system analyzes consecutive results of the SS-CNN. If the system determines that driver falls asleep, an alarm rings to awake the driver in order to avoid a possible accident. The proposed SS-CNN provides an accuracy of 98.95%, which outperforms the previous works. In the experimental section, we provide several links in which real-time operations of the proposed system can be observed.
In this paper, we propose a portable device named SOMN_IA, to detect drowsiness and distraction in drivers. The SOMN_IA can be installed inside of any type of vehicle, and it operates in real time, alerting the dangerous state caused by drowsiness and/or distraction in the driver. The SOMN_IA contains three types of alarm: light alarm, sound alarm, and the transmission of information about the driver’s dangerous state to a third party if the driver does not correct his/her dangerous state. The SOMN_IA contains a face detector and a classifier based on the convolutional neural networks (CNN), and it aids in the management of consecutive information, including isolated error correction mechanisms. All of the algorithmic parts of the SOMN_IA are analyzed and adjusted to operate in real-time in a portable device with limited computational power and memory space. The SOMN_IA requires only a buck-type converter to connect to the car battery. The SONM_IA discriminates correctly between real drowsiness and normal blinking, as well as between real dangerous distraction and a driver’s normal attention to his/her right and left. Although the real performance of the SOMN_IA is superior to the CNN classification accuracy thanks to isolated error correction, we compare the CNN classification accuracy with the previous systems.
Video surveillance systems are a key tool for the identification of anomalous events, but they still rely heavily on human analysis, which limits their efficiency. Current video anomaly detection models aim to automatically detect such events. However, most of them provide only a binary classification (normal or anomalous) and do not identify the specific type of anomaly. Although recent proposals address anomaly classification, they typically require full video analysis, making them unsuitable for online applications. In this work, we propose a modular framework for the joint detection and classification of anomalies, designed to operate on individual clips within continuous video streams. The architecture integrates interchangeable modules (feature extractor, detector, and classifier) and is adaptable to both offline and online scenarios. Specifically, we introduce a multi-category classifier that processes only anomalous clips, enabling efficient clip-level classification. Experiments conducted on the UCF-Crime dataset validate the effectiveness of the framework, achieving 74.77% clip-level accuracy and 58.96% video-level accuracy, surpassing prior approaches and confirming its applicability in real-world surveillance environments.
Video Anomaly Detection (VAD) is a well-established area of research with significant potential for enhancing video surveillance in urban public transportation. However, current VAD systems often propose powerful methodologies but overlook their use in extreme environments like public transportation, necessitating a balance between performance and computational efficiency. In this paper, we evaluate a key component in many VAD frameworks: feature extractors. We investigate five extractors: Inflated 3D ConvNets (I3D), 3D Convolutional Neural Networks (C3D), Unified Transformer (UniFormer) in Small (UniFormer-S) and Base (UniFormer-B) versions, and Temporal Shift Module (TSM). These are integrated into a VAD architecture employing Bidirectional Encoder Representations from Transformers (BERT) with Multiple Instance Learning (MIL), chosen for its modularity and clear separation between the feature extractor and anomaly detector module. UniFormer-S demonstrated a processing rate of 4.64 clips per second with a computational demand of 28.717 GFLOPs on edge devices like the Jetson Orin NX (8GB RAM, 20W power). On the UCF-Crime dataset, UniFormer-S with BERT + MIL achieves an AUC of 79.74%. These findings highlight the promise of UniFormer-S and the use of edge devices like the Jetson Orin NX in public transportation due to their balance of performance and efficiency.
In this paper we present an alternative distortion-free algorithm to ownership authentication and integrity veri-fication of digital images that use Contrastive Language-Image Pre-Training (CLIP), Vector Quantized Generative Adversarial Network (VQGAN) and a custom signature based on crypto-graphic message digest. Authentication and integrity of digital media are evaluated by the naked eye, as shown in the output of the generative architecture, as well as numerical metrics such as PSNR and SSIM, respectively. The code is publicly available at https://github.com/JonathanFlores250/NoiseHashGAN.