Real-Time Mask-wearing Detection on Edge Devices via Lightweight Convolutional Neural Networks

A LIGHTWEIGHT CNN-BASED ANDROID VISION SYSTEM FOR REAL-TIME DRIVER DROWSINESS DETECTION USING EYE-STATE ANALYSIS

Driver drowsiness remains one of the leading causes of road traffic accidents worldwide, as fatigue significantly impairs a driver's alertness, reaction time, and decision-making ability. Existing drowsiness detection approaches often require specialized hardware or computationally intensive models that limit their deployment on resource-constrained mobile devices. This study presents a lightweight CNN-based Android vision system for real-time driver drowsiness detection using eye-state analysis. The proposed system combines Haar Cascade classifiers for real-time face and eye localization with a custom Convolutional Neural Network (CNN) for classifying eye states as open or closed. A score-based decision mechanism continuously monitors eye closure across successive video frames and activates an audible alarm when prolonged eye closure indicates possible driver fatigue. The CNN model was trained using labeled eye-image datasets in Python with the Keras deep learning framework and subsequently integrated into an Android application for real-time inference using a smartphone camera. Experimental evaluation demonstrated that the developed system accurately classified eye states and generated timely drowsiness alerts under real-time operating conditions while maintaining computational efficiency suitable for mobile deployment. The findings demonstrate that lightweight deep learning models can be effectively deployed on Android devices to provide an accessible, low-cost, and practical solution for continuous driver drowsiness monitoring and improved road safety.

Face Mask Detection Using Deep Learning: A Comparative Study of CNN, VGG16 and MobileNetV2 for Real-Time Applications

The COVID-19 pandemic highlighted the importance of face masks as an effective non-pharmaceutical intervention for reducing the transmission of infectious diseases. Monitoring mask compliance in public environments such as hospitals, educational institutions, transportation hubs, and workplaces remains a challenging task when performed manually. Recent advances in computer vision and deep learning have enabled the development of automated face mask detection systems capable of operating in real time. This paper presents a comparative study of three deep learning architectures, namely a Custom Convolutional Neural Network (CNN), VGG16, and MobileNetV2, for face mask detection. The study employs a publicly available dataset containing 12,000 facial images categorized into mask and no-mask classes. Data preprocessing techniques including resizing, normalization, and augmentation were applied to improve model generalization. Experimental results demonstrate that MobileNetV2 outperforms the other architectures, achieving an accuracy of 98.7%, precision of 98.4%, recall of 99.0%, and an AUC-ROC score of 0.99 while maintaining real-time performance. The proposed system was further integrated with OpenCV for live video stream analysis. The findings indicate that lightweight transfer learning models offer an effective and practical solution for real-time face mask detection in resource-constrained environments.

Real-Time Face Mask Detection Using Transfer Learning with MobileNetV2

The COVID-19 pandemic created an urgent need for automated systems capable of verifying face-mask compliance in public spaces. This paper presents a lightweight, real-time face-mask classifier built on transfer learning with the MobileNetV2 architecture. A pretrained ImageNet backbone is used as a frozen feature extractor with a compact classification head, followed by a fine-tuning phase that unfreezes the final convolutional layers. The model is trained and evaluated on the publicly available. Face Mask ∼12K Images dataset, comprising approximately twelve thousand pre-cropped and class-balanced face images split into training, validation, and test partitions. Using data augmentation, two-phase training, and standard regularization, the classifier attains approximately 99% accuracy on the held-out test set with near-perfect precision and recall for both the masked and unmasked classes. The results confirm that a low-compute, mobile-oriented backbone combined with transfer learning is sufficient for accurate binary mask detection, making the approach suitable for deployment on edge devices. The proposed pipeline is a clean, reproducible, end-to-end implementation rather than a novel methodology.

Real-Time Vision-Based Fall Detection Systems for the Elderly: A Systematic Review

The findings show that CNN-based architectures dominate algorithm choice, edge devices dominate deployment platforms, and optimization remains central to real-time inference on constrained hardware.

Real-Time Drowsiness Detection Using Dual MobileNetV2 Models on Desktop and Edge Devices

Drowsiness is a leading cause of human error in transportation and in shift-based occupational work, yet delivering reliable real-time detection on affordable, resource-constrained hardware remains difficult. This study aims to develop and evaluate a vision-based drowsiness detection system that behaves consistently across a full-power desktop and a low-cost edge device. The system couples two independent MobileNetV2 transfer-learning classifiers — one for eye state (Open/Closed) and one for mouth state (Yawn/No_yawn) — with a temporal decision engine that converts frame-level predictions into microsleep and excessive-yawning alerts. Both classifiers were trained on a merged multi-source dataset (8,548 training images) and evaluated with a class-balanced protocol (186 images/class for the eye branch and 448 images/class for the mouth branch) to remove test-set imbalance bias. The decision engine was realised as two platform-appropriate pipelines that share an offline-first, retry-capable event architecture: a duration-based, two-tier hysteresis alert on a desktop application (Haar-cascade detection, H5/float32 models) and a frame-count alert designed for a Raspberry Pi 5 edge board (MediaPipe detection, quantised TensorFlow Lite models). On the class-balanced test set the eye branch reached 95.16% (H5) / 95.97% (TFLite) accuracy and the mouth branch reached 96.65% for both formats, with above-99% cross-format prediction agreement. Converting to TFLite cut model size by 73.4% (8.99 to 2.39 MB) and single-frame model inference latency roughly thirteen-fold (about 25 to 1.9 ms, measured on the development machine). Real-time desktop sessions sustained 6.9–12.0 FPS, and the Haar detector located a face in only 15.8% of off-angle frames versus 96.9–98.6% of frontal frames. This single-session result offers a preliminary, rather than definitive, indication of the detector's pose sensitivity. A lightweight dual-MobileNetV2 design with platform-appropriate detectors shows promise for delivering consistent real-time drowsiness alerts across heterogeneous hardware tiers.

Enhancing facial expression recognition with lightweight attention-based CNN