Fatigue driving is widely recognized as one of the major factors contributing to traffic accidents, posing not only a serious threat to road safety but also potential risks to drivers’ health and public security. With the rapid development of modern transportation, how to efficiently and accurately detect and warn against driver fatigue has become a critical issue in the field of intelligent transportation. To effectively address this issue, this paper proposes a novel fatigue driving detection method based on a Multi-Head Transformer with Adaptive Weighted Loss. In the proposed framework, the YOLOv8 model is first employed to efficiently and accurately locate key facial regions of the dri... More >

Road safety has become an increasingly important concern and the integration of Advanced Rider Assistance Systems and Advanced Driver Assistance Systems plays a crucial role in preventing accidents. This work proposes a computer vision pipeline to automatically detect hazardous road anomalies—loose gravel, potholes, and puddles—from a motorcycle-mounted camera, targeting real-time operation on embedded edge devices. A hybrid dataset of 28764 annotated images was created by combining real-world photos, Blender-rendered synthetic scenes, and AI-generated images to improve diversity and coverage. Multiple state-of-the-art object detectors were trained and benchmarked, including the YOLOv5/7... More >

Defocus blur detection is essential for computational photography applications, but existing methods struggle with accurate blur localization and boundary preservation. We propose SemanticBlur, a deep learning framework which integrates semantic understanding with attention mechanisms for robust defocus blur detection. Our semantic-aware attention module combines channel attention, spatial attention, and semantic enhancement to leverage high-level features for low-level feature refinement. The architecture employs a modified ResNet-50 backbone with dilated convolutions that preserves spatial resolution while expanding receptive fields, coupled with a feature pyramid decoder using learnable f... More >

To address the challenge of traditional models in simultaneously capturing local fluctuations and global trends for air pollutant concentration prediction, this paper proposes a multimodal deep learning model named MLP-BiLSTM- MHAT. The model integrates static features via MLP, extracts temporal dependencies through bidirectional LSTM (BiLSTM), and employs a Multi-head Attention mechanism (MHAT) to fuse local and global features while enhancing interactions between static and temporal characteristics. An improved Adam algorithm dynamically optimizes learning rates to balance the influence of heterogenous features. Validated on multi-site air quality data from Beijing, experimental results de... More >

Fall detection (FD) systems are an important part of healthcare monitoring, especially for elderly populations, where quick intervention can prevent serious injuries. This paper introduces an optimized YOLOV5-based framework that combines dual attention mechanisms for improved FD in real-time edge deployment situations. The proposed design integrates the Convolutional Block Attention Module (CBAM) and Squeeze-and-Excitation (SE) blocks within the YOLOv5 backbone, along with an improved Focus module that uses slice-based feature extraction. These enhancements allow the model to effectively capture both spatial and channel-wise dependencies, which are essential for distinguishing fall events f... More >