One of the most effective deterrent methods is using face masks to prevent the spread of the virus during the COVID-19 pandemic. Deep learning face mask detection networks have been implemented into COVID-19 monitoring systems to provide effective supervision for public areas. However, previous works have limitations: the challenge of real-time performance (i.e., fast inference and low accuracy) and training datasets. The current study aims to propose a comprehensive solution by creating a new face mask dataset and improving the YOLOv5 baseline to balance accuracy and detection time. Particularly, we improve YOLOv5 by adding coordinate attention (CA) module into the baseline backbone following two different schemes, namely YOLOv5s-CA and YOLOV5s-C3CA. In detail, we train three models with a Kaggle dataset of 853 images consisting of three categories: without a mask “NM," with mask “M,” and incorrectly worn mask “IWM” classes. The experimental results show that our modified YOLOv5 with CA module achieves the highest accuracy mAP@0.5 of 93.9% compared with 87% of baseline and detection time per image of 8.0 ms (125 FPS). In addition, we build an integrated system of improved YOLOv5-CA and auto-labeling module to create a new face mask dataset of 7110 images with more than 3500 labels for three categories from YouTube videos. Our proposed YOLOv5-CA and the state-of-the-art detection models (i.e., YOLOX, YOLOv6, and YOLOv7) are trained on our 7110 images dataset. In our dataset, the YOLOv5-CA performance enhances with mAP@0.5 of 96.8%. The results indicate the enhancement of the improved YOLOv5-CA model compared with several state-of-the-art works.
High-quality 3D objects play a crucial role in digital twins, while synthetic data generated from these objects have become essential in deep learning-based computer vision applications. The task of collecting and labeling real defects on industrial object surfaces has many challenges and efforts, while synthetic data generation feasibly replicates huge amounts of labeled data. However, synthetic datasets lack realism in their rendered images. To overcome this issue, this paper introduces a single framework for 3D industrial object reconstruction and synthetic defect generation for digital twin smart factory applications. In detail, NeRF is applied to reconstruct our custom industrial 3D objects through videos collected by a smartphone camera. Several NeRF-based models (i.e., Instant-NGP, Nerfacto, Volinga, and Tensorf) are compared to choose the best outcome for the next step of defect generation on the 3D object surface. To be fairly evaluated, we train four models using the Nerfstudio framework with our three custom datasets of two objects. From the experiment’s results, Instant-NGP and Nerfacto achieve the best outcomes, outperforming all other methods significantly. The exported meshes of 3D objects are refined using Blender before loading into NVIDIA Omniverse Code to generate defects on the surface with the Replicator. To evaluate the object detection performance and to verify the benefits of synthetic defect data, we conducted experiments with YOLO-based models on our synthetic and real-plus-synthetic defects. From the experiment’s results, the synthetic defect data contribute to improving YOLO models’ generalization capability with the highest and lowest accuracy mAP@0.5 enhancement of 18.8 and 1.5 percent on YOLOv6n and YOLOv8s, respectively.
In the Republic of Korea, fire outbreaks caused by electrical devices are one of the most frequent accidents, causing severe damage to human lives and infrastructure. The metropolitan police, The National Institute of Scientific Investigation, and the National Fire Research Institute conduct fire root-cause inspections to determine whether these fires are external or internal infrastructure fires. However, obtaining results is a complex process. In addition, the situation has been hampered by the lack of sufficient digital forensics and relevant programs. Apart from electrical devices, multi-sockets are among the main fire instigators. In this study, we aim to verify the feasibility of utilizing YOLO-based deep-learning object detection models for fire-cause inspection systems for multi-sockets. Particularly, we have created a novel image dataset of multi-socket fire causes with 3300 images categorized into the three classes of socket, both burnt-in and burnt-out. This data was used to train various models, including YOLOv4-csp, YOLOv5n, YOLOR-csp, YOLOv6, and YOLOv7-Tiny. In addition, we have proposed an improved YOLOv5n-SE by adding a squeeze-and-excitation network (SE) into the backbone of the conventional YOLOv5 network and deploying it into a two-stage detector framework with a first stage of socket detection and a second stage of burnt-in/burnt-out classification. From the experiment, the performance of these models was evaluated, revealing that our work outperforms other models, with an accuracy of 91.3% mAP@0.5. Also, the improved YOLOv5-SE model was deployed in a web browser application.