Huizhou Yang

Forest resources are one of the indispensable resources of the earth, which are the basis for the survival and development of human society. With the swift advancements in computer vision and artificial intelligence technology, the utilization of deep learning for smoke detection has achieved remarkable results. However, the existing deep learning models have poor performance in forest scenes and are difficult to deploy because of numerous parameters. Hence, we introduce an optimized forest fire smoke monitoring system for embedded edge devices based on a lightweight deep learning model. The model makes full use of the multi-scale variable attention mechanism of Transformer architecture to strengthen the ability of image feature extraction. Considering the needs of application scenarios, we propose an improved lightweight network model LCNet for feature extraction, which can reduce the parameters and enhance detecting ability. In order to improve running speed, a simple semi-supervised label knowledge distillation scheme is used to enhance the overall detection capability. Finally, we design and implement a forest fire smoke detection system on an embedded device, including the Jetson NX hardware platform, high-definition camera, and detection software system. The lightweight model is transplanted to the embedded edge device to achieve rapid forest fire smoke detection. Also, an asynchronous processing framework is designed to make the system highly available and robust. The improved model reduces three-fourths of the parameters and increases speed by 3.4 times with similar accuracy to the original model. This demonstrates that our system meets the precision demand and detects smoke in time.

Various studies have shown that it is necessary to estimate the drivers’ vigilance to reduce the occurrence of traffic accidents. Most existing EEG-based vigilance estimation studies have been performed on intra-subject and multi-channel signals, and these methods are too costly and complicated to implement in practice. Hence, aiming at the problem of cross-subject vigilance estimation of single-channel EEG signals, an estimation algorithm based on capsule network (CapsNet) is proposed. Firstly, we propose a new construction method of the input feature maps to fit the characteristics of CapsNet to improve the algorithm accuracy. Meanwhile, the self-attention mechanism is incorporated in the algorithm to focus on the key information in feature maps. Secondly, we propose substituting the traditional multi-channel signals with the single-channel signals to improve the utility of algorithm. Thirdly, since the single-channel signals carry fewer dimensions of the information compared to the multi-channel signals, we use the conditional generative adversarial network to improve the accuracy of single-channel signals by increasing the amount of data. The proposed algorithm is verified on the SEED-VIG, and Root-mean-square-error (RMSE) and Pearson Correlation Coefficient (PCC) are used as the evaluation metrics. The results show that the proposed algorithm improves the computing speed while the RMSE is reduced by 3%, and the PCC is improved by 12% compared to the mainstream algorithm. Experiment results prove the feasibility of using forehead single-channel EEG signals for cross-subject vigilance estimation and offering the possibility of lightweight EEG vigilance estimation devices for practical applications.

Forest fires have continually endangered personal safety and social property. To reduce the occurrences of forest fires, it is essential to detect forest fire smoke accurately and quickly. Traditional forest fire smoke detection based on convolutional neural networks (CNNs) needs many hand-designed components and shows poor ability to detect small and inconspicuous smoke in complex forest scenes. Therefore, we propose an improved early forest fire smoke detection model based on deformable transformer for end-to-end object detection (deformable DETR). We use deformable DETR as a baseline containing the best sparse spatial sampling for smoke with deformable convolution and relation modeling capability of the transformer. We integrate a Multi-scale Context Contrasted Local Feature module (MCCL) and a Dense Pyramid Pooling module (DPPM) into the feature extraction module for perceiving features of small or inconspicuous smoke. To improve detection accuracy and reduce false and missed detections, we propose an iterative bounding box combination method to generate precise bounding boxes which can cover the entire smoke object. In addition, we evaluate the proposed approach using a quantitative and qualitative self-made forest fire smoke dataset, which includes forest fire smoke images of different scales. Extensive experiments show that our improved model’s forest fire smoke detection accuracy is significantly higher than that of the mainstream models. Compared with deformable DETR, our model shows better performance with improvement of mAP (mean average precision) by 4.2%, AP_S (AP for small objects) by 5.1%, and other metrics by 2% to 3%. Our model is adequate for early forest fire smoke detection with high detection accuracy of different-scale smoke objects.