In social production and daily life, safety production plays a crucial role. The management of safety and environmental conservation generates a significant number of documents. Traditional manual methods in processing records involve inherent drawbacks such as subjectivity, low efficiency, and untimely warnings. In recent years, natural language processing (NLP) has gained significant attention and application in processing large volumes of documents. Therefore, this research proposes a semantic clustering model for identifying incidents related to security and environmental conservation management. The relation-enhanced attention mechanism and noise adversarial training were introduced during the pre-training of the corpus based on the records of security and environmental conservation management, aiming to generate a high-dimensional understanding of the text in the specific domain. A novel high-density spatial hierarchical clustering algorithm (HDBSCAN) was applied in clustering analysis on the text embedding, achieving effective semantic hierarchical clustering of records. The results indicate that this method can effectively capture semantics within the dataset. In comparison to traditional clustering methods such as K-Means and DBSCAN, HDBSCAN demonstrates superior performance in terms of clustering effectiveness and stability. Through this approach, this research aims to implement automatic classification of incidents in safety and environmental conservation management based on records, facilitating the safeguarding of social production and daily life. This research provides a new perspective and tool for the automated analysis of environmental events, with significant practical implications for environmental safety management.
To address the challenge of poor image quality in industrial surveillance videos under low-light conditions, hindering the normal execution of target recognition and detection tasks, this paper proposes a low-light surveillance image enhancement model based on Multi-Scale Retinex (MSR). Firstly, the MSR algorithm is employed to enhance the brightness of the images. Due to the loss of fine details in the brightness-enhanced part, the Laplacian sharpening algorithm is subsequently applied to enhance the details, allowing the brightness-enhanced images to retain more detailed features. Experimental results indicate that compared to the MSR algorithm and histogram equalization algorithm, the proposed algorithm in this paper performs better in terms of signal-to-noise ratio, grayscale values, and standard deviation. It effectively improves image quality while achieving a balance between brightness, details, and real-time performance.
With the development of deep learning technology, image-based object detection algorithms have been widely used in oilfield safety behavior regulation. However, the accuracy of identifying safety warning bands in oilfields is low, mainly due to the extreme aspect ratios. To solve the above problems, this paper proposes an improved YOLOv5-based method for detecting rotating targets of oilfield warning bands. By adding an additional angle prediction task to the original object detection framework and using a cyclic smooth labelling algorithm to transform the angle regression problem into a classification problem, the horizontal and predicted angle decoders can be combined to obtain the rotation bounding box of the target. This provides a more accurate spatial position representation of the warning band target, making it easier for the network to extract strong discriminative features of the target. Compared with traditional object detection algorithms annotated with horizontal bounding boxes, the rotation bounding box annotated object detection algorithm proposed in this paper significantly improves the recognition performance of safety warning bands and meets practical application requirements.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.