Real-Time personnel safety detection in chemical parks using YOLOv8-ARR

GD-YOLO: An improved convolutional neural network architecture for real-time detection of smoking and phone use behaviors

Fiber Laser Methane Sensor and its Application in Coal Mine Safety

The safe approach distance detection of large construction equipment in substations is important to ensure the safety and stability of the power system, as well as to prevent equipment damage, power outages and other accidents. The current method is unable to intelligently distinguish construction equipment from power equipment and realize real-time safety approach distance detection. Therefore, this paper constructs a safety approach distance detection system for large-scale construction equipment in substations based on stereo vision and target detection, and realizes real-time high-precision safe approach distance detection between large-scale construction equipment and electric power equipment. Firstly, the system distinguishes construction equipment from power equipment using a GhostNet-based substation construction target detection model. Secondly, the system obtains spatial information regarding the operation scene using a lightweight stereo matching model based on channel attention, then calculates the spatial surface center of the target based on the spatial information and detection results, and finally calculates the safety approach distance between construction equipment and power equipment. Compared with MobileNetv3-YOLOv4, the map and the recall rate of the proposed method are improved by 13.1% and 29.0%; compared with the AnyNet stereo matching method, the proposed method decreases the end point error and 3 pixels error by 34.2% and 25.8%. The actual data show that the detection speed of the proposed method is 19.35 frames per second, and the mean absolute error is 0.942 m and the mean relative error is 3.802%. This method can accurately measure the safe approach distance in real time in real scenarios to guarantee the safety of personnel and equipment.

: For a number of years the U.S. Air Force has been performing research to develop safe intake simulants for chemical warfare agents (CWA) to provide accurate and quantitative real-time assessment of troop proficiency and gear efficacy during chemical warfare (CW) field exercises. Chloropentafluorobenzene (CPFB) was identified and evaluated as a candidate inhalation simulant, and was determined to possess desirable physiochemical and toxicological properties. These include rapid uptake, low metabolism and toxicity, rapid and predictable clearance, real-time detectability by existing portable 'breathalyzer' technology and by fielded CWA detectors, realistic canister breakthrough and commercial availability. A physiologically based pharmacokinetic (PBPK) model for CPEB has been developed which accurately describes the time course of blood and exhaled air concentrations during and following inhalation exposures of rats and primates to CPFB. This model has been employed to predict human exhaled air concentrations for several hours following brief CPFB exposures, such as might be experienced in training exercises using CPFB as an intake simulant. These simulants could be used to determine the exhaled air concentrations at which personnel would have been incapacitated had the exposure been to a real agent. The PBPK model was also used to calculate internal dose measures for a quantitative assessment of safe exposure criteria for the use of CPFB in such exercises. To assure the safety of personnel it is recommended that field exercises be designed to avoid exposures greater than 30 parts per million (ppm) , with the daily (8 h) time-weighted average not to exceed 3 ppm. The exposure guideline should not impair use of CPFB since field analytical methods can measure CPFB at part per trillion levels.

The construction environment is complex and dangerous, and it is difficult to achieve all-round, whole-process and real-time helmet detection. In order to ensure the safety of personnel, this paper proposes a helmet detection algorithm based on improved YOLO v5s. First, replace the backbone feature extraction network of YOLOv5s with the end-side neural network architecture GhostNet, which greatly reduces the amount of network parameters. Introduce the lightweight module attention mechanism ECA-Net in the C3 module to improve the feature extraction ability, and finally use the CIOU as the loss function to improve the positioning accuracy. The average accuracy (mAP) of the improved model on the SHWD dataset reaches 93.86%, and the processing speed (FPS) reaches 49. Compared with the original YOLOv5s, the amount of parameters is reduced by 13.33% without reducing the mAP, and the size of the model is reduced. 26.6%, processing speed increased by 22.5%. The experimental results show that it can effectively reduce the amount and size of model parameters and meet the real-time detection requirements of embedded devices.

In order to improve the ability to protect personnel safety during the construction process, current methods have low accuracy in detecting workers wearing helmets. In view of the current requirements for construction safety, we studied the helmet wearing status real-time detection method for construction safety. After pre-process the video of construction, the helmet wearing object was captured using SSD algorithm. By building a sample set of helmets wearing status and combining two kinds of networks, CNN and LSTM, the real-time detection of helmet wearing status is achieved. Simulation experiments show that the detection rate of the studied method is higher than 90% and is reliable.

Coal mine wire rope detection is related to personnel and production safety. With the Chinese coal mining trend tending towards deep mining, a considerable amount of data is critical for the online detection of deep well lifting wire rope. To improve the sampling rate, decrease the analysis processing time and realise real-time online detection, this paper proposes an online detection data compression processing method. The study focuses on the distortion compression method for the online detection signal of deep well hoisting wire rope. The set partitioning in hierarchical trees (SPIHT) algorithm is one of the most advanced methods in the field of image transformation coding. Compared with other coding algorithms, the SPIHT algorithm demonstrates desired characteristics such as a high signal-to-noise ratio, lower complexity and decreased computational load, among others. This paper discusses how, in combination with the image processing method, a compression coding method for the one-dimensional signal of the magnetic leakage detection of the mining wire rope is developed. Furthermore, the set partitioning sorting algorithm is investigated and analysed, the temporal orientation tree structure of the one-dimensional signal of the wavelet coefficient is defined for wire rope magnetic leakage detection and the SPIHT algorithm is presented, in addition to an example of the one-dimensional signal from the magnetic leakage detection of the wire rope. The results reveal that under the condition of the normalised mean square error (NMSE; NMSE < 0.01) of distortion, the compression ratio improved by 30%. The online detection signal lossy compression method proposed in this study has a considerable influence on the recovery of the original signal, in addition to a higher compression ratio and a reduced computation time, compared to the existing method.

Public transportation systems are among the most open public facilities in the world and susceptible to breaches of security. Reconciling the need for workplace safety and security with budgetary pressures requires new approaches to increase the effectiveness of existing solutions while preserving flexibility and low costs. An inexpensive sensor-based intrusion detection system that remotely monitors and notifies on- and/or off-site personnel of any incidents can significantly multiply the observational effectiveness of a few onsite safety or security personnel monitoring a facility. The advancement in the miniaturization of circuits has produced small computing devices allowing the development of pervasive applications that only a few years ago were not possible. The combination of such devices with wireless networks and micro-electro-mechanical systems technology provides a new platform for research and development of innovative monitoring applications. This project developed a low-cost, scalable, real-time intrusion detection and remote notification system called WSN-IRNS, using wireless sensor networks with the purpose of enhancing the safety and security of transit facilities. WSN-IRNS provides a cost-effective alternative or supplement to traditional wired security systems for protecting vulnerable areas and facilities such as garages, tunnels, and transit yards. The Internet-connected system supports real-time intervention by notifying personnel upon the detection of an intrusion through multimedia messages, which can include captured camera images that are delivered directly to mobile phones. Field tests have successfully demonstrated the proof-of-concept of the system, although adjustments and fine tuning of system parameters will be needed for environment-specific installations.

In the construction process, wearing a safety helmet is an important guarantee for personnel safety. However, manual detection is time-consuming, labor-intensive, and unable to provide real-time monitoring. To address this issue, a helmet-wearing detection algorithm has been proposed based on YOLOv5s. The algorithm uses the YOLOv5s network and introduces the CoordAtt coordinate attention mechanism module into its backbone to consider global information and improve the network’s ability to detect small targets. To improve feature fusion, the residual block in the backbone network has been replaced by a Res2NetBlock structure. The experimental results show that compared to the original YOLOv5 algorithm, the accuracy and speed of the self-made helmet data set have improved by 2.3 percentage points and 18 FPS, respectively. Compared to the YOLOv3 algorithm, accuracy and speed have improved by 13.8 percentage points and 95 FPS, respectively, resulting in a more accurate, lightweight, efficient, and real-time helmet-wearing detection.

Railroad construction sites are high-risk environments where monitoring personnel safety is critical for preventing accidents and enhancing construction efficiency. Traditional manual monitoring and image processing methods exhibit deficiencies in real-time performance and accuracy. This paper proposes a railway worker detection method based on improved support vector machines (ISVM), while using non-local mean noise reduction and histogram equalisation pre-processing techniques to optimise image quality to improve detection efficiency and accuracy. Multiscale features are then extracted with Inception v3 and combined with principal component analysis (PCA) for dimensionality reduction. Finally, an SVM classification algorithm is employed for personnel detection. To process small sample categories, data enhancement techniques (e.g., random flip and rotation) and K-fold cross-validation are applied to optimize the model parameters. The experimental results demonstrate that the ISVM method significantly improves accuracy and real-time performance compared to traditional detection methods and single deep learning models. This method provides technical support for railroad construction safety monitoring and effectively addresses personnel detection tasks in complex construction environments.

Electric power operation violation recognition (EPOVR) is essential for personnel safety, achieved by detecting key objects in electric power operation scenarios. Recent methods usually use the YOLOv8 model to achieve EPOVR; however, the YOLOv8 model still has four problems that need to be addressed. Firstly, the capability for feature representation of irregularly shaped objects is not strong enough. Secondly, the capability for feature representation is not strong enough to precisely detect multi-scale objects. Thirdly, the localization accuracy is not ideal. Fourthly, many violation categories in electric power operation cannot be covered by the existing datasets. To address the first problem, a deformable C2f (DC2f) module is proposed, which contains deformable convolutions and depthwise separable convolutions. For the second problem, an adaptive multi-scale feature enhancement (AMFE) module is proposed, which integrates multi-scale depthwise separable convolutions, adaptive convolutions, and a channel attention mechanism to optimize multi-scale feature representation while minimizing the number of parameters. For the third problem, an optimized complete intersection over union (OCIoU) loss is proposed for bounding box localization. Finally, a novel dataset named EPOVR-v1.0 is proposed to evaluate the performance of the object detection model applied in EPOVR. Ablation studies validate the effectiveness of the DC2f module, AMFE module, OCIoU loss, and their combinations. Compared with the baseline YOLOv8 model, the mAP@0.5 and mAP@0.5–0.95 are improved by 3.2% and 4.4%, while SDAP@0.5 and SDAP@0.5–0.95 are reduced by 0.34 and 0.019, respectively. Furthermore, the number of parameters and GFLOPS are shown to have slightly decreased. Comparison with seven YOLO models shows that our DAO-YOLO model achieves the highest detection accuracy while achieving real-time object detection for EPOVR.

Intelligent personnel safety management is a critical component of smart manufacturing infrastructure. This paper presents an integrated framework combining a structurally optimized neural network (enhanced with spatial and channel feature fusion mechanisms for multi-scale detection) with an agent-based large language model (LLM) enhanced with retrieval-augmented generation (RAG) capabilities for factory safety monitoring. The visual detection component employs the Similarity-Aware Channel Pruning (SACP) method for automated, performance-preserving compression by identifying and suppressing redundant channels based on similarity and norm regularization, while the agent-based LLM with RAG capabilities dynamically integrates real-time violation data with established safety management protocols to generate precise diagnostic reports and operational recommendations. The optimized network achieves real-time violation detection in parallel video streams, and the LLM-powered assistant facilitates intelligent decision-making through natural language querying. Extensive evaluations on multiple benchmark datasets and a real-world safety helmet detection dataset demonstrate the scheme’s superior performance in both accuracy and practical applicability for industrial deployment.

Chemical disasters from industrial accidents or sabotage require swift, precise responses. This study examines the effectiveness of integrating gas detection equipment, particularly Ion Mobility Spectrometry (IMS), in enhancing preparedness and early response. Through a review of technical literature and device specifications, it found that IMS-based portable tools significantly improve real-time detection of toxic gases, aiding in rapid source identification, personnel safety, and tactical decision-making. The study highlights the importance of equipment standardization, specialized personnel training, and incorporating detection systems into national chemical disaster response protocols to strengthen operational readiness and response efficiency.

In an effort to overcome the difficulty of real-time early warning via traditional infrared imaging technology caused by the complex working environment in coal mines, this paper proposes a mine early warning method based on uncooled infrared focal plane technology. The infrared thermal spectrogram of the detected object was visually displayed in a pseudo-color image with high resolution and high sensitivity, which can realize the real-time detection and early warning of personnel safety in modern mines. The multipoint compression correction algorithm based on human visual characteristics divided the response units of all acquisition units into gray intervals according to a threshold value, then the corresponding parameters were set in different intervals, and finally, each interval was compressed using a two-point correction algorithm. The volume of stored data was the sum of the calibration curve and the data from an encode table corrected by a MATLAB simulation, and the number of CPU cycles was run by a CCS 3.3 clock calculation algorithm. The results showed that when the temperature of the blackbody reached 115 °C, the nonuniformity before correction was 6.32%, and the nonuniformity after the multipoint correction of human eyes was 2.99%, which implied that the algorithm proposed in this paper had good denoising ability. The number of CPU cycles occupied by this algorithm was 18,257,363 cycles/frame with a frequency of 29.97 Hz. The sharpness of the compressed infrared images was obviously improved, and the uniformity was better. The method proposed in this paper can meet the need for modern mine personnel search and rescue, equipment supervision and dangerous area detection and other early warning requirements so as to achieve the goal of developing smart mines and ensuring safety in coal mine production.

In the complex environment of fully mechanized mining faces, the current object detection algorithms face significant challenges in achieving optimal accuracy and real-time detection of mine personnel and safety helmets. This difficulty arises from factors such as uneven lighting conditions and equipment obstructions, which often lead to missed detections. Consequently, these limitations pose a considerable challenge to effective mine safety management. This article presents an enhanced algorithm based on YOLOv11n, referred to as GCB-YOLOv11. The proposed improvements are realized through three key aspects: Firstly, the traditional convolution is replaced with GSConv, which significantly enhances feature extraction capabilities while simultaneously reducing computational costs. Secondly, a novel C3K2_FE module was designed that integrates Faster_block and ECA attention mechanisms. This design aims to improve detection accuracy while also accelerating detection speed. Finally, the introduction of the Bi FPN mechanism in the Neck section optimizes the efficiency of multi-scale feature fusion and addresses issues related to feature loss and redundancy. The experimental results demonstrate that GCB-YOLOv11 exhibits strong performance on the dataset concerning mine personnel and safety helmets, achieving a mean average precision of 93.6%. Additionally, the frames per second reached 90.3 f·s−1, representing increases of 3.3% and 9.4%, respectively, compared to the baseline model. In addition, when compared to models such as YOLOv5s, YOLOv8s, YOLOv3 Tiny, Fast R-CNN, and RT-DETR, GCB-YOLOv11 demonstrates superior performance in both detection accuracy and model complexity. This highlights its advantages in mining environments and offers a viable technical solution for enhancing the safety of mine personnel.