Smoky Environment Research Articles

SmokeNav: Millimeter‐Wave‐Radar/Inertial Measurement Unit Integrated Positioning and Semantic Mapping in Visually Degraded Environments for First Responders

First responders often face hazardous and life‐threatening situations in environments filled with smoke, posing significant risks to their safety. The existing perception solutions, such as camera or light detection and ranging (LiDAR)‐based methods, are inadequate when faced with visually degraded conditions caused by smoke. In this work, SmokeNav, a novel system that combines data from an inertial sensor and millimeter‐wave (mmWave) radar, is proposed to enhance situational awareness for first responders in smoky environments. SmokeNav utilizes an inertial positioning module that exploits the human motion constraints with a foot‐mounted inertial measurement unit to provide accurate user localization. By integrating this location information with mmWave radar data, it employs a probabilistic occupancy map construction to reconstruct an accurate metric map. To enable semantic understanding of the environment, a DNN‐based semantic segmentation model that incorporates radar reflectivity and employs focal loss to improve performance is introduced. Herein, extensive real‐world experiments in smoky environments is conducted to demonstrate that SmokeNav precisely localizes the user and generates detailed maps with semantic segmentation. In this work, potentials are held for enhancing the safety and effectiveness of first responders in hazardous conditions.

Improving blacksmith safety through protective equipment education and occupational health and safety program support

Pande Besi or blacksmith craftsmen, is one of the small industries that has developed in Tabanan Regency, Bali Province. Blacksmith craftsmen are exposed to a hot, dusty, and smoky environment, posing potential hazards to occupational health and safety. They typically work on the floor with makeshift seats, adopting non-ergonomic postures that can lead to musculoskeletal complaints such as pain in the back, waist, neck, shoulders, and buttocks. The purpose of this service activity is to educate blacksmith craftsmen on the importance of using Personal Protective Equipment (PPE) and maintaining proper working postures to prevent accidents and occupational diseases. This activity involves training and mentoring, targeting 30 individuals, focusing on the use of PPE, and improving work attitudes to reduce musculoskeletal complaints and occupational diseases. Results from 30 respondents showed that before counseling and assistance, the majority of the blacksmith craftsmen's knowledge was in the sufficient category (46.67 percent). After counseling, 90 percent of the respondents' knowledge was in the good category. Regarding work attitudes, before mentoring, the highest value was less than 70 percent, while after mentoring, 93.33 percent were categorized as having a good work attitude. The impact of this activity is an increase in knowledge and improvement in the work attitudes of blacksmith craftsmen in Tabanan Regency.

Complex smoke removal in image: Integrating frequency learning network with data synthesis method

This paper introduces a novel neural network architecture and an enhanced data synthesis method that significantly boost the performance in removing complex smoke from images. The architecture features a multi-branch and multi-scale feature fusion design, which effectively integrates multiple feature streams and adaptively restores the background by identifying specific smoke characteristics within the image. A newly designed Fourier residual block is incorporated to capture frequency domain information, enabling the network to process and transform information across both spatial and frequency domains. To improve the network’s generalization ability and robustness, an in-depth analysis of the imaging process in smoky environments was conducted, leading to an improved method for synthesizing smoke images. This methodology facilitates the creation of a more varied and realistic training dataset, substantially enhancing the neural network’s capabilities in image restoration. Experimental results show that this approach is highly effective on both synthetic and real-world smoke datasets, outperforming existing image de-smoking methods in terms of quantitative metrics and visual perception. The code for this method is available at https://github.com/Exiagit/MFSR.

Analysis of multispectral polarization imaging image information based on micro-polarizer array.

As a new detection technology, polarization imaging is of great significance in the field of target detection. At present, polarization imaging technology usually adopts visible light polarization imaging. The technique is difficult to image the target in complex background due to its narrow working spectrum and short detection distance. Therefore, based on the principle of full Stokes micro-polarizer array, this paper proposes a multi-spectral polarization imaging scheme and designs a multi-spectral polarization imaging detection system penetrating haze. Conducting indoor and outdoor polarized imaging experiments. Finally, image quality was assessed using metrics such as information entropy (EN), average gradient (AG), and standard deviation (STD). The results show that compared with traditional strength detection, the imaging system has significantly improved detection distance and imaging quality in smoky environments. The imaging system can effectively enhance the contours and details of the target object and improve detection and recognition capabilities.

Method of echo recognition of target in smoke environment based on residual convolutional neural network for pulsed laser detection

A recognition algorithm based on full waveform decomposition and residual convolutional neural network is proposed for the anti-interference problem of pulsed laser detection in smoky environments. As the original waveform data lack of features, a deep network - Resnet18 was used for the initial training. Considering the complexity of the algorithm, the structure, number of convolutional kernels, and sampling rate of Resnet18 were optimized, resulting in a lightweight version of Resnet6 with optimal parameters. Then, a pulsed laser detection platform under smoke environment was built. Considering the generalization of experimental data, five different scenes were designed to evaluate the algorithm. Compared to other algorithms, the proposed algorithm demonstrates superior performance in terms of low computational complexity (0.0441 MB parameters) and high recognition accuracy (94.59% ± 0.46). Finally, additional experiments were conducted on the detection platform. Frosted material was used as the detection target with different intensity of noise signals to verify the robustness.

Efficiently Range-Coupled Position Estimation for an Aerial Swarm With the Confidence Evaluation of Onboard Sensing

This work proposes an efficient range-coupled localization approach for aerial swarms considering the variance of onboard sensors in cluttered environments. First, a reciprocal bond estimation algorithm is proposed to estimate the position; it constructs an optimization framework based on the range-coupled observability analysis. Subsequently, considering the variable performance characteristics of onboard sensors in cluttered environments, a moving confidence evaluation algorithm is proposed to improve the resilience of the position estimation system by assessing the concurrent reliability of all sensors. Mathematically, the aforementioned two algorithms are integrally formulated using a nonlinear least-squares equation. Notably, solving this nonlinear problem is typically a low-efficiency process that deteriorates with the scale of the swarm. To overcome this issue, a gradient-aware Levenberg–Marquardt algorithm is herein proposed to enhance the computational efficiency of this system to solve this nonlinear least-squares problem. Finally, swirling experiments involving four drones are carried out to verify the performance of the proposed methods. The results demonstrate that the time cost of optimization in each servo period is only approximately 7.15 ms, and the computational efficiency exhibits at least a 2.78 times improvement over the existing methods. Meanwhile, even in a smoky environment, the estimation precision can be as great as 8 cm, which is comparable to results obtained using state-of-the-art methods.

A sensor review for human detection with robotic systems in regular and smoky environments

Search and rescue robots gained a significant attention in the past, as they assist firefighters during their rescue missions. The opportunity to move autonomously or remotely controlled with intelligent sensor technology, to detect victims in unknown fire smoke environments, introduces a growing technology in fire engineering. Since sensor systems are a component of mobile robots, there is a demand for intelligent robot vision, especially for human detection in fire smoke environments. In this article, an overview of sensor technologies and their algorithms for human detection in regular and smoky environments is presented. These sensor technologies are categorized into single sensor and multi-sensor systems. Novel sensor approaches are led by artificial intelligence, 3D mapping and multi-sensor fusion. The article provides a contribution for future research directions in algorithms and applications and supports decision-makers in fire engineering to get knowledge in trends, novel applications and challenges in this field of research.

Polarized laser target detection system for smoky environment based on full-waveform decomposition and multiscale convolutional neural networks with attention

To overcome the problem that the smoky environment affects the laser detection performance and generates false alarm, this paper proposes a polarization pulse laser target detection method based on the difference of the polarization information between the target and the smoke, combining full waveform decomposition and Multiple Scale-Attention convolutional neural network with Focal loss function (MSAFCNN). Optimal parameters of the algorithm are obtained by studying the recognition accuracy of the algorithm with different sampling rates and the number of convolution kernels. The polarization pulse laser detection platform is built and the target detection experiments under five different scenarios using infrared lasers are conducted. The polarization echo signals of the smoke and the targets are collected and the recognition accuracy of the proposed algorithm is calculated. The ablation experiments are carried out and MSAFCNN is compared with several advanced algorithms. The experimental results show that the proposed algorithm has the highest recognition accuracy (99.085% ± 0.249%) compared with other algorithms. According to the ablation experiment, the recognition accuracy can be improved by 1.381% using MSAFCNN. The recognition experiments with different sampling rates and numbers of convolutional kernels are performed, and the accuracy of the proposed algorithm can reach 99.348% ± 0.178% at 1 GHz sampling rate and 98.910% ± 0.297% at 500 MHz sampling rate. The optimal number of convolutional kernels is 16, and the number of the algorithm parameters is only 125.273 KB, which provides the feasibility for the subsequent implementation of the algorithm in hardware.

Compressed Sensing Imaging with Compensation of Motion Errors for MIMO Radar

Using a multiple-input-multiple-output (MIMO) radar for environment sensing is gaining more attention in unmanned ground vehicles (UGV). During the movement of the UGV, the position of MIMO array compared to the ideal imaging position will inevitably change. Although compressed sensing (CS) imaging can provide high resolution imaging results and reduce the complexity of the system, the inaccurate MIMO array elements position will lead to defocusing of imaging. In this paper, a method is proposed to realize MIMO array motion error compensation and sparse imaging simultaneously. It utilizes a block coordinate descent (BCD) method, which iteratively estimates the motion errors of the transmitting and receiving elements, as well as synchronously achieving the autofocus imaging. The method accurately estimates and compensates for the motion errors of the transmitters and receivers, rather than approximating them as phase errors in the data. The validity of the proposed method is verified by simulation and measured experiments in a smoky environment.

Analysis of temporal and spatial distribution characteristics of ammonium chloride smoke particles in confined spaces

In response to the demand for short-range detection of anti-smoke environment interference by laser fuzes, this study proposes a smoke environment simulation of non-uniform continuous point source diffusion and investigates an experimental laboratory smoke environment using an ammonium chloride smoke agent. The particle size distribution, composition, and mass flow distribution of the smoke were studied. Based on a discrete phase model and a k-ε turbulence model, a numerical simulation was developed to model the smoke generation and diffusion processes of the smoke agent in a confined space. The temporal and spatial distribution characteristics of the smoke mass concentration, velocity, and temperature in the space after smoke generation were analyzed, and the motion law governing the smoke diffusion throughout the entire space was summarized. Combined with the experimental verification of the smoke environment laboratory, the results showed that the smoke plume changed from fan-shaped to umbrella-shaped during smoke generation, and then continued to spread around. Meanwhile, the mass concentration of smoke in the space decreased from the middle outward; the changes in temperature and velocity were small and stable. In the diffusion stage (after 900 s), the mass concentration of smoke above 0.8 m was relatively uniform across an area of smoke that was 12 m thick. The concentration decreased over time, following a consistent decreasing trend, and the attenuation was negligible in a very short time. Therefore, this system was suitable for conducting experimental research on laser fuzes in a smoke environment. Owing to the stability of the equipment and facilities, the setup could reproduce the same experimental smoke environment by artificially controlling the smoke emission of the smoke agent. Overall, this work provides a theoretical reference for subsequent research efforts regarding the construction of uniform smoke environments and evaluating laser transmission characteristics in smoky environments.

Research on dark channel dehazing of single-image based on non-dispersive infrared (NDIR) detection technology

This paper presents an experimental study on the non-dispersive infrared (NDIR) detection technology and dark channel dehazing technology. Based on the analysis of Beer-Lambert Law and differential carbon dioxide detection principle, this paper proposes an atmospheric light value estimation algorithm based on NDIR detection technology. First, the change characteristics of the gas concentration in indoor smoky environment are collected and analyzed. Then appropriate weighting coefficients are chosen based on the gas characteristics to estimate the atmospheric light value. Finally, the digital image dehazing technology through dark channel prior is used for calculation to obtain a haze-free image with high quality and high resolution. The experiment in this paper proves the feasibility of combining NDIR detection technology with dehazing technology, and its ability to improve image quality and achieve better restoration effect.

Cross-Modal Contrastive Learning of Representations for Navigation Using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental Conditions

Deep reinforcement learning (RL), where the agent learns from mistakes, has been successfully applied to a variety of tasks. With the aim of learning collision-free policies for unmanned vehicles, deep RL has been used for training with various types of data, such as colored images, depth images, and LiDAR point clouds, without the use of classic map--localize--plan approaches. However, existing methods are limited by their reliance on cameras and LiDAR devices, which have degraded sensing under adverse environmental conditions (e.g., smoky environments). In response, we propose the use of single-chip millimeter-wave (mmWave) radar, which is lightweight and inexpensive, for learning-based autonomous navigation. However, because mmWave radar signals are often noisy and sparse, we propose a cross-modal contrastive learning for representation (CM-CLR) method that maximizes the agreement between mmWave radar data and LiDAR data in the training stage. We evaluated our method in real-world robot compared with 1) a method with two separate networks using cross-modal generative reconstruction and an RL policy and 2) a baseline RL policy without cross-modal representation. Our proposed end-to-end deep RL policy with contrastive learning successfully navigated the robot through smoke-filled maze environments and achieved better performance compared with generative reconstruction methods, in which noisy artifact walls or obstacles were produced. All pretrained models and hardware settings are open access for reproducing this study and can be obtained at https://arg-nctu.github.io/projects/deeprl-mmWave.html

LoRa Backscatter Assisted State Estimator for Micro Aerial Vehicles with Online Initialization

The advances in agile micro aerial vehicles (MAVs) have shown great potential in replacing humans for labor-intensive or dangerous indoor investigation, such as warehouse management and fire rescue. However, the design of a state estimation system that enables autonomous flight poses fundamental challenges in such dim or smoky environments. Current dominated computer-vision based solutions only work in well-lighted texture-rich environments. This paper addresses the challenge by proposing Marvel, an RF backscatter-based state estimation system with online initialization and calibration. Marvel is nonintrusive to commercial MAVs by attaching backscatter tags to their landing gears without internal hardware modifications, and works in a plug-and-play fashion with an automatic initialization module. Marvel is enabled by three new designs, a backscatter-based pose sensing module, an online initialization and calibration module, and a backscatter-inertial super-accuracy state estimation algorithm. We demonstrate our design by programming a commercial MAV to autonomously fly in different trajectories. The results show that Marvel supports navigation within a range of 50 m or through three concrete walls, with an accuracy of 34 cm for localization and 4.99 for orientation estimation. We further demonstrate our online initialization and calibration by comparing to the perfect initial parameter measurements from burdensome manual operations.

Contrast of Image of an Object Observed in Smoke Conditions using Polarizing Filtering of Radiation Scattered by Smoke Particles

The aim of the work was to study the contrasts of the images of an object observed in a smoky environment, using polarizing filtering of radiation scattered by smoke particles towards the observer, and without filtering. Prospects for developing optical accessories for firefighters to improve the observation of objects in smoke were evaluated by comparing image contrasts.The goal was achieved by experimentally simulating the process of transmitting images of a blackandwhite object with a sharp black/white transition boundary through various types of smoke aerosols using polarizing filtering of radiation scattered by smoke particles, and without filtering and evaluating image contrasts.Studies of image contrasts for different optical densities of smoke in two registration schemes were performed, when the receiving optical system is located near the illumination source of the object at a distance of ≈ 150 mm from it, and when it is located at a distance from the illumination source of the object at a distance of ≈ 800 mm.It is established that the method of forming the image of the object using polarization filtering of radiation backscattering (RBS) reduces the rate of image contrast reduction with an increase in optical smoke density compared to image registration without filtering (RBS).A significant difference in the contrasts of images recorded with filtration (RBS) and in the absence of it is observed for "light" fumes (smoldering of wood, cotton) at average optical densities of smoke.The results obtained can be used in the development of optical accessories for firefighter-rescuer to improve the conditions of observation of objects in adverse conditions of vision: smoke, vaporization, fog.

METHOD OF CONDUCTING PRACTICAL EXERCISES IN A MULTIFUNCTIONAL SIMULATOR OF CONTAINER TYPE

The paper analyzes the current state of practical training of firefighters using the existing material and technical base of the garrisons of the Rescue Service of Civil Defense of Ukraine. The existing method of conducting classes in most cases is the same, and the material base does not meet modern requirements and does not allow to reproduce the real conditions of the fire in the process of training personnel. Training of personnel of the fire and rescue service should take place in conditions as close as possible to the real fire, primarily in gassed and smoky rooms. The problem of training firefighters is the use of obsolete training complexes, primarily such as heat and smoke chambers. Existing methods and means of training personnel to work in a smoky and gassy environment, which is modeled on training complexes, do not reproduce the conditions of the fire, and outdated training scenarios allow you to get used to them, which calls into question the effectiveness of such training. technical imperfection is one of the main reasons for improper training of firefighters. Today, the requirements for domestic training complexes are insufficient and do not meet the conditions close to a real fire. As a training complex, in this paper it is proposed to consider a multifunctional container-type simulator, located on the basis of the training ground of Lviv State University of Life Safety. The training of firefighters in a multifunctional container-type simulator takes place in a variety of conditions and situations that allow personnel to be as close as possible to real extreme conditions; have elements of extreme complexity; learn to make decisions independently; create a variety of options for physical and emotional stress. A method of conducting practical classes in a multifunctional container-type simulator for training firefighters has been developed, which in combination with theoretical training will allow to increase the level of their professional training in conditions close to real fires. This technique can be used to train not only professional firefighters, but also members of the newly formed voluntary fire brigades of the united territorial communities.

CREATION OF WORKPLACE FOR PREPARATION OF FIREFIGHTERS IN ORDER TO CONDUCT RESCUE OPERATIONS IN A CONFINED SPACE ON THE HORIZONTAL SECTIONS

Every year in Ukraine there are accidents when working in confined spaces, including fatalities. In most cases, people do not perform the necessary pre-screening of the environment and do not use adequate respiratory and visual protection. Work in a confined space is classified as hazardous work because there is a real threat of the release of harmful vapours, gases, and other substances into the working area that can poison workers and cause damage to the body in certain concentrations. Such spaces include open hatches and inspection wells, sewers, trenches, pipelines, ducts, closed cellars and other areas with insufficient ventilation. Quite often, rescue attempts lead to tragedies when both an employee and a poorly equipped, unprepared rescuer (firefighter) are killed at the same time. An analysis of the rescue work in a confined space shows us that it is both horizontal and vertical. Therefore, the effectiveness of rescuing people and carrying out rescue work in a foggy, smoky environment in a confined space depends largely on the level of training of firefighters and their equipment, namely: individual respiratory protection and equipment for the rescue of humans and animals. Therefore, the actual scientific and practical task that needs specific justification will be the choice of the site and structural elements for the work place arrangement and the procedure for conducting rescue operations in a confined space by the firefighters. The article analyzes the tragic cases that have occurred with firefighters and other workers in water and sewerage wells, reservoirs and tanks, the difficulties that arise in carrying out emergency rescue operations in a confined space, and the feasibility of creating such workplaces in order to train firefighters.

EFFICIENCY EVALUATION OF FIRE THERMAL IMAGING CAMERAS IN THE FIRE MODULE

The issue of selection and evaluation of fire thermal imaging cameras (TICs) is new for the personnel of the State Emergency Service of Ukraine (SES of Ukraine) units, as in the recent years the units began to receive them and use during firefighting and rescue operations. Among the variety of brands and manufacturers of TICs, it is quite difficult to determine and make the right decision "which one to choose?", especially considering that they are all quite similar in their characteristics and are in the same price range. Moreover, sellers are not mentioned about their weaknesses, and especially do not emphasize what exactly you need to focus on and under what conditions properly they should be used.
 The purpose of the work is to assess the dependence of the effectiveness of fire detection and rescue operations considering the technical parameters and brands of fire thermal imagers. According to the method of estimating the parameters of TICs, which was developed at the Lviv State University of Life Safety, a comparative evaluation of the performance of TICs, which are used by units of SES of Ukraine. TICs of the following brands were selected for research: FLIR K2, 3M SCOTT V206, FLIR K33, 3M SCOTT V320, LEADER TIC3, 3M SCOTT X380 TIC3. According to their tactical and technical characteristics, the presented TICs were divided into three groups, two in each. To obtain a quantitative assessment of the visual quality of the display of the indicators understudy, a four-point rating scale was adopted: 5 - excellent reflection; 4 - good reflection; 3 - mediocre reflection; 2 - unsatisfactory reflection. According to the results of the research and the set amount of points, which took into account all series of experiments, the best result in their groups showed: Group I - 3M SCOTT V206, Group II - FLIR K33, Group III - 3M SCOTT X380. Based on experimental studies, it can be argued that the current parameters (tactical and technical characteristics) that influence the choice of TICs are: the size of the matrix, the refresh rate, temperature range and temperature sensitivity. These parameters are decisive during the reconnaissance of the SCBA (Self Contained Breathing Apparatus) units in gassed and smoky environments to solve complex tactical tasks, such as searching for a victim or hidden combustion centre and other tasks for their intended purpose.

Study to access the surgical outcome among patients attending ophthalmology unit with pterygium using various autografts at RVM Hospital, Siddipet, Telangana state

Introduction: Pterygium is more common in tropical areas, with prevalence ranging from 0.3 to 29%. Pterygium is more frequent in areas with more ultraviolet radiation, in hot, dry, windy, dusty, and smoky environments. Aim of the study is to assess the pterygium outcome with primary pterygium surgery. Methodology: Hospital based Prospective interventional study with purposive sampling method. Study sample is 60 cases. The present study was conducted in Department of ophthalmology, RVM institute of Medical sciences and hospital, Telangana state. Study period was January 2019 to January 2020. Statistical analysis was done by entering data in excel sheet and expressing the data by frequency distribution, analysis is done by SPSS version: 21. Results: Majority of the patients were between the ages of 30 to 50 years. The average age of the study group was 47.6 years. Female preponderance is observed than the male in this study. Males 21 and females 39. The location of pterygium was nasal in 60 eyes (100%). Majority of the patients presented with type III(50%) and grade III (64%). 12% of the patients presented with type I and 38% of the patients presented with type II pterygium. 36% of the patients presented with grade II pterygium16 patients out of 50 patients (32%) included in the study showed an improvement in visual acuity post-operatively. In 34 patients (68%) visual acuity remained the same. The mean visual acuity preoperatively was 0.52 +/- 0.46.D which improved to 0.68 +0.32 (P = 0.002) post-operatively. Conclusion: Pterygium excision is a safe, effective and economical option for the management of primary pterygium requiring surgical intervention.

Sphagnum: a promising indoor air purifier

In the present era, where pollution levels are alarmingly high and mankind is facing newer and newer diseases due to high levels of pollution, suspended particulate matter (SPM) leads to many respiratory diseases. In this work, the effectiveness of Sphagnum cymbifolium on indoor SPM concentration levels was studied under different conditions – namely, dark, sunlight and smoky conditions. S. cymbifolium was found effective in reducing the concentration of SPM in the environment, particularly indoors and in indoor smoky environments. Some further research areas are also proposed.

An in-situ monitoring system for electron beam wire-feed additive manufacturing

Wire-feed additive manufacturing (AM) is a promising method for fabricating large metal components with complex geometry. Plenty of studies proved that wire transition status has critical influence on the forming quality in wire-feed AM process. It is important to develop a high adaptive system for in-situ monitoring wire transition status, due to common methods such as CCD monitoring fail in smoky, high temperature and vacuum environment. In this paper, in order to overcome this problem, an in-situ monitoring system based on the electromagnetic principle was firstly designed and fabricated. The experiments indicated that triple common states of wire transition can be distinguished with the system. The results showed that 0.5–mm spatial resolution and 0.4-s response time satisfy the demand for monitoring in AM process. In addition, the system adaptability for complex situation was validated and enhances performance with the lifting voltage. In practical, the monitoring system successfully worked over a long period in the high temperature, vacuum environment during the electron beam AM process. This study provided a new design for process monitoring, which is feasible and valuable for developing AM technology.