Red-green-blue Research Articles

Structural, optical and Judd-Ofelt analyses of Gd2-xEuxSi2O7 nanocrystals for lighting applications

A series of Eu3+-doped silicate-based red light-emitting nanocrystalline materials is fabricated via the solution combustion technique. Triclinic crystalline powders with a P-1 space group are formed containing irregularly sized grains. Three-lifetime values indicates the presence of three different local environments surrounding the Eu3+ ion. Upon near-UV excitation, the photoluminescence (PL) spectrum shows a red emission owing to the electronic band at ∼612 nm, consistent with the electronic transition 5D0 → 7F2. The energy bandgap is probed using diffuse reflectance spectroscopy. The critical distance between adjacent Eu3+ ions was evaluated to be ∼18.70 Å and multipolar exchanges were found accountable for the concentration quenching. The obtained chromaticity coordinates fall in the red regime of the CIE (1931) triangle, which replicates the potency of designated nanomaterials in the design and architecture of R-G-B (red–green–blue) phosphor-based LEDs.

Development of a digital phenotyping system using 3D model reconstruction for zoysiagrass

AbstractDigital phenotyping, particularly the use of plant 3D models, is a promising method for high‐throughput plant evaluation. Although many recent studies on the topic have been published, further research is needed to apply it to breeding research and other related fields. In this study, using a 3D model phenotyping system we developed, we reconstructed and analyzed 20 accessions of zoysiagrass (Zoysia spp.), including three species and their hybrid, over a period of 1 year. Artificial neural network with three hidden layers was able to effectively remove nonplant parts while retaining plant parts that were incorrectly removed using the cropping method, offering a robust and flexible approach for post‐processing of 3D models. The system also demonstrated its ability to accurately evaluate a range of traits, including height, area, and color using red green blue (RGB)‐based vegetation indices. The results showed a high correlation between the estimated volume obtained from voxel 3D model and dry weight, enabling its use as a non‐destructive method for measuring plant volume. In addition, we found that the green red normalized difference index from RGB‐based indices was similar to the commonly used normalized difference vegetation index in controlled illumination conditions. These results demonstrate the potential for three‐dimensional model phenotyping to facilitate plant breeding, particularly in the field of turfgrass and feed crops.

Enhancing Face Spoofing Attack Detection: Performance Evaluation of a VGG-19 CNN Model

With the wide use of facial verification and authentication systems, the performance evaluation of Spoofing Attack Detection (SAD) module in the systems is important, because poor performance leads to successful face spoofing attacks. Previous studies on face SAD used a pretrained Visual Geometry Group (VGG) -16 architecture to extract feature maps from face images using the convolutional layers, and trained a face SAD model to classify real and fake face images, obtaining poor performance for unseen face images. Therefore, this study aimed to evaluate the performance of VGG-19 face SAD model. Experimental approach was used to build the model. VGG-19 algorithm was used to extract Red Green Blue (RGB) and deep neural network features from the face datasets. Evaluation results showed that the performance of the VGG-19 face SAD model improved by 6% compared with the state-of-the-art approaches, with the lowest equal error rate (EER) of 0.4%. In addition, the model had strong generalization ability in top-1 accuracy, threshold operation, quality test, fake face test, equal error rate, and overall test standard evaluation metrics.

Fault classification using convolutional neural networks and color channels for time-frequency analysis of acoustic emissions

We present a novel method for real-time fault classification using the time history of acoustic emissions (AEs) recorded from a lab-scale gas turbine operating under normal and faulty conditions across multiple turbine speeds. Time-frequency features are extracted using the continuous wavelet transform, and for each signal, the root mean square (RMS) and kurtosis are calculated. We employ a color mapping technique to combine the time-frequency and statistical features into a single red–green–blue (RGB) image. The red channel is mapped to the time-frequency data, whereas the green and blue channels are mapped to the RMS and kurtosis, respectively. Subsequently, a deep convolutional neural network is trained on the generated images to classify the gas turbine condition. We show that the proposed model can form an online monitoring system using AEs to classify multiple running conditions at various turbine speeds. The methodology not only achieves real-time classification of faults but also minimizes the human intervention in identifying these faults. The datasets and codes used in this paper will be openly available.

Using a Smartphone-Based Colorimetric Device with Molecularly Imprinted Polymer for the Quantification of Tartrazine in Soda Drinks.

The present study reports the development and application of a rapid, low-cost in-situ method for the quantification of tartrazine in carbonated beverages using a smartphone-based colorimetric device with molecularly imprinted polymer (MIP). The MIP was synthesized using the free radical precipitation method with acrylamide (AC) as the functional monomer, N,N'-methylenebisacrylamide (NMBA) as the cross linker, and potassium persulfate (KPS) as radical initiator. The smartphone (RadesPhone)-operated rapid analysis device proposed in this study has dimensions of 10 × 10 × 15 cm and is illuminated internally by light emitting diode (LED) lights with intensity of 170 lux. The analytical methodology involved the use of a smartphone camera to capture images of MIP at various tartrazine concentrations, and the subsequent application of the Image-J software to calculate the red, green, blue (RGB) color values and hue, saturation, value (HSV) values from these images. A multivariate calibration analysis of tartrazine in the range of 0 to 30 mg/L was performed, and the optimum working range was determined to be 0 to 20 mg/L using five principal components and a limit of detection (LOD) of 1.2 mg/L was obtained. Repeatability analysis of tartrazine solutions with concentrations of 4, 8, and 15 mg/L (n = 10) showed a coefficient of variation (% RSD) of less than 6%. The proposed technique was applied to the analysis of five Peruvian soda drinks and the results were compared with the UHPLC reference method. The proposed technique showed a relative error between 6% and 16% and % RSD lower than 6.3%. The results of this study demonstrate that the smartphone-based device is a suitable analytical tool that offers an on-site, cost-effective, and rapid alternative for the quantification of tartrazine in soda drinks. This color analysis device can be used in other molecularly imprinted polymer systems and offers a wide range of possibilities for the detection and quantification of compounds in various industrial and environmental matrices that generate a color change in the MIP matrix.

Predicting Ballast Fouling Conditions Through RGB-Based Statistical Quantity Analysis

Evaluating railway ballast fouling is critical to assessing track conditions and planning proper ballast maintenance. Varying material properties associated with different ballast fouling conditions can be used to evaluate the severity of fouling. Although approaches using ground penetration radar, impulse response, surface wave, and SmartRock have been developed to estimate the fouling conditions, these methods require special sensors and equipment, or well-trained technicians. Recently, convolutional neural network (CNN) based computer vision approaches have become popular in performing particle segmentation to obtain the ballast grain size distribution. The coarse aggregate fraction can be evaluated by the CNN method, but it is not easy to segment fine particles accurately with these approaches. This study proposes a novel image analysis approach to directly estimate the ballast fouling conditions. First, fouled ballast images with different fouling conditions are taken as references. The RGB (red, green, blue) color distributions of the fouled ballast images are then processed through statistical analysis. A strong linear correlation is found between Fouling Index (FI) and variance and this is used to establish the FI prediction model. The established FI prediction model is tested and validated by additional fouled ballast samples. The FI prediction model proposed in this study can be used to quantify ballast fouling conditions with promising performance.

Rapid and sensitive smartphone non-enzymatic colorimetric assay for the detection of glucose in food based on peroxidase-like activity of Fe3O4@Au nanoparticles

A low-cost and reliable analytical method based on the combination of a newly designed Fe3O4@Au as peroxidase mimetics, supported on smartphone analysis software package was proposed for the determination of glucose content in food samples. The nanocomposite was prepared by self-assembling technique, and the characterization was carried out using transmission electron microscopy (TEM), Fourier transforms infrared, and X-ray diffractometer. Record the color change of the solution with a smartphone camera and optimize the operation parameters and reaction conditions. A smartphone with a free self-developed app was accustomed live the RGB (red–greenblue) values of color intensity within the Fe3O4@Au system and were processed with Image J software before computationally convert them glucose concentrations. At the optimization experiment, reaction temperature of 60 °C, reaction time of 50 min and the amount of addition of Fe3O4@Au 0.0125 g was the optimal combination of detecting glucose smartphone color detection system. Hereon, the accuracy of the proposed method was evaluated by comparison between smartphone colorimetry and UV–vis spectrophotometer, a linear calibration in the range of 0.25 ∼ 15 mmol/L glucose was obtained with minimum detection limit of 1.83 and 2.25 μmol/L, respectively. The proposed method was applied effectively to the detection of glucose in actual samples. The results were in accordance with the conventional UV–vis spectrophotometer method.

Flood cascading on critical infrastructure with climate change: A spatial analysis of the extreme weather event in Xinxiang, China

Floods caused by extreme weather events and climate change have increased in occurrence and severity all over the world, resulting in devastation and disruption of activities. Researchers and policy practitioners have increasingly paid attention to the role of critical infrastructure (CI) in disaster risk reduction, flood resilience and climate change adaptation in terms of its backbone functions in maintaining societal services in hazard attacks. The analysed city in this study, Xinxiang (Henan province, China), was affected by an extreme flood event that occurred on 17–23 July 2021, which caused great socio-economic losses. However, few studies have focused on medium-sized cities and the flood cascading effects on CI during this event. Therefore, this study explores the damages caused by this flooding event with links to CI, such as health services, energy supply stations, shelters and transport facilities (HEST infrastructure). To achieve this, the study first combines RGB (red, green blue) composition and supervised classification for flood detection to monitor and map flood inundation areas. Second, it manages a multiscenario simulation and evaluates the cascading effects on HEST infrastructure. Diverse open-source data are employed, including Sentinel-1 synthetic aperture radar (SAR) data and Landsat-8 OIL data, point-of-interest (POI) and OpenStreetMap (OSM) data. The study reveals that this extreme flood event has profoundly affected croplands and villagers. Due to the revisiting period of Sentinel-1 SAR data, four scenarios are simulated to portray the retreated but ‘omitted’ floodwater: Scenario 0 is the flood inundation area on 27 July, and Scenarios 1, 2 and 3 are built based on this information with a buffer of 50, 100 and 150 m outwards, respectively. In the four scenarios, as the inundation areas expand, the affected HEST infrastructure becomes more clustered at the centre of the core study area, indicating that those located in the urban centre are more susceptible to flooding. Furthermore, the affected transport facilities assemble in the north and east of the core study area, implying that transport facilities located in the north and east of the core study area are more susceptible to flooding. The verification of the flood inundation maps and affected HEST infrastructure in the scenario simulation support the series method adopted in this study. The findings of this study can be used by flood managers, urban planners and other decision makers to better understand extreme historic weather events in China, improve flood resilience and decrease the negative impacts of such events on HEST infrastructure.

Design and development of a delta robot system to classify objects using image processing

In this paper, a delta robot is designed to grasp objects in an automatic sorting system. The system consists of a delta robot arm for grasping objects, a belt conveyor for transmitting objects, a camera mounted above the conveyor to capture images of objects, and a computer for processing images to classify objects. The delta robot is driven by three direct current (DC) servo motors. The controller is implemented by an Arduino board and Raspberry Pi 4 computer. The Arduino is programmed to provide rotation to each corresponding motor. The Raspberry Pi 4 computer is used to process images of objects to classify objects according to their color. An image processing algorithm is developed to classify objects by color. The blue, green, red (BGR) image of objects is converted to HSV color space and then different thresholds are applied to recognize the object’s color. The robot grasps objects and put them in the correct position according to information received from Raspberry. Experimental results show that the accuracy when classifying red and yellow objects is 100%, and for green objects is 97.5%. The system takes an average of 1.8 s to sort an object.

Оценка степени пигментации трабекулы у больных первичной открытоугольной глаукомой с помощью колориметрической шкалы

Purpose. Development of a photocolorimetric scale to assess the extent of trabecula pigmentation along its circumference in patients with primary open-angle glaucoma. Material and methods.Study of 36 patients (62 eyes) with primary open-angle glaucoma was performed. Average age: 61.5 ± 9.8 years (48–75 years). Men – 24 (40 eyes), women – 12 (22 eyes). All patients underwent a comprehensive ophthalmic examination, as well as photoregistration of the iridocorneal angle. Using the Pixelmator Pro (Pixelmator Team, USA) and the photographic images, we performed colorimetric estimation of the degree of the iridocorneal angle pigmentation. RGB (Red, Green, Blue) values for weak, moderate, pronounced, and sharply pronounced trabecular pigmentation were determined. Using color model HSL (Hue, Saturation, Lightness) derived percentages (range) corresponding to a certain degree of trabecular pigmentation. Results.Basing on the results, a colorimetric scale was developed for quantifying the trabecular pigmentation degree in patients with primary open-angle glaucoma. The results obtained by us will serve in the future for more accurate objectification of the definition of pigmentation degree, which is certainly of practical importance in the clinical practice of ophthalmologists. Conclusion. The application of HSL-color models allows to estimate with high reliability the differences between levels of trabecular pigmentation in patients with glaucoma. Using a photocolorimetric scale allows to estimate objectively the efficacy of laser operations aimed at reducing the degree of trabecular pigmentation of the iridocorneal angle. Keywords: primary open-angle glaucoma, gonioscopy, photocolorimetric assessment of the pigmentation degree, colorimetric scale

A deep learning algorithm-based visual strategy intervention study for children with autism spectrum disorders - extraction and detection of children's behavioral features.

Autism spectrum disorder is a group of neurodevelopmental disorders. The disease's etiology is unclear, and there is no specific drug treatment for the core symptoms of autism spectrum disease. The study aims to explore effective intervention methods for children with autism spectrum disorders.This paper proposes a visual strategy intervention method for children with autism spectrum disorders. This method combines feature extraction and abnormal behavior detection and can use a visual cue strategy to integrate children into social groups. Firstly, the spatial-temporal feature fusion structure is added to extract behavioral features from children, and the spatial information contained in MotionNet is fused with temporal features. Optical Flow Feature (OFF) subnetwork is added to the optical flow extraction feature network. Each layer feature is input to the OFF subnet to extract the time feature further. Then, a behavior detection method based on the sequential pool is proposed. This method combines attention mechanism and clustering pool to effectively describe human behavior dynamics in the long, redundant video under complex background. Finally, feature extraction and behavior detection experiments are carried out on SDUFall, Weizmann, and HMDB51 data sets.The model's accuracy is still slightly higher than others in that only the video Red-Green-Blue (RGB) frame is used as input. Compared with OFF, SDUFall can reach 88.64%, and HMDB51 can only reach 63.81%. In contrast, the proposed model can reach 72.09%, higher than others. The descriptor obtained the best result of 92.57%, which is 3.64%, 2.58%, and 1.73% higher than the other three comparison descriptors. The data show that the method presented here is effective and has advantages in detecting children's abnormal behavior.This method and visual intervention for children with autism spectrum disorders can help them to overcome social barriers.

Multi-volume variable scale bitmap data object classification algorithm architectural concrete color difference detection

Architectural concrete color difference (ACCD) directly affects building aesthetics. At present, the AC apparent quality detection method is based on a subjective artificial observation and detection process. The large volume of AC building, however, makes it difficult for quality inspectors to sample on site. Therefore, the manuscript establishes the aerial vehicle-to-ground coordinate conversion model and quadrotor unmanned aerial vehicle (QUAV) Eulerian motion model wherein the real-time optimization of QUAV motion parameters through remote sensing technology improves data collection stability. The proposed ACCD detection model, which is based on the QUAV remote sensing technology, is established by the improved multi-volume bitmap data object classification algorithm (BDOCA). The detection accuracy of MobileNetV3, ResNet50, and VGG16 algorithms reach 86.33%, 92.10%, and 87.62%, respectively. The study acquires experimental images from different buildings and produces a generalized identification set. It then verifies the ACCD detection model generalized identification capability by the traversal type detection method. The MobileNetV3, ResNet50, and VGG16 algorithms all achieved a generalized identification accuracy of 99.6%. The study builds the ACCD model by red-green-blue (RGB) spatial conversion, Kalman filtering noise reduction, noise point open operation, connected domain close operation, and mask quantization segmentation operation. This method implements color difference block coding, color difference threshold pixel point scale calculation, and geometric parameter calculation.

YOLO Based Deep Learning Model for Segmenting the Color Images

The first stage is to extract fine details from a picture using Red Green Blue (RGB) colour space is colour image segmentation. Most grayscale and colour picture segmentation algorithms use original or updated fuzzy c-means (FCM) clustering. However, due to two factors, the majority of these methods are inefficient and fail to produce the acceptable segmentation results for colour photos. The inclusion of local spatial information often results in a high level of computational complexity due to the repetitive distance computation between clustering centres and pixels within a tiny adjacent window. The second reason is that a typical neighbouring window tends to mess up the local spatial structure of images. Color picture segmentation has been improved by introducing Deep Convolution Neural Networks (CNNs) for object detection, classification and semantic segmentation. This study seeks to build a light-weight for object detector that uses a depth and colour image from a publically available dataset to identify objects in a scene. It's likely to output in the depth way by expanding the YOLO network's network architecture. Using Taylor based Cat Salp Swarm algorithm (TCSSA), the weight of the suggested model is modified to improve the accuracy of region extraction findings. It is possible to test the detector's efficacy by comparing it to various datasets. Testing showed that the suggested model is capable of segmenting input into multiple metrics using bounding boxes. The results shows that the proposed model achieved 0.20 of Global Consistency Error (GCE) and 1.85 of Variation of Information (VOI) on BSDS500 dataset, where existing techniques achieved nearly 1.96 to 1.86 of VOI and 0.25 to 0.22 of GCE for the same dataset.

Colorimetric Signal Readout for the Detection of Volatile Organic Compounds Using a Printable Glass-Based Dielectric Barrier Discharge-Type Helium Plasma Detector.

In this paper, we report on a printable glass-based manufacturing method and a new proof-of-concept colorimetric signal readout scheme for a dielectric barrier discharge (DBD)-type helium plasma photoionization detector. The sensor consists of a millimeter-sized glass chamber manufactured using a printable glass suspension. Plasma inside the chip is generated using a custom-built power supply (900 V and 83.6 kHz), and the detector uses ∼5 W of power. Our new detection scheme is based on detecting the change in the color of plasma after the introduction of target gases. The change in color is first captured by a smartphone camera as a video output. The recorded video is then processed and converted to an image light intensity vs retention time plot (gas chromatogram) using three standard color space models (red, green, blue (RGB), hue, saturation, lightness (HSL), and hue, saturation, value (HSV)) with RGB performing the best among the three models. We successfully detected three different categories of volatile organic compounds using our new detection scheme and a 30-m-long gas chromatography column: (1) straight-chain alkanes (n-pentane, n-hexane, n-heptane, n-octane, and n-nonane), (2) aromatics (benzene, toluene, and ethylbenzene), and (3) polar compounds (acetone, ethanol, and dichloromethane). The best limit of detection of 10 ng was achieved for benzene at room temperature. Additionally, the device showed excellent performance for different types of sample mixtures consisting of three and five compounds. Our new detector readout method combined with our ability to print complex glass structures provides a new research avenue to analyze complex gas mixtures and their components.

0264 Untangling Correlations Between Positive Affect and Light and Activity Data Using Deep Learning

Abstract Introduction Research has found activity and light data continuously captured via wearable devices predict psychological outcomes. Understanding which sources are most predictive could suggest which biological or environmental factors most impact outcomes. Existing work has largely relied on summary measures of these sources. This may overgeneralize important nuances in the sources that are correlated to the outcomes. We utilized deep learning to predict daily affected based on raw actigraphy and light data to determine which sources are most predictive of daytime positive affect. Methods We modeled the daily mean (DMPA) and standard deviation (DSDPA) of positive affect using actigraphy and light data from a cohort of 172 adolescents who completed an ecological momentary protocol for 7-8 days. Positive affect was measured via PANAS-SF and administered via smartphone 5-6 times daily. The outcomes are predicted using the actigraphy and light data during the environmental night (time between astronomical twilight and dawn) prior to each outcome. Convolutional neural networks are used to predict the outcomes using all permutations of actigraphy, white light, and red-green-blue (RGB) light data. Results The mean (standard deviation) of the DMPA and DSDPA outcomes were 6.53(1.60) and 1.28(1.15) respectively. Using white and RGB light we could predict DMPA and DSDPA with a root mean squared error (RMSE) of 1.59 and 1.08 respectively (i.e., within 0.99 and 0.93 deviations respectively). Conclusion Our work indicates that white and RGB light best predict positive affect. This may indicate that light-based environmental night factors have a larger impact on daily affect than activity-based factors. Most results were within a few hundredths of a deviation from each other, and the channels that best predicted affect differed depending on whether DMPA or DSDPA was modeled. Our methods provide a way to predict affect from raw data and suggest which environmental and biological data have clinical implications towards affect. Important next steps include using time periods related to individual’s dim light melatonin onset and comparing findings from deep learning to those based on summary measures. Support (if any) CARRS Pilot Grant (Wheeler), R01-AA025626 (Hasler), R01-DA044143 (Hasler), RF1-AG056311-04 (Wallace)

Identifying Tree Species in a Warm-Temperate Deciduous Forest by Combining Multi-Rotor and Fixed-Wing Unmanned Aerial Vehicles

Fixed-wing unmanned aerial vehicles (UAVs) and multi-rotor UAVs are widely utilized in large-area (>1 km2) environmental monitoring and small-area (<1 km2) fine vegetation surveys, respectively, having different characteristics in terms of flight cost, operational efficiency, and landing and take-off methods. However, large-area fine mapping in complex forest environments is still a challenge in UAV remote sensing. Here, we developed a method that combines a multi-rotor UAV and a fixed-wing UAV to solve this challenge at a low cost. Firstly, we acquired small-scale, multi-season ultra-high-resolution red-green-blue (RGB) images and large-area RGB images by a multi-rotor UAV and a fixed-wing UAV, respectively. Secondly, we combined the reference data of visual interpretation with the multi-rotor UAV images to construct a semantic segmentation model and used the model to expand the reference data. Finally, we classified fixed-wing UAV images using the large-area reference data combined with the semantic segmentation model and discuss the effects of different sizes. Our results show that combining multi-rotor and fixed-wing UAV imagery provides an accurate prediction of tree species. The model for fixed-wing images had an average F1 of 92.93%, with 92.00% for Quercus wutaishanica and 93.86% for Juglans mandshurica. The accuracy of the semantic segmentation model that uses a larger size shows a slight improvement, and the model has a greater impact on the accuracy of Quercus liaotungensis. The new method exploits the complementary characteristics of multi-rotor and fixed-wing UAVs to achieve fine mapping of large areas in complex environments. These results also highlight the potential of exploiting this synergy between multi-rotor UAVs and fixed-wing UAVs.

Assessing thermal imagery integration into object detection methods on air-based collection platforms

Object detection models commonly focus on utilizing the visible spectrum via Red–Green–Blue (RGB) imagery. Due to various limitations with this approach in low visibility settings, there is growing interest in fusing RGB with thermal Long Wave Infrared (LWIR) (7.5–13.5 µm) images to increase object detection performance. However, we still lack baseline performance metrics evaluating RGB, LWIR and RGB-LWIR fused object detection machine learning models, especially from air-based platforms. This study undertakes such an evaluation, finding that a blended RGB-LWIR model generally exhibits superior performance compared to independent RGB or LWIR approaches. For example, an RGB-LWIR blend only performs 1–5% behind the RGB approach in predictive power across various altitudes and periods of clear visibility. Yet, RGB fusion with a thermal signature overlay provides edge redundancy and edge emphasis, both which are vital in supporting edge detection machine learning algorithms (especially in low visibility environments). This approach has the ability to improve object detection performance for a range of use cases in industrial, consumer, government, and military applications. This research greatly contributes to the study of multispectral object detection by quantifying key factors affecting model performance from drone platforms (including distance, time-of-day and sensor type). Finally, this research additionally contributes a novel open labeled training dataset of 6300 images for RGB, LWIR, and RGB-LWIR fused imagery, collected from air-based platforms, enabling further multispectral machine-driven object detection research.

Hybrid WDM-PDM visible light communication system incorporating compressed spectrum return to zero advance modulation format

Abstract Hybrid wavelength division multiplexing (WDM) and polarization division multiplexing (PDM) technology is a promising candidate for high capacity and extended reach in visible light communication (VLC) systems. However, multilevel modulations and direct modulation are suffered from two predominant limitations in VLC such as high complexity and frequency chirping respectively. Therefore, in this work, a high-capacity VLC system is presented by employing a hybrid WDM-PDM and compressed spectrum return to zero (CSRZ) advanced modulation format. Moreover, direct modulation is replaced with external modulation employing Mach-Zehndar modulators and red/green/blue (RGB) laser diodes (LDs). A detailed comparison of non-return to zero (NRZ) and CSRZ is performed at varied VLC lengths in terms of bit error rate (BER) and Q factor. Results revealed that CSRZ is far better than NRZ and external modulation offered an edge over direct modulation. The maximum VLC distance achieved using CSRZ is 229 cm within acceptable BER limits (10−3) without forward error correction (FEC).

Control System for Indoor Safety Measures Using a Faster R-CNN Architecture

This paper presents a control system for indoor safety measures using a Faster R-CNN (Region-based Convolutional Neural Network) architecture. The proposed system aims to ensure the safety of occupants in indoor environments by detecting and recognizing potential safety hazards in real time, such as capacity control, social distancing, or mask use. Using deep learning techniques, the system detects these situations to be controlled, notifying the person in charge of the company if any of these are violated. The proposed system was tested in a real teaching environment at Rey Juan Carlos University, using Raspberry Pi 4 as a hardware platform together with an Intel Neural Stick board and a pair of PiCamera RGB (Red Green Blue) cameras to capture images of the environment and a Faster R-CNN architecture to detect and classify objects within the images. To evaluate the performance of the system, a dataset of indoor images was collected and annotated for object detection and classification. The system was trained using this dataset, and its performance was evaluated based on precision, recall, and F1 score. The results show that the proposed system achieved a high level of accuracy in detecting and classifying potential safety hazards in indoor environments. The proposed system includes an efficiently implemented software infrastructure to be launched on a low-cost hardware platform, which is affordable for any company, regardless of size or revenue, and it has the potential to be integrated into existing safety systems in indoor environments such as hospitals, warehouses, and factories, to provide real-time monitoring and alerts for safety hazards. Future work will focus on enhancing the system’s robustness and scalability to larger indoor environments with more complex safety hazards.

Recognizing Urban Functional Zones by GF-7 Satellite Stereo Imagery and POI Data

The identification of urban functional zones (UFZs) is crucial for urban planning and optimizing industrial layout. Fusing remote sensing images and social perception data is an effective way to identify UFZs. Previous studies on UFZs recognition often ignored band information outside the red–green–blue (RGB), especially three-dimensional (3D) urban morphology information. In addition, the probabilistic methods ignore the potential semantic information of Point of Interest (POI) data. Therefore, we propose an “Image + Text” multimodal data fusion framework for UFZs recognition. To effectively utilize the information of Gaofen-7(GF-7) stereo images, we designed a semi-transfer UFZs recognition model. The transferred model uses the pre-trained model to extract the deep features from RGB images, and a small self-built convolutional network is designed to extract the features from RGB bands, near-infrared (NIR) band, and normalized digital surface model (nDSM) generated by GF-7. Latent Dirichlet allocation (LDA) is employed to extract POI semantic features. The fusion features of the deep features of the GF-7 image and the semantic features of POI are fed into a classifier to identify UFZs. The experimental results show that: (1) The highest overall accuracy of 88.17% and the highest kappa coefficient of 83.91% are obtained in the Beijing Fourth Ring District. (2) nDSM and NIR data improve the overall accuracy of UFZs identification. (3) POI data significantly enhance the recognition accuracy of UFZs, except for shantytowns. This UFZs identification is simple and easy to implement, which can provide a reference for related research. However, considering the availability of POI data distribution, other data with socioeconomic attributes should be considered, and other multimodal fusion strategies are worth exploring in the future.