Research on Calculation of Defect Area of Building Exterior Windows Based on Infrared Image Processing Technology
Lingling ZHANG, Ao XU, Jiran ZHANG, Panpan REN, Libin DING, and Daixiao WEI
A method for defect detection and area calculation of exterior windows of buildings is proposed by combining infrared thermal imaging technology and image processing technology. Using equipment for detection of building exterior window defects, the differential-pressure method was utilized to detect the air penetration of an exterior window, and the defective area of the air penetration of this window was calculated. Infrared images of the exterior window of the building collected by an infrared thermal imager were subjected to image preprocessing, exterior window defect detection, and area calculation after inspection. Then, an infrared-image detection model of exterior window defects was established. The results show that preprocessing can make use of the weighted average method for grayscale processing, the median filter for noise reduction, image sharpening, and histogram equalization for image enhancement processing. The outcome of the aforementioned approaches is evident. The detection of the pretreatment infrared image, which is obtained using the Roberts algorithm, minimizes the difference between the test and experimental values. This makes the detection information closer to the actual position of the defect. A primary assessment of the airtightness performance level of exterior windows can be achieved by comparing the results provided by the proposed infrared image processing technology with airtightness on-site tests.A method for defect detection and area calculation of exterior windows of buildings is proposed by combining infrared thermal imaging technology and image processing technology. Using equipment for detection of building exterior window defects, the differential-pressure method was utilized to detect the air penetration of an exterior window, and the defective area of the air penetration of this window was calculated. Infrared images of the exterior window of the building collected by an infrared thermal imager were subjected to image preprocessing, exterior window defect detection, and area calculation after inspection. Then, an infrared-image detection model of exterior window defects was established. The results show that preprocessing can make use of the weighted average method for grayscale processing, the median filter for noise reduction, image sharpening, and histogram equalization for image enhancement processing. The outcome of the aforementioned approaches is evident. The detection of the pretreatment infrared image, which is obtained using the Roberts algorithm, minimizes the difference between the test and experimental values. This makes the detection information closer to the actual position of the defect. A primary assessment of the airtightness performance level of exterior windows can be achieved by comparing the results provided by the proposed infrared image processing technology with airtightness on-site tests.
- Feb. 04, 2023
- Infrared Technology
- Vol. 44, Issue 12, 1358 (2022)
- DOI：
Deep Residual UNet Network-based Infrared Image Segmentation Method for Electrical Equipment
He LIU, Tiancheng ZHAO, Junbo LIU, Lixin JIAO, Zhihao XU, and Xiaocui YUAN
Infrared thermal image processing is an effective method for detecting defects in electrical equipment. Aiming at the problem of electrical equipment segmentation in infrared thermal images with a complex background, in this study we propose a deep residual UNet network for infrared thermal image segmentation. Using a deep residual network to replace VGG16 to perform feature extraction and coding for the UNet network, a deep residual series UNET network was constructed to segment electrical equipment. To validate the effectiveness of the Res-UNet network, infrared images, including current transformers and circuit breakers, were used to test the segmentation results and were compared with the traditional UNet and Deeplabv3+ networks. The networks were tested using 876 images. The experimental results show that RES18-UNET can accurately segment electrical equipment; the segmentation precision of current transformers and circuit breakers is greater than 93%, and the mean intersection over union (MIoU) is greater than 89%. Our method obtains more accurate segmentation results than UNet and Deeplabv3+, setting the basis for intelligent diagnosis of electrical faults.Infrared thermal image processing is an effective method for detecting defects in electrical equipment. Aiming at the problem of electrical equipment segmentation in infrared thermal images with a complex background, in this study we propose a deep residual UNet network for infrared thermal image segmentation. Using a deep residual network to replace VGG16 to perform feature extraction and coding for the UNet network, a deep residual series UNET network was constructed to segment electrical equipment. To validate the effectiveness of the Res-UNet network, infrared images, including current transformers and circuit breakers, were used to test the segmentation results and were compared with the traditional UNet and Deeplabv3+ networks. The networks were tested using 876 images. The experimental results show that RES18-UNET can accurately segment electrical equipment; the segmentation precision of current transformers and circuit breakers is greater than 93%, and the mean intersection over union (MIoU) is greater than 89%. Our method obtains more accurate segmentation results than UNet and Deeplabv3+, setting the basis for intelligent diagnosis of electrical faults.
- Feb. 04, 2023
- Infrared Technology
- Vol. 44, Issue 12, 1351 (2022)
- DOI：
Multi-scale Guided Filter and Decision Fusion for Thermal Fault Diagnosis of Power Equipment
Jian LIANG, Zhihong HUANG, and Keren ZHANG
This paper introduces a thermal fault diagnosis method called multi-scale guided filtering and de-cision fusion. The proposed method combines multiscale guided filtering and decision-fusion techniques for fault diagnosis. It comprises three main steps. First, the Mahalanobis distance between the fault area and background is estimated, and initial thermal fault diagnosis results are generated. The initial diagnosis result is then filtered using guided filtering with various parameters, and several filtering feature maps are generat-ed. Different filtering feature maps contain complementary spatial-structure information. Finally, a principal component analysis algorithm fuses these filtering feature maps to capture their spatial structure information and thermal information in filtering feature maps. Experimental results show that the proposed diagnosis method has a better detection performance than the current state-of-the-art detectors.This paper introduces a thermal fault diagnosis method called multi-scale guided filtering and de-cision fusion. The proposed method combines multiscale guided filtering and decision-fusion techniques for fault diagnosis. It comprises three main steps. First, the Mahalanobis distance between the fault area and background is estimated, and initial thermal fault diagnosis results are generated. The initial diagnosis result is then filtered using guided filtering with various parameters, and several filtering feature maps are generat-ed. Different filtering feature maps contain complementary spatial-structure information. Finally, a principal component analysis algorithm fuses these filtering feature maps to capture their spatial structure information and thermal information in filtering feature maps. Experimental results show that the proposed diagnosis method has a better detection performance than the current state-of-the-art detectors.
- Feb. 04, 2023
- Infrared Technology
- Vol. 44, Issue 12, 1344 (2022)
- DOI：
Study on Ultrasonic Guided Wave Propagation Characteristics and Damage Imaging for Composite Structures Under Variable Temperature Field
Changlin WANG, Li REN, and Yongteng ZHONG
The Lamb-wave-based damage location method has been widely used for health monitoring of composite structures. However, it is easily interfered by external factors because its service environment is complex and changeable. To determine the influence of the temperature field on the propagation of Lamb waves in composite structures, in this study we first investigated the propagation characteristics of ultrasonic guided waves on glass fiber laminates under a temperature field using an infrared thermal imager. Subsequently, a corrected model was established using the extracted amplitude attenuation and phase delay errors. Consequently, a modified multiple signal classification(2D-MUSIC) algorithm-based damage imaging method is proposed for composite structures. The experimental results on glass fiber composite laminates show that the proposed method can effectively improve the resolution and accuracy of the original algorithm under a variable temperature field.The Lamb-wave-based damage location method has been widely used for health monitoring of composite structures. However, it is easily interfered by external factors because its service environment is complex and changeable. To determine the influence of the temperature field on the propagation of Lamb waves in composite structures, in this study we first investigated the propagation characteristics of ultrasonic guided waves on glass fiber laminates under a temperature field using an infrared thermal imager. Subsequently, a corrected model was established using the extracted amplitude attenuation and phase delay errors. Consequently, a modified multiple signal classification(2D-MUSIC) algorithm-based damage imaging method is proposed for composite structures. The experimental results on glass fiber composite laminates show that the proposed method can effectively improve the resolution and accuracy of the original algorithm under a variable temperature field.
- Feb. 04, 2023
- Infrared Technology
- Vol. 44, Issue 12, 1338 (2022)
- DOI：
Study on Dual-Fluid Spray Cleaning Technique for Single-wafer Particle Removal
Baihong LIU, Weiping YANG, Xiang LIANG, Lili YANG, Haonan DU, Jiabing BAO, Chunming SHI, Yuexia MA, Yane YIN, and Yu DUAN
The particle removal efficiency (PRE) of single-wafer substrates using dual-fluid spray-cleaning technology was investigated. The ratio displacement-diameter(H/D), which is dimensionless, is introduced to discuss the effect of PRE on a single-wafer surface. In addition, the effects of spray time and nozzle injection pressure on PRE are discussed. The results show that increasing the spray time and nozzle injection pressure can increase PRE. The highest PRE occurred when the displacement-diameter ratio was close to 1. When the ratio was less than 1, the PRE increased with an increase in the displacement–diameter ratio. When the ratio was greater than 1, the partial area of the wafer surface was not washed, and the PRE decreased rapidly with an increase in the ratio. The dual-fluid spray-cleaning method can achieve more than 99% PRE for particle sizes between 0.2 .m and 0.3 .m and more than 96% PRE for particle sizes between 0.1 m and 0.5 m.The particle removal efficiency (PRE) of single-wafer substrates using dual-fluid spray-cleaning technology was investigated. The ratio displacement-diameter(H/D), which is dimensionless, is introduced to discuss the effect of PRE on a single-wafer surface. In addition, the effects of spray time and nozzle injection pressure on PRE are discussed. The results show that increasing the spray time and nozzle injection pressure can increase PRE. The highest PRE occurred when the displacement-diameter ratio was close to 1. When the ratio was less than 1, the PRE increased with an increase in the displacement–diameter ratio. When the ratio was greater than 1, the partial area of the wafer surface was not washed, and the PRE decreased rapidly with an increase in the ratio. The dual-fluid spray-cleaning method can achieve more than 99% PRE for particle sizes between 0.2 .m and 0.3 .m and more than 96% PRE for particle sizes between 0.1 m and 0.5 m.
- Feb. 04, 2023
- Infrared Technology
- Vol. 44, Issue 12, 1332 (2022)
- DOI：
An Infrared Image Detail Enhancement Algorithm Based on Parameter Adaptive Guided Filtering
Huiming OUYANG, Likun XIA, Zemin LI, Yan HE, Xiaojie ZHU, Youpan ZHU, Bangze ZENG, and Yongkang ZHOU
Of all the image layered filters, guided filter has been widely studied and applied in the field of infrared image detail enhancement because of its good edge preserving effect and low computational complexity. However, traditional fixed regularization parameter ε of the guide filter cannot achieve good filtering layering effect in all scenarios. Therefore, an adaptive algorithm of parameter ε based on local variance is proposed in this paper to improve the adaptability of the guide filter in all scenarios. In addition, an improved detail layer adaptive enhancement algorithm based on noise mask function is proposed by using the adaptive parameter ε value, which can effectively suppress the noise level and improve the detail enhancement ability of the algorithm in different scenes.Of all the image layered filters, guided filter has been widely studied and applied in the field of infrared image detail enhancement because of its good edge preserving effect and low computational complexity. However, traditional fixed regularization parameter ε of the guide filter cannot achieve good filtering layering effect in all scenarios. Therefore, an adaptive algorithm of parameter ε based on local variance is proposed in this paper to improve the adaptability of the guide filter in all scenarios. In addition, an improved detail layer adaptive enhancement algorithm based on noise mask function is proposed by using the adaptive parameter ε value, which can effectively suppress the noise level and improve the detail enhancement ability of the algorithm in different scenes.
- Feb. 04, 2023
- Infrared Technology
- Vol. 44, Issue 12, 1324 (2022)
- DOI：
Research on Crowd Abnormal Behavior Detection Based on Improved SSD
Jie KANG, Ye TIAN, and Gang YANG
Aiming at the problems of high algorithmic complexity and low detection accuracy caused by overlapping occlusions in abnormal crowd behavior detection, this paper proposes an algorithm for crowd abnormal behavior detection based on an improved single-shot multi-box detector(SSD). First, the lightweight network MobileNet v2 was used to replace the original feature extraction network VGG-16, and a convolutional layer was constructed by a deformable convolution module to enhance the receptive field. Feature enhancement was performed by integrating the position information into the channel attention, which can capture long-range dependencies between spatial locations, allowing for better handling of overlapping occlusions. The experimental results show that the proposed algorithm has a good detection effect on abnormal crowd behavior.Aiming at the problems of high algorithmic complexity and low detection accuracy caused by overlapping occlusions in abnormal crowd behavior detection, this paper proposes an algorithm for crowd abnormal behavior detection based on an improved single-shot multi-box detector(SSD). First, the lightweight network MobileNet v2 was used to replace the original feature extraction network VGG-16, and a convolutional layer was constructed by a deformable convolution module to enhance the receptive field. Feature enhancement was performed by integrating the position information into the channel attention, which can capture long-range dependencies between spatial locations, allowing for better handling of overlapping occlusions. The experimental results show that the proposed algorithm has a good detection effect on abnormal crowd behavior.
- Feb. 04, 2023
- Infrared Technology
- Vol. 44, Issue 12, 1316 (2022)
- DOI：
Infrared Image Enhancement Based on Adaptive Bilateral Filtering and Directional Gradient
Fengying NIE, Lixia HOU, and Liyong WAN
To overcome the defects of existing infrared image enhancement methods, such as under-enhancement, over-enhancement, and low contrast, an infrared image enhancement method based on adaptive bilateral filtering and directional gradient is proposed. The bilateral filter was improved, and its weighting coefficient is now adaptive to smooth and detailed regions. The improved bilateral filter is used as the central surround function of Retinex to decompose the infrared image into a base layer and a detail layer. Using improved platform histogram equalization, the base layer image is enhanced, and a directional gradient operator is proposed to extract the gradient image of the detail layer image to perform nonlinear adaptive edge enhancement on the detail-layer image. Experimental results show that, compared with existing methods, the proposed method can improve the brightness and contrast of infrared images more effectively. In addition, the visual effect of enhanced images using this method is better.To overcome the defects of existing infrared image enhancement methods, such as under-enhancement, over-enhancement, and low contrast, an infrared image enhancement method based on adaptive bilateral filtering and directional gradient is proposed. The bilateral filter was improved, and its weighting coefficient is now adaptive to smooth and detailed regions. The improved bilateral filter is used as the central surround function of Retinex to decompose the infrared image into a base layer and a detail layer. Using improved platform histogram equalization, the base layer image is enhanced, and a directional gradient operator is proposed to extract the gradient image of the detail layer image to perform nonlinear adaptive edge enhancement on the detail-layer image. Experimental results show that, compared with existing methods, the proposed method can improve the brightness and contrast of infrared images more effectively. In addition, the visual effect of enhanced images using this method is better.
- Feb. 04, 2023
- Infrared Technology
- Vol. 44, Issue 12, 1309 (2022)
- DOI：
High-precision Template Matching Tracking Algorithm for Optoelectronic Tracking System
Hao WU, Yong ZHANG, Xin LI, Minghua SI, and Weiming WANG
To achieve high-precision measurements under the operating conditions of optoelectronic tracking systems and satisfy high-precision target matching in complex environments, in this study we adopted the average normalized cross-correlation algorithm. To improve the matching speed and real-time tracking, the computational complexity was simplified by using the sum table method to correlate the sum of images, squares, and the correlation of images. The wavelet pyramid method was used as the search strategy, and the center of the template was used as the reference point for cross-shaped search. A termination threshold was introduced, which reduced the number of mismatched points to increase the search speed. To verify the effectiveness of the algorithm, an optoelectronic tracking system was placed on a two-dimensional turntable in an experiment that used the algorithm to track a target. The experimental results show that the missed target was controlled within 3 pixels. The proposed algorithm can realize high-precision and stable tracking in optoelectronic tracking systems.To achieve high-precision measurements under the operating conditions of optoelectronic tracking systems and satisfy high-precision target matching in complex environments, in this study we adopted the average normalized cross-correlation algorithm. To improve the matching speed and real-time tracking, the computational complexity was simplified by using the sum table method to correlate the sum of images, squares, and the correlation of images. The wavelet pyramid method was used as the search strategy, and the center of the template was used as the reference point for cross-shaped search. A termination threshold was introduced, which reduced the number of mismatched points to increase the search speed. To verify the effectiveness of the algorithm, an optoelectronic tracking system was placed on a two-dimensional turntable in an experiment that used the algorithm to track a target. The experimental results show that the missed target was controlled within 3 pixels. The proposed algorithm can realize high-precision and stable tracking in optoelectronic tracking systems.
- Feb. 04, 2023
- Infrared Technology
- Vol. 44, Issue 12, 1301 (2022)
- DOI：
Optics
Physics
Geography
All Subjects
Optical Metasurfaces: Fundamentals and Applications (2022)
In Progress
Editor (s): Guixin Li, Thomas Pertsch, Shumin Xiao
Special Issue on Relativistic Laser Plasma Interaction (RLPI) Diagnostics and Instrumentation (2022)
Submission Open:1 June 2022; Submission Deadline: 31 December 2022
Editor (s): Joerg Schreiber, Rodrigo Lopez-Martens, Lieselotte Obst-Huebl, Jianhui Bin
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20