RFIENet: RGB-thermal feature interactive enhancement network for semantic segmentation of insulator in backlight scenes

Li, Bing; Wang, Tian; Zhai, Yongjie; Yuan, Jing

doi:10.1016/j.measurement.2022.112177

Cited by 17 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous current studies focus on improving the accuracy of detection by increasing the scale of network [ 28 , 29 ], resulting in slower detection speed and heavier computing resources, which is difficult to be applied in the practical industry production process. Inspired by the ResNet [ 30 ], which is widely used in various industry detection scenarios [ 31 , 32 ] due to its efficient feature extraction capacity, an improved backbone based on ResNet34 is designed to constitute the encoders of the proposed method for efficient feature extraction. The details of the encoders are shown in Table 1 , in which the “Number” denotes that the times to repeat the corresponding operation.…”

Section: Methodsmentioning

confidence: 99%

A Multi-Source Data Fusion Network for Wood Surface Broken Defect Segmentation

Zhu,

Xu,

Lin

et al. 2024

Sensors

View full text Add to dashboard Cite

Wood surface broken defects seriously damage the structure of wooden products, these defects have to be detected and eliminated. However, current defect detection methods based on machine vision have difficulty distinguishing the interference, similar to the broken defects, such as stains and mineral lines, and can result in frequent false detections. To address this issue, a multi-source data fusion network based on U-Net is proposed for wood broken defect detection, combining image and depth data, to suppress the interference and achieve complete segmentation of the defects. To efficiently extract various semantic information of defects, an improved ResNet34 is designed to, respectively, generate multi-level features of the image and depth data, in which the depthwise separable convolution (DSC) and dilated convolution (DC) are introduced to decrease the computational expense and feature redundancy. To take full advantages of two types of data, an adaptive interacting fusion module (AIF) is designed to adaptively integrate them, thereby generating accurate feature representation of the broken defects. The experiments demonstrate that the multi-source data fusion network can effectively improve the detection accuracy of wood broken defects and reduce the false detections of interference, such as stains and mineral lines.

show abstract