Query：
学者姓名：陈丹
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
The efficient pointer meter reading methods have been proposed based on machine vision to replace timeconsuming manual inspections for the industrial monitoring. However, the interference factors, such as rain or dirt, can occlude meter, which poses obstacles in the recognition and labeling of pointer and scales. To solve these problems, we propose a multi-task network with pointer and main scale detection (PMSD-Net) for the occluded meter reading with synthetic data generation technology. Specifically, dense parallel dilated convolution block is proposed for correlating the pointer and main scale features with large receptive field. Multi-scale feature fusion is designed to purify noisy features for the detailed information extraction. The relation reconstruction mechanism is designed to reconstruct the feature relation under severe occlusion. Moreover, the keypoint detection branch is designed to detect meter center and pointer tip according to the segmented pointer, which can identify changeable position of the segmented pointer tip to determine the pointer orientation. Finally, the synthetic data generation technology is developed to generate massive labeled data with simulated interference factors in the meter for the training, which enhances the generalization ability of PMSD-Net in various occlusion scenes. Experimental results indicate that PMSD-Net can segment more accurate regions of pointer and main scale and detect the changeable position of pointer tip for occluded meters, thereby improving the accuracy in reading occluded meters.
Keyword ：
Keypoint detection Keypoint detection Multi-task network Multi-task network Occluded meter reading Occluded meter reading Pointer and main scale segmentation Pointer and main scale segmentation Synthetic data generation Synthetic data generation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Ye , Xu, Zhezhuang , Wu, Yiying et al. A multi-task network for occluded meter reading with synthetic data generation technology [J]. | ADVANCED ENGINEERING INFORMATICS , 2025 , 64 . |
| MLA | Lin, Ye et al. "A multi-task network for occluded meter reading with synthetic data generation technology" . | ADVANCED ENGINEERING INFORMATICS 64 (2025) . |
| APA | Lin, Ye , Xu, Zhezhuang , Wu, Yiying , Yuan, Meng , Chen, Dan , Zhu, Jinyang et al. A multi-task network for occluded meter reading with synthetic data generation technology . | ADVANCED ENGINEERING INFORMATICS , 2025 , 64 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Machine vision-based meter reading technologies have been developed to monitor the status of devices in industrial sites. However, the integrity of the pointer can be destroyed by the occlusion on the meter, such as dirt or rain. In this case, the pointer detection becomes a challenging task in the meter reading. To overcome this challenge, in this article, the pointer generative adversarial network (Pointer-GAN) is proposed for pointer mask generation. Specifically, an occlusion simulation method is developed in the data preprocessing to provide sufficient images of occluded meters (OMs) in the training phase, and the dilated convolution is adopted in the residual block to strengthen the correlation among pointer features in the long-range. Next, the multiscale attention mechanism (MAM) is designed for preventing the pointer feature in the low-level from being affected by the noise. Finally, the dense dilated convolution block (DDC block) is utilized to integrate the pointer feature in the low and high level for the pointer mask generation. The experiments demonstrate that the Pointer-GAN can generate the pointer mask with higher accuracy for the meters under occlusion compared to the other methods, thereby improving success rates of reading meters in different occlusion scenarios.
Keyword ：
Accuracy Accuracy Convolution Convolution Deep learning Deep learning Feature extraction Feature extraction Generative adversarial network (GAN) Generative adversarial network (GAN) Generative adversarial networks Generative adversarial networks Generators Generators Meter reading Meter reading Meters Meters occlusion occlusion pointer mask generation pointer mask generation pointer meter reading pointer meter reading Training Training YOLO YOLO
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Ye , Xu, Zhezhuang , Chen, Dan et al. Occluded Meter Reading With Pointer Mask Generation Based on Generative Adversarial Network [J]. | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2025 , 74 . |
| MLA | Lin, Ye et al. "Occluded Meter Reading With Pointer Mask Generation Based on Generative Adversarial Network" . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 74 (2025) . |
| APA | Lin, Ye , Xu, Zhezhuang , Chen, Dan , Yuan, Meng , Zhu, Jinyang , Yuan, Yazhou . Occluded Meter Reading With Pointer Mask Generation Based on Generative Adversarial Network . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2025 , 74 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对DeepLabv3+网络对多个目标图像的分割性能不够优越、容易丢失图像的细节信息、产生分割断裂等问题，提出一种基于改进DeepLabv3+网络的图像语义分割方法。首先，在空洞空间金字塔池化ASPP模块中添加空洞卷积分支，并将不同空洞卷积分支与输入特征拼接，实现不同感受野下的多通道特征信息融合；其次，在ASPP模块后引入PSA注意力机制，减少特征提取时的信息损失。实验结果表明，与原DeepLabv3+网络相比，改进DeepLabv3+网络模型在PASCAL VOC 2012数据集上MIoU总体提高了1.62%,在自制数据集上MIoU总体提高了0.63%,验证了改进DeepLabv3+网络模型的良好分割性能以及在现实场景下的可行性。
Keyword ：
DeepLabv3+ DeepLabv3+ PSA注意力机制 PSA注意力机制 特征信息融合 特征信息融合 语义分割 语义分割
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 柯寅 , 陈丹 . 基于改进DeepLabv3+网络的图像语义分割方法 [J]. | 智能计算机与应用 , 2025 , 15 (04) : 17-24 . |
| MLA | 柯寅 et al. "基于改进DeepLabv3+网络的图像语义分割方法" . | 智能计算机与应用 15 . 04 (2025) : 17-24 . |
| APA | 柯寅 , 陈丹 . 基于改进DeepLabv3+网络的图像语义分割方法 . | 智能计算机与应用 , 2025 , 15 (04) , 17-24 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
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.
Keyword ：
deep learning deep learning multi-source data fusion multi-source data fusion semantic segmentation semantic segmentation U-Net U-Net wood defect detection wood defect detection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhu, Yuhang , Xu, Zhezhuang , Lin, Ye et al. A Multi-Source Data Fusion Network for Wood Surface Broken Defect Segmentation [J]. | SENSORS , 2024 , 24 (5) . |
| MLA | Zhu, Yuhang et al. "A Multi-Source Data Fusion Network for Wood Surface Broken Defect Segmentation" . | SENSORS 24 . 5 (2024) . |
| APA | Zhu, Yuhang , Xu, Zhezhuang , Lin, Ye , Chen, Dan , Ai, Zhijie , Zhang, Hongchuan . A Multi-Source Data Fusion Network for Wood Surface Broken Defect Segmentation . | SENSORS , 2024 , 24 (5) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The meter reading with machine vision greatly improves the efficiency of industrial monitoring. However, the pointer and scales of the meter can be occluded by rain or dirt, which greatly reduces the accuracy of the meter reading recognition. To solve this problem, we propose a generative adversarial network (PMS-GAN) with pointer generation and main scale detection for occluded meter reading. Specifically, dilated convolution block is designed to correlate separated pointer features. Then multi-scale feature fusion mechanism is proposed to guarantee the precision of pointer generation and main scale detection with guidance of semantic information. Moreover, feature enhancement mechanism is proposed to construct the long -range relationship for generating pointer under high occlusion. Finally, the reading is accomplished by calculating local angle with generated pointer and detected main scales. Experiments show that PMS-GAN can generate more intact pointer and detect main scales to guarantee the success and accuracy of occluded meter reading.
Keyword ：
Generative adversarial network Generative adversarial network Local angle calculation Local angle calculation Main scale detection Main scale detection Occluded meter reading Occluded meter reading Pointer generation Pointer generation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Ye , Xu, Zhezhuang , Yuan, Meng et al. Pointer generation and main scale detection for occluded meter reading based on generative adversarial network [J]. | MEASUREMENT , 2024 , 234 . |
| MLA | Lin, Ye et al. "Pointer generation and main scale detection for occluded meter reading based on generative adversarial network" . | MEASUREMENT 234 (2024) . |
| APA | Lin, Ye , Xu, Zhezhuang , Yuan, Meng , Chen, Dan , Zhu, Jinyang , Yuan, Yazhou . Pointer generation and main scale detection for occluded meter reading based on generative adversarial network . | MEASUREMENT , 2024 , 234 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Surface defect detection of sawn timber is a critical task to ensure the quality of wooden products. Current methods have challenges in considering detection accuracy and speed simultaneously, due to the complexity of defects and the massive length of sawn timbers. Specifically, there are scale variation, large intraclass difference and high interclass similarity in the defects, which reduce the detection accuracy. To overcome these challenges, we propose an efficient multilevel-feature integration network (EMINet) based on YOLOv5s. To obtain discriminative features of defects, the cross fusion module (CFM) is proposed to fully integrate the multilevel features of backbone. In the CFM, the local information aggregation is designed to enrich the detailed information of high-level features, and the global information aggregation is designed to enhance the semantic information of low-level features. Experimental results demonstrate that the proposed EMINet achieves better accuracy with fast speed compared with the state-of-the-art methods.
Keyword ：
information aggregation information aggregation machine vision machine vision multilevel feature integration multilevel feature integration sawn timber sawn timber surface defect detection surface defect detection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhu, Yuhang , Xu, Zhezhuang , Lin, Ye et al. Surface defect detection of sawn timbers based on efficient multilevel feature integration [J]. | MEASUREMENT SCIENCE AND TECHNOLOGY , 2024 , 35 (4) . |
| MLA | Zhu, Yuhang et al. "Surface defect detection of sawn timbers based on efficient multilevel feature integration" . | MEASUREMENT SCIENCE AND TECHNOLOGY 35 . 4 (2024) . |
| APA | Zhu, Yuhang , Xu, Zhezhuang , Lin, Ye , Chen, Dan , Zheng, Kunxin , Yuan, Yazhou . Surface defect detection of sawn timbers based on efficient multilevel feature integration . | MEASUREMENT SCIENCE AND TECHNOLOGY , 2024 , 35 (4) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Occlusion recognition plays a vital role in smart manufacturing and industrial automation. This paper proposes an enhanced YOLOv8-based model designed to accurately recognize and locate occluded objects in industrial environments, assisting robots in precise grasping tasks. The model integrates the AKConv module and the Effciou loss function, which improve feature extraction and bounding box regression, especially in complex and highly occluded scenarios. Experimental results confirm that the modified YOLOv8s_Effciou model achieves a balanced performance across different levels of occlusion, showing notable robustness in challenging environments with high occlusion. © 2024 IEEE.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, R. , Zhang, H. , Liu, Z. et al. CAE-YOLOV8: Occlusion Object Detection Based on Improved YOLOv8 [未知]. |
| MLA | Liu, R. et al. "CAE-YOLOV8: Occlusion Object Detection Based on Improved YOLOv8" [未知]. |
| APA | Liu, R. , Zhang, H. , Liu, Z. , Chen, D. . CAE-YOLOV8: Occlusion Object Detection Based on Improved YOLOv8 [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对遮挡目标的机器人抓取存在的遮挡干扰问题,提出了改进的YOLO-CA-SD和语义分割的遮挡目标检测模型及抓取方法,完成多目标及非目标物互相遮挡干扰情况下的抓取.首先,该模型在YOLOv5l中添加坐标注意力,在损失函数基础上考虑检测框匹配方向的问题,增加框之间的角度信息,并对原模型检测部分进行解耦,减少耦合造成的信息丢失.其次,提出了改进的DeeplabV3+目标分割模型,用MobileNetV2 替换DeeplabV3+原主干网络,减小模型复杂度,在空洞空间金字塔池化结构中添加CA模块融合像素坐标信息提高分割精度,解决了遮挡干扰问题.最后,利用点云配准得到目标姿态相对于模板姿态的末端旋转角及最优抓取点.在 2 750 张自主构建的常用工具遮挡数据集上进行性能测试,结果表明:改进后的模型在mAP@0.5,mAP@0.5:0.95、60%目标物体遮挡率数据集及 60%非目标物体遮挡率数据集上的检测精度分别提高了 0.052%、0.968%、6.000%、7.400%.此基础上改进的语义分割模型分割速度和MIOU分别提升了 33.45%和 0.625%,并且通过ABB IRB1200 机械臂实现遮挡目标的抓取实验,验证了该方法的可行性与实用性.
Keyword ：
DeeplabV3+模型 DeeplabV3+模型 YOLO YOLO 点云配准 点云配准 目标抓取 目标抓取 遮挡目标检测 遮挡目标检测
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 林哲 , 潘慧琳 , 陈丹 . 融合改进YOLO和语义分割的遮挡目标抓取方法 [J]. | 电子测量与仪器学报 , 2024 , 38 (12) : 190-201 . |
| MLA | 林哲 et al. "融合改进YOLO和语义分割的遮挡目标抓取方法" . | 电子测量与仪器学报 38 . 12 (2024) : 190-201 . |
| APA | 林哲 , 潘慧琳 , 陈丹 . 融合改进YOLO和语义分割的遮挡目标抓取方法 . | 电子测量与仪器学报 , 2024 , 38 (12) , 190-201 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对ACCT-Ⅲ实验箱开展"自动控制原理"实验教学缺乏具体的被控对象的问题,设计以电机为被控对象的实验教学,内容包括建立电机电流和速度数学模型,设计电流、速度闭环PID控制系统,控制系统Matlab仿真,实际伺服电机平台实验等.该实验教学从实物建模、模型仿真、控制器设计到控制系统仿真与实物验证,以项目设计理念为指导,让学生更好地理论与实际相结合,达到知识的内化,提高了教学质量.
Keyword ：
仿真与实物验证 仿真与实物验证 电机实验教学 电机实验教学 自动控制原理 自动控制原理
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 黄宴委 , 程国扬 , 陈丹 et al. 基于电机的"自动控制原理"实验教学 [J]. | 电气电子教学学报 , 2024 , 46 (4) : 186-191 . |
| MLA | 黄宴委 et al. "基于电机的"自动控制原理"实验教学" . | 电气电子教学学报 46 . 4 (2024) : 186-191 . |
| APA | 黄宴委 , 程国扬 , 陈丹 , 陈少斌 . 基于电机的"自动控制原理"实验教学 . | 电气电子教学学报 , 2024 , 46 (4) , 186-191 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Detecting wood broken defects through machine vision is challenging due to the similar appearance of defect and defect-free regions on images. Laser profilometer is a reasonable solution, nevertheless, imperfect point cloud representation, such as slope profile, incontinuity of tiny defects and similarity between broken defects and sound area, poses obstacles. To overcome these challenges, this study proposes a multi-line detection method based on bidirectional long-and short-term memory network (Bi-LSTM) for real-time wood broken defect detection. The feature that represents the extent of surface damage in line-level is designed by residual extraction and sorting operation. The Bi-LSTM combines adjacent information to exaggerate semantic information of detection line. Context information extracted by Bi-LSTM are concatenated for multi -line detection to reduce computation complexity. Finally, detection results are modified by considering the information of adjacent lines of point cloud. Experimental results show that the proposed method achieves real-time detection with high accuracy.
Keyword ：
Bi-LSTM Bi-LSTM Feature extraction Feature extraction Laser profilometer Laser profilometer Multi-line detection Multi-line detection Wood broken defect Wood broken defect
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, Zhezhuang , Lin, Ye , Chen, Dan et al. Wood broken defect detection with laser profilometer based on Bi-LSTM network [J]. | EXPERT SYSTEMS WITH APPLICATIONS , 2023 , 242 . |
| MLA | Xu, Zhezhuang et al. "Wood broken defect detection with laser profilometer based on Bi-LSTM network" . | EXPERT SYSTEMS WITH APPLICATIONS 242 (2023) . |
| APA | Xu, Zhezhuang , Lin, Ye , Chen, Dan , Yuan, Meng , Zhu, Yuhang , Ai, Zhijie et al. Wood broken defect detection with laser profilometer based on Bi-LSTM network . | EXPERT SYSTEMS WITH APPLICATIONS , 2023 , 242 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
