A Scene Knowledge Integrating Network for Transmission Line Multi-Fitting Detection

Aiming at the severe occlusion problem and the tiny-scale object problem in the multi-fitting detection task, the Scene Knowledge Integrating Network (SKIN), including the scene filter module (SFM) and scene structure information module (SSIM) is proposed. Firstly, the particularity of the scene in...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinhang Chen, Xinsheng Xu, Jing Xu, Wenjie Zheng, Qianming Wang
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/24/8207
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037454983135232
author Xinhang Chen
Xinsheng Xu
Jing Xu
Wenjie Zheng
Qianming Wang
author_facet Xinhang Chen
Xinsheng Xu
Jing Xu
Wenjie Zheng
Qianming Wang
author_sort Xinhang Chen
collection DOAJ
description Aiming at the severe occlusion problem and the tiny-scale object problem in the multi-fitting detection task, the Scene Knowledge Integrating Network (SKIN), including the scene filter module (SFM) and scene structure information module (SSIM) is proposed. Firstly, the particularity of the scene in the multi-fitting detection task is analyzed. Hence, the aggregation of the fittings is defined as the scene according to the professional knowledge of the power field and the habit of the operators in identifying the fittings. So, the scene knowledge will include global context information, fitting fine-grained visual information and scene structure information. Then, a scene filter module is designed to learn the global context information and fitting fine-grained visual information, and a scene structure module is designed to learn the scene structure information. Finally, the scene semantic features are used as the carrier to integrate three categories of information into the relative scene features, which can assist in the recognition of the occluded fittings and the tiny-scale fittings after feature mining and feature integration. The experiments show that the proposed network can effectively improve the performance of the multi-fitting detection task compared with the Faster R-CNN and other state-of-the-art models. In particular, the detection performances of the occluded and tiny-scale fittings are significantly improved.
format Article
id doaj-art-e79c048f00c34cfe904123152de24fdc
institution DOAJ
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e79c048f00c34cfe904123152de24fdc2025-08-20T02:56:51ZengMDPI AGSensors1424-82202024-12-012424820710.3390/s24248207A Scene Knowledge Integrating Network for Transmission Line Multi-Fitting DetectionXinhang Chen0Xinsheng Xu1Jing Xu2Wenjie Zheng3Qianming Wang4College of Quality & Standardization, China Jiliang University, Hangzhou 310018, ChinaCollege of Quality & Standardization, China Jiliang University, Hangzhou 310018, ChinaState Grid Huzhou Electric Power Supply Company, Huzhou 313000, ChinaAutomation Department, North China Electric Power University, Baoding 071003, ChinaAutomation Department, North China Electric Power University, Baoding 071003, ChinaAiming at the severe occlusion problem and the tiny-scale object problem in the multi-fitting detection task, the Scene Knowledge Integrating Network (SKIN), including the scene filter module (SFM) and scene structure information module (SSIM) is proposed. Firstly, the particularity of the scene in the multi-fitting detection task is analyzed. Hence, the aggregation of the fittings is defined as the scene according to the professional knowledge of the power field and the habit of the operators in identifying the fittings. So, the scene knowledge will include global context information, fitting fine-grained visual information and scene structure information. Then, a scene filter module is designed to learn the global context information and fitting fine-grained visual information, and a scene structure module is designed to learn the scene structure information. Finally, the scene semantic features are used as the carrier to integrate three categories of information into the relative scene features, which can assist in the recognition of the occluded fittings and the tiny-scale fittings after feature mining and feature integration. The experiments show that the proposed network can effectively improve the performance of the multi-fitting detection task compared with the Faster R-CNN and other state-of-the-art models. In particular, the detection performances of the occluded and tiny-scale fittings are significantly improved.https://www.mdpi.com/1424-8220/24/24/8207deep learningobject detectiontransmission line fittingsscene knowledgecontext information
spellingShingle Xinhang Chen
Xinsheng Xu
Jing Xu
Wenjie Zheng
Qianming Wang
A Scene Knowledge Integrating Network for Transmission Line Multi-Fitting Detection
Sensors
deep learning
object detection
transmission line fittings
scene knowledge
context information
title A Scene Knowledge Integrating Network for Transmission Line Multi-Fitting Detection
title_full A Scene Knowledge Integrating Network for Transmission Line Multi-Fitting Detection
title_fullStr A Scene Knowledge Integrating Network for Transmission Line Multi-Fitting Detection
title_full_unstemmed A Scene Knowledge Integrating Network for Transmission Line Multi-Fitting Detection
title_short A Scene Knowledge Integrating Network for Transmission Line Multi-Fitting Detection
title_sort scene knowledge integrating network for transmission line multi fitting detection
topic deep learning
object detection
transmission line fittings
scene knowledge
context information
url https://www.mdpi.com/1424-8220/24/24/8207
work_keys_str_mv AT xinhangchen asceneknowledgeintegratingnetworkfortransmissionlinemultifittingdetection
AT xinshengxu asceneknowledgeintegratingnetworkfortransmissionlinemultifittingdetection
AT jingxu asceneknowledgeintegratingnetworkfortransmissionlinemultifittingdetection
AT wenjiezheng asceneknowledgeintegratingnetworkfortransmissionlinemultifittingdetection
AT qianmingwang asceneknowledgeintegratingnetworkfortransmissionlinemultifittingdetection
AT xinhangchen sceneknowledgeintegratingnetworkfortransmissionlinemultifittingdetection
AT xinshengxu sceneknowledgeintegratingnetworkfortransmissionlinemultifittingdetection
AT jingxu sceneknowledgeintegratingnetworkfortransmissionlinemultifittingdetection
AT wenjiezheng sceneknowledgeintegratingnetworkfortransmissionlinemultifittingdetection
AT qianmingwang sceneknowledgeintegratingnetworkfortransmissionlinemultifittingdetection