{"title":"IFS-DETR:基于端到端结构化网络的工业火灾烟雾实时检测算法","authors":"","doi":"10.1016/j.measurement.2024.115660","DOIUrl":null,"url":null,"abstract":"<div><p>Fire prevention in industrial settings are paramount for ensuring human safety and economic stability. However, current mainstream DETR detectors face significant challenges in applications due to the necessity for extensive memory accesses and inference delays. To tackle these complexities, we propose an Industrial Fire Smoke Detector based on an end-to-end structured framework. In a series of innovative optimizations, we firstly adopt a more lightweight backbone network, LeanNet, for feature extraction. Combined with the optimized Transformer architecture, this approach enhances the model’s detection speed to address real-time challenges effectively. Secondly, we introduce a Feature Fusion Network based on alignment mechanisms to enhance the DETR model’s multi-scale object representation capabilities without significantly increasing latency. Subsequently, to facilitate easier training and optimization of IFS-DETR, we introduce IoU-aware query selection and an aspect ratio-based denoising training strategy, and enhance the localization loss function using Inner-SIoU. Finally, we deploy IFS-DETR on NVIDIA Jetson Orin Nano. The dataset is available at <span><span>https://github.com/Sonnenb1ume/IFS-DETR</span><svg><path></path></svg></span>.</p></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":null,"pages":null},"PeriodicalIF":5.2000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0263224124015458/pdfft?md5=611c18cfd54260852ed8b85809b6b200&pid=1-s2.0-S0263224124015458-main.pdf","citationCount":"0","resultStr":"{\"title\":\"IFS-DETR: A real-time industrial fire smoke detection algorithm based on an end-to-end structured network\",\"authors\":\"\",\"doi\":\"10.1016/j.measurement.2024.115660\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Fire prevention in industrial settings are paramount for ensuring human safety and economic stability. However, current mainstream DETR detectors face significant challenges in applications due to the necessity for extensive memory accesses and inference delays. To tackle these complexities, we propose an Industrial Fire Smoke Detector based on an end-to-end structured framework. In a series of innovative optimizations, we firstly adopt a more lightweight backbone network, LeanNet, for feature extraction. Combined with the optimized Transformer architecture, this approach enhances the model’s detection speed to address real-time challenges effectively. Secondly, we introduce a Feature Fusion Network based on alignment mechanisms to enhance the DETR model’s multi-scale object representation capabilities without significantly increasing latency. Subsequently, to facilitate easier training and optimization of IFS-DETR, we introduce IoU-aware query selection and an aspect ratio-based denoising training strategy, and enhance the localization loss function using Inner-SIoU. Finally, we deploy IFS-DETR on NVIDIA Jetson Orin Nano. The dataset is available at <span><span>https://github.com/Sonnenb1ume/IFS-DETR</span><svg><path></path></svg></span>.</p></div>\",\"PeriodicalId\":18349,\"journal\":{\"name\":\"Measurement\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.2000,\"publicationDate\":\"2024-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0263224124015458/pdfft?md5=611c18cfd54260852ed8b85809b6b200&pid=1-s2.0-S0263224124015458-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Measurement\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0263224124015458\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Measurement","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0263224124015458","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
IFS-DETR: A real-time industrial fire smoke detection algorithm based on an end-to-end structured network
Fire prevention in industrial settings are paramount for ensuring human safety and economic stability. However, current mainstream DETR detectors face significant challenges in applications due to the necessity for extensive memory accesses and inference delays. To tackle these complexities, we propose an Industrial Fire Smoke Detector based on an end-to-end structured framework. In a series of innovative optimizations, we firstly adopt a more lightweight backbone network, LeanNet, for feature extraction. Combined with the optimized Transformer architecture, this approach enhances the model’s detection speed to address real-time challenges effectively. Secondly, we introduce a Feature Fusion Network based on alignment mechanisms to enhance the DETR model’s multi-scale object representation capabilities without significantly increasing latency. Subsequently, to facilitate easier training and optimization of IFS-DETR, we introduce IoU-aware query selection and an aspect ratio-based denoising training strategy, and enhance the localization loss function using Inner-SIoU. Finally, we deploy IFS-DETR on NVIDIA Jetson Orin Nano. The dataset is available at https://github.com/Sonnenb1ume/IFS-DETR.
期刊介绍:
Contributions are invited on novel achievements in all fields of measurement and instrumentation science and technology. Authors are encouraged to submit novel material, whose ultimate goal is an advancement in the state of the art of: measurement and metrology fundamentals, sensors, measurement instruments, measurement and estimation techniques, measurement data processing and fusion algorithms, evaluation procedures and methodologies for plants and industrial processes, performance analysis of systems, processes and algorithms, mathematical models for measurement-oriented purposes, distributed measurement systems in a connected world.