海报:基于深度学习的传感器多目标检测的边缘计算

2022 IEEE/ACM 7th Symposium on Edge Computing (SEC) Pub Date : 2022-12-01 DOI:10.1109/SEC54971.2022.00033

Alperen Kalay, Alparslan Fisne

{"title":"海报:基于深度学习的传感器多目标检测的边缘计算","authors":"Alperen Kalay, Alparslan Fisne","doi":"10.1109/SEC54971.2022.00033","DOIUrl":null,"url":null,"abstract":"This study purposes a real-time computing of deep learning-based multi-target detection in defense-purpose edge sensors. Our study suggests two fundamental optimizations to accelerate target detection inference model: algebraic enhancements and post-training quantization. Comprehensive benchmark results show that our computing design achieves real-time multi-target detection on energy-efficient edge devices.","PeriodicalId":364062,"journal":{"name":"2022 IEEE/ACM 7th Symposium on Edge Computing (SEC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Poster: Edge Computing for Deep Learning-based Sensor Multi-Target Detection\",\"authors\":\"Alperen Kalay, Alparslan Fisne\",\"doi\":\"10.1109/SEC54971.2022.00033\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study purposes a real-time computing of deep learning-based multi-target detection in defense-purpose edge sensors. Our study suggests two fundamental optimizations to accelerate target detection inference model: algebraic enhancements and post-training quantization. Comprehensive benchmark results show that our computing design achieves real-time multi-target detection on energy-efficient edge devices.\",\"PeriodicalId\":364062,\"journal\":{\"name\":\"2022 IEEE/ACM 7th Symposium on Edge Computing (SEC)\",\"volume\":\"9 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE/ACM 7th Symposium on Edge Computing (SEC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SEC54971.2022.00033\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE/ACM 7th Symposium on Edge Computing (SEC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SEC54971.2022.00033","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

研究了基于深度学习的国防边缘传感器多目标检测的实时计算问题。我们的研究提出了加速目标检测推理模型的两种基本优化方法:代数增强和训练后量化。综合基准测试结果表明，我们的计算设计实现了对节能边缘设备的实时多目标检测。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Poster: Edge Computing for Deep Learning-based Sensor Multi-Target Detection

This study purposes a real-time computing of deep learning-based multi-target detection in defense-purpose edge sensors. Our study suggests two fundamental optimizations to accelerate target detection inference model: algebraic enhancements and post-training quantization. Comprehensive benchmark results show that our computing design achieves real-time multi-target detection on energy-efficient edge devices.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2022 IEEE/ACM 7th Symposium on Edge Computing (SEC)

自引率

0.00%

发文量