基于卷积神经网络的车辆细粒度识别在现实世界中的应用

2018 14th Symposium on Neural Networks and Applications (NEUREL) Pub Date : 2018-11-01 DOI:10.1109/NEUREL.2018.8587012

Jakub Špaňhel, Jakub Sochor, A. Makarov

{"title":"基于卷积神经网络的车辆细粒度识别在现实世界中的应用","authors":"Jakub Špaňhel, Jakub Sochor, A. Makarov","doi":"10.1109/NEUREL.2018.8587012","DOIUrl":null,"url":null,"abstract":"We explore the implementation of vehicle fine-grained type and color recognition based on neural networks in a real-world application. We suggest changes to the previously published method with respect to capabilities of low-powered devices, such as Nvidia Jetson. Experimental evaluation shows that the accuracy of MobileNet net slightly decreases compared to ResNet-50 from 89.55% to 86.13% while inference is 2.4× faster on Jetson.","PeriodicalId":371831,"journal":{"name":"2018 14th Symposium on Neural Networks and Applications (NEUREL)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Vehicle Fine-grained Recognition Based on Convolutional Neural Networks for Real-world Applications\",\"authors\":\"Jakub Špaňhel, Jakub Sochor, A. Makarov\",\"doi\":\"10.1109/NEUREL.2018.8587012\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We explore the implementation of vehicle fine-grained type and color recognition based on neural networks in a real-world application. We suggest changes to the previously published method with respect to capabilities of low-powered devices, such as Nvidia Jetson. Experimental evaluation shows that the accuracy of MobileNet net slightly decreases compared to ResNet-50 from 89.55% to 86.13% while inference is 2.4× faster on Jetson.\",\"PeriodicalId\":371831,\"journal\":{\"name\":\"2018 14th Symposium on Neural Networks and Applications (NEUREL)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 14th Symposium on Neural Networks and Applications (NEUREL)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NEUREL.2018.8587012\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 14th Symposium on Neural Networks and Applications (NEUREL)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NEUREL.2018.8587012","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 6

摘要

我们在现实世界的应用中探索了基于神经网络的车辆细粒度类型和颜色识别的实现。我们建议针对低功耗设备(如Nvidia Jetson)的功能对先前发布的方法进行更改。实验评估表明，与ResNet-50相比，MobileNet net的准确率略有下降，从89.55%降至86.13%，而在Jetson上的推理速度提高了2.4倍。

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

Vehicle Fine-grained Recognition Based on Convolutional Neural Networks for Real-world Applications

We explore the implementation of vehicle fine-grained type and color recognition based on neural networks in a real-world application. We suggest changes to the previously published method with respect to capabilities of low-powered devices, such as Nvidia Jetson. Experimental evaluation shows that the accuracy of MobileNet net slightly decreases compared to ResNet-50 from 89.55% to 86.13% while inference is 2.4× faster on Jetson.

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

2018 14th Symposium on Neural Networks and Applications (NEUREL)

自引率

0.00%

发文量