自动驾驶中的目标检测——从大数据集到小数据集

2019 11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI) Pub Date : 2019-06-01 DOI:10.1109/ECAI46879.2019.9041976

David-Traian Iancu, Alexandru Sorici, A. Florea

{"title":"自动驾驶中的目标检测——从大数据集到小数据集","authors":"David-Traian Iancu, Alexandru Sorici, A. Florea","doi":"10.1109/ECAI46879.2019.9041976","DOIUrl":null,"url":null,"abstract":"The purpose of the paper is to analyze the current capacity of pedestrian and vehicle detection through four state of the art detectors -Yolo, SSD, Faster R-CNN and RetinaNet on a big dataset (BDD100K). Also, we analyzed if the results are transferable from one dataset to another - we used a small dataset from our campus, we offered some quantitative results and we made an error analysis based on the dataset characteristics (e.g. weather, light, size of the object).","PeriodicalId":285780,"journal":{"name":"2019 11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"Object detection in autonomous driving - from large to small datasets\",\"authors\":\"David-Traian Iancu, Alexandru Sorici, A. Florea\",\"doi\":\"10.1109/ECAI46879.2019.9041976\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The purpose of the paper is to analyze the current capacity of pedestrian and vehicle detection through four state of the art detectors -Yolo, SSD, Faster R-CNN and RetinaNet on a big dataset (BDD100K). Also, we analyzed if the results are transferable from one dataset to another - we used a small dataset from our campus, we offered some quantitative results and we made an error analysis based on the dataset characteristics (e.g. weather, light, size of the object).\",\"PeriodicalId\":285780,\"journal\":{\"name\":\"2019 11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)\",\"volume\":\"79 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ECAI46879.2019.9041976\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ECAI46879.2019.9041976","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 8

摘要

本文的目的是在大数据集(BDD100K)上，通过yolo、SSD、Faster R-CNN和RetinaNet四种最先进的检测器来分析当前行人和车辆检测的能力。此外，我们还分析了结果是否可以从一个数据集转移到另一个数据集——我们使用了一个来自我们校园的小数据集，我们提供了一些定量结果，并根据数据集的特征(例如天气、光线、物体的大小)进行了误差分析。

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

Object detection in autonomous driving - from large to small datasets

The purpose of the paper is to analyze the current capacity of pedestrian and vehicle detection through four state of the art detectors -Yolo, SSD, Faster R-CNN and RetinaNet on a big dataset (BDD100K). Also, we analyzed if the results are transferable from one dataset to another - we used a small dataset from our campus, we offered some quantitative results and we made an error analysis based on the dataset characteristics (e.g. weather, light, size of the object).

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

2019 11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)

自引率

0.00%

发文量