人工中央凹视觉注意的目标检测与定位

Cristina Melício, R. Figueiredo, A. F. Almeida, A. Bernardino, J. Santos-Victor
{"title":"人工中央凹视觉注意的目标检测与定位","authors":"Cristina Melício, R. Figueiredo, A. F. Almeida, A. Bernardino, J. Santos-Victor","doi":"10.1109/DEVLRN.2018.8761032","DOIUrl":null,"url":null,"abstract":"In the last decades, in order to make the processing of a scene more efficient, biologically inspired approaches have been proposed. Visual attention models are being studied and actively developed in order to reduce the complexity and computational time of the existing methods. We propose a biologically inspired model that combines a single pre-trained CNN architecture with an artificial foveal visual system that performs simultaneously the classification and localization of objects in images. This model is based on the fact that only a small part of the image is processed with high resolution at each time so we load a foveated image in the network and successively employ feed-forward passes to determine the class labels and then via backward propagation determine the object possible locations according to each semantic label. By directing the attention to the center of the proposed location we mimic the human saccadic eye movements. In the results obtained we used the ILSVRC 2012 validation data set in a GoogLeNet CNN. We demonstrate that for non-centered objects the gain of the classification performance between iterations is significant showing that when mimicking the human visual behaviour of foveation, saccades are needed to integrate the information at each time.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"38 4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Object detection and localization with Artificial Foveal Visual Attention\",\"authors\":\"Cristina Melício, R. Figueiredo, A. F. Almeida, A. Bernardino, J. Santos-Victor\",\"doi\":\"10.1109/DEVLRN.2018.8761032\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the last decades, in order to make the processing of a scene more efficient, biologically inspired approaches have been proposed. Visual attention models are being studied and actively developed in order to reduce the complexity and computational time of the existing methods. We propose a biologically inspired model that combines a single pre-trained CNN architecture with an artificial foveal visual system that performs simultaneously the classification and localization of objects in images. This model is based on the fact that only a small part of the image is processed with high resolution at each time so we load a foveated image in the network and successively employ feed-forward passes to determine the class labels and then via backward propagation determine the object possible locations according to each semantic label. By directing the attention to the center of the proposed location we mimic the human saccadic eye movements. In the results obtained we used the ILSVRC 2012 validation data set in a GoogLeNet CNN. We demonstrate that for non-centered objects the gain of the classification performance between iterations is significant showing that when mimicking the human visual behaviour of foveation, saccades are needed to integrate the information at each time.\",\"PeriodicalId\":236346,\"journal\":{\"name\":\"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)\",\"volume\":\"38 4 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/DEVLRN.2018.8761032\",\"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 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DEVLRN.2018.8761032","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

摘要

在过去的几十年里,为了更有效地处理场景,人们提出了受生物学启发的方法。为了减少现有方法的复杂性和计算时间,人们正在积极研究和开发视觉注意模型。我们提出了一个受生物学启发的模型,该模型将单个预训练的CNN架构与人工中央凹视觉系统相结合,该系统可以同时对图像中的物体进行分类和定位。该模型基于每次只对一小部分图像进行高分辨率处理的事实,因此我们在网络中加载一个注视点图像,依次采用前馈传递确定类标签,然后通过后向传播根据每个语义标签确定目标的可能位置。通过将注意力引导到指定位置的中心,我们模仿了人类的跳眼运动。在得到的结果中,我们使用了GoogLeNet CNN的ILSVRC 2012验证数据集。研究表明,对于非中心目标,迭代之间的分类性能增益是显著的,这表明在模仿人类注视点的视觉行为时,每次都需要扫视来整合信息。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Object detection and localization with Artificial Foveal Visual Attention
In the last decades, in order to make the processing of a scene more efficient, biologically inspired approaches have been proposed. Visual attention models are being studied and actively developed in order to reduce the complexity and computational time of the existing methods. We propose a biologically inspired model that combines a single pre-trained CNN architecture with an artificial foveal visual system that performs simultaneously the classification and localization of objects in images. This model is based on the fact that only a small part of the image is processed with high resolution at each time so we load a foveated image in the network and successively employ feed-forward passes to determine the class labels and then via backward propagation determine the object possible locations according to each semantic label. By directing the attention to the center of the proposed location we mimic the human saccadic eye movements. In the results obtained we used the ILSVRC 2012 validation data set in a GoogLeNet CNN. We demonstrate that for non-centered objects the gain of the classification performance between iterations is significant showing that when mimicking the human visual behaviour of foveation, saccades are needed to integrate the information at each time.
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信