--> -->

  • <tr id='9iCmwy'><strong id='9iCmwy'></strong><small id='9iCmwy'></small><button id='9iCmwy'></button><li id='9iCmwy'><noscript id='9iCmwy'><big id='9iCmwy'></big><dt id='9iCmwy'></dt></noscript></li></tr><ol id='9iCmwy'><option id='9iCmwy'><table id='9iCmwy'><blockquote id='9iCmwy'><tbody id='9iCmwy'></tbody></blockquote></table></option></ol><u id='9iCmwy'></u><kbd id='9iCmwy'><kbd id='9iCmwy'></kbd></kbd>

    <code id='9iCmwy'><strong id='9iCmwy'></strong></code>

    <fieldset id='9iCmwy'></fieldset>
          <span id='9iCmwy'></span>

              <ins id='9iCmwy'></ins>
              <acronym id='9iCmwy'><em id='9iCmwy'></em><td id='9iCmwy'><div id='9iCmwy'></div></td></acronym><address id='9iCmwy'><big id='9iCmwy'><big id='9iCmwy'></big><legend id='9iCmwy'></legend></big></address>

              <i id='9iCmwy'><div id='9iCmwy'><ins id='9iCmwy'></ins></div></i>
              <i id='9iCmwy'></i>
            1. <dl id='9iCmwy'></dl>
              1. <blockquote id='9iCmwy'><q id='9iCmwy'><noscript id='9iCmwy'></noscript><dt id='9iCmwy'></dt></q></blockquote><noframes id='9iCmwy'><i id='9iCmwy'></i>
                • 北大核心期刊(《中文核心期刊要目总览》2017版)
                • 中国科技核心期刊(中国科技论文统计源期刊)
                • JST 日本科学技术振兴机构数据库(日)收录期刊

                留言板

                尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

                姓名
                邮箱
                手机号码
                标题
                留言内容
                验证码

                用于多光谱行人检测的改进光照权重融合方法

                金彦亮 葛飞扬

                金彦亮, 葛飞扬. 用于多光谱行人检测的改进光照权重融合方法[J]. 微电子学与计算机, 2021, 38(1): 27-32.
                引用本文: 金彦亮, 葛飞扬. 用于多光谱行人检测的改进光照权重融合方法[J]. 微电子学与计算机, 2021, 38(1): 27-32.
                JIN Yan-liang, GE Fei-yang. Improved fusion method based on ambient illumination condition for multispectral pedestrian detection[J]. Microelectronics & Computer, 2021, 38(1): 27-32.
                Citation: JIN Yan-liang, GE Fei-yang. Improved fusion method based on ambient illumination condition for multispectral pedestrian detection[J]. Microelectronics & Computer, 2021, 38(1): 27-32.

                用于多光谱行人检测的改进光照权重融合方法

                基金项目: 

                上海市科委重点项目 19511102803

                详细信息
                  作者简介:

                  金彦亮??男, (1974-), 博士, 副教授.研究方向为无线传感器网络、无线多媒体传感器网络、无线宽带接入和信号处理

                  通讯作者:

                  葛飞扬(通讯作者)??男, (1994-), 硕士研究生.研究方向为目标检测、行人检测.E-mail: gfy0921@qq.com

                • 中图分类号: TP391.41

                Improved fusion method based on ambient illumination condition for multispectral pedestrian detection

                • 摘要:

                  着卷积神经网络的发展, 基于多光谱图像的行人检测研究取得了巨大进步, 且应用广泛.最近研究表明, 融合由多光谱相机(可见光和热成像相机)捕获的图像信息可以使行人在强光和弱光条件下的检测都变得鲁棒.然而, 如何根据光照条件有效地融合图像◥信息仍缺乏进一步的研究.本文提出了一种多层次特征提取方法, 旨在从不同特征层提取有用信息.同时, 还提出一种置信度融合机制, 测量多光谱图像的光照情况.采用一个融合函数对双流网络输出的分类结果和RPN输出的分类结果进行融合, 提高行人检测的性能.通过实验将所提出的多¤光谱光照感知检测R-CNN(MIAD-RCNN)与现有的多光谱行人检测器进行比较, 该方法在全天候均具有较低的漏检率和较快的速度.

                   

                • 图 1  多光谱光照感知检测R-CNN网络的总体结构

                  图 2  不同方法对比图

                  (a)单独的可见光图像流☆分类器(b)单独的红外图像流分类器

                  表  1  不同层级的特征图的光照感知分类的准确性比较

                  白天 夜晚
                  多层次特征图 96.96% 94.48%
                  第五层特征图 98.90% 97.99%
                  下载: 导出CSV

                  表  2  和原始RPN+下游CNN分类器的漏检率对比

                  Reasonable- all Reasonable- day Reasonable- night
                  可见光图ω 像流分类 39.89% 32.75% 54.53%
                  红外图像流分类 32.50% 34.10% 30.24%
                  置信度融合 25.67% 26.75% 24.84%
                  置信度融合+多层次特征提取 24.92% 25.21% 24.17%
                  下载: 导出CSV

                  表  3  和原始RPN+下游CNN分类器的漏检率对比

                  Reasonable- all Reasonable- day Reasonable- night
                  ACF+T+THOG 54.80% 51.97% 61.19%
                  Halfway Fusion 37.19% 37.12% 35.33%
                  Fusion RPN+BDT 29.68% 30.51% 27.62%
                  FRPN-Sum+TSS 26.67% 26.75% 25.24%
                  IATDNN+IAMSS 26.37% 27.29% 24.41%
                  MIAD-RCNN 24.92% 25.21% 24.17%
                  下载: 导出CSV

                  表  4  不▓同检测方法的速度对比

                  方法 Halfway Fusion Fusion RPN+BDT FRPN- Sum+TSS IATDNN+ IAMSS MIAD- RCNN
                  时间 0.398 s 0.780 s 0.230 s 0.226s 0.218 s
                  下载: 导出CSV
                • [1] ZHANG L L, LIN L, LIANG X D, et al. Is faster R-CNN doing well for pedestrian detection?[C]//14th European Conference on Computer Vision. Amsterdam: Springer, 2016: 443-457. DOI: 10.1007/978-3-319-46475-6_28.
                  [2] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge: ACM, 2015: 91-99.
                  [3] BRAZIL G, YIN X, LIU X M. Illuminating pedestrians via simultaneous detection and segmentation[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 4950-4959. DOI: 10.1109/ICCV.2017.530.
                  [4] HWANG S, PARK J, KIM N, et al. Multispectral pedestrian detection: benchmark dataset and baseline[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 1037-1045. DOI: 10.1109/CVPR.2015.7298706.
                  [5] WAGNER J, FISCHER V, HERMAN M, et al. Multispectral pedestrian detection using deep fusion convolutional neural networks[C]//24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges: ESANN, 2016.
                  [6] LIU J J, ZHANG S T, WANG S, et al. Multispectral deep neural networks for pedestrian detection[M]//WILSON R C, HANCOCK E R, SMITH W A P. Proceedings of the British Machine Vision Conference. British: BMVA Press, 2016. DOI: 10.5244/C.30.73.
                  [7] GUAN D Y, CAO Y P, YANG J X, et al. Fusion of multispectral data through illumination-aware deep neural networks for pedestrian detection[J]. Information Fusion, 2019, 50: 148-157. DOI: 10.1016/j.inffus.2018.11.017.
                  [8] KONIG D, ADAM M, JARVERS C, et al. Fully convolutional region proposal networks for multispectral person detection[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu: IEEE, 2017: 49-56. DOI: 10.1109/CVPRW.2017.36.
                  [9] GUAN D Y, CAO Y P, YANG J X, et al. Exploiting fusion architectures for multispectral pedestrian detection and segmentation[J]. Applied Optics, 2018, 57(18): D108-D116.
                • 加载中
                图(2) / 表(4)
                计量
                • 文章访问数:  2771
                • HTML全文浏览量:  260
                • PDF下载量:  77
                • 被引次数: 0
                出版历程
                • 收稿日期:  2020-04-20
                • 修回日期:  2020-05-20

                目录

                  /

                  返回文章
                  返回