###
计算机系统应用:2019,28(1):107-112
本文二维码信息
码上扫一扫!
面向车辆检测的扩张全卷积神经网络
程雅慧1,2,3, 蔡烜4, 冯瑞1,2,3
(1.复旦大学 计算机科学技术学院, 上海 201203;2.上海视频技术与系统工程研究中心, 上海 201203;3.复旦大学 上海市智能信息处理实验室, 上海 201203;4.物联网技术研发中心, 上海 201204)
Dilated Fully Convolutional Network with Grouped Proposals for Vehicle Detection
(1.School of Computer Science, Fudan University, Shanghai 201203, China;2.Shanghai Engineering Research Center for Video Technology and System, Shanghai 201203, China;3.Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai 201203, China;4.Internet of Things Technology Research and Development Center, Shanghai 201204, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 135次   下载 100
投稿时间:2018-07-31    修订日期:2018-08-27
中文摘要: 近年来,深度学习方法被广泛用来解决车辆检测问题并取得了显著的成果,然而,当车辆尺寸较小时,当前深度学习算法的检测丢失率仍然很高.为了解决这个问题,本文提出了一种基于组合目标框提取结构的扩张全卷积神经网络(Dilated Fully Convolutional Network with Grouped Proposals,DFCN-GP).具体提出了一种结合低层特征和高层特征的组合网络模型用于生成目标框,其中低层特征对小目标更加敏感.此外,为保留更多的细节信息,基于扩张卷积思想,增加了网络最后一层卷积层的大小和感受野,用于目标框的提取和车辆检测.通过控制变量的对比试验,对基于组合方式的目标框提取网络和扩张卷积层的有效性进行了验证.本文提出的算法模型在公开数据集UA-DETRAC上性能优异.
Abstract:Although deep learning based vehicle detection approaches have achieved remarkable success recently, they are still likely to miss comparatively small-sized vehicle. To address this problem, we propose a novel Dilated Fully Convolutional Network with Grouped Proposals (DFCN-GP) for vehicle detection. Specifically, we invented a grouped network structure to combine feature maps from both lower and higher level convolutional layers for the generation of object proposal and focusing more on lower level features, which are more sensitive to discovering small object. In addition, we increase the size and reception field of the feature map in the last convolutional layers to keep more detailed information via dilated convolution, which is used in both object proposal and vehicle detection sub-networks. In the experiment, we conducted ablation studies to demonstrate the effectiveness of the grouped proposals and dilated convolutional layer. We also show that the proposed approach outperforms other state-of-the-art methods on the UA-DETRAC vehicle detection.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本:
程雅慧,蔡烜,冯瑞.面向车辆检测的扩张全卷积神经网络.计算机系统应用,2019,28(1):107-112
CHENG Ya-Hui,CAI Xuan,FENG Rui.Dilated Fully Convolutional Network with Grouped Proposals for Vehicle Detection.COMPUTER SYSTEMS APPLICATIONS,2019,28(1):107-112

用微信扫一扫

用微信扫一扫