arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.04424cs.CVcs.LGstat.ML
收藏

基于胶囊网络的交通标志检测深度学习模型

Novel Deep Learning Model for Traffic Sign Detection Using Capsule Networks

Amrita School of Engineering, Coimbatore(阿姆里塔工程学院(哥印拜陀));Amrita Vishwa Vidyapeetham(阿姆里塔·维什瓦·维迪亚皮塔姆大学)

Amara Dinesh Kumar

摘要:

卷积神经网络是迄今为止用于交通信号分类的最广泛使用的深度学习算法,但它们未能捕获姿势、视图、本文提出了一种使用深度学习架构的交通标志检测新方法,称为胶囊网络,该方法在德国交通标志数据集上实现了出色的性能。胶囊网络由胶囊组成,其是通过使用动态路由和协议路由算法来表示对象的实例化参数(如姿态和方向)的一组神经元。与手动特征提取的先前方法不同,具有许多参数的多个深度神经网络,我们的方法消除了人工操作,并提供了对空间变化的抵抗能力。CNN可以很容易地被各种对手攻击所欺骗,胶囊网络可以克服Capsule网络在德国交通标志识别基准数据集(GTSRB)上的准确率达到了97.6%。

英文摘要:

Convolutional neural networks are the most widely used deep learning algorithms for traffic signal classification till date but they fail to capture pose, view, orientation of the images because of the intrinsic inability of max pooling layer.This paper proposes a novel method for Traffic sign detection using deep learning architecture called capsule networks that achieves outstanding performance on the German traffic sign dataset.Capsule network consists of capsules which are a group of neurons representing the instantiating parameters of an object like the pose and orientation by using the dynamic routing and route by agreement algorithms.unlike the previous approaches of manual feature extraction,multiple deep neural networks with many parameters,our method eliminates the manual effort and provides resistance to the spatial variances.CNNs can be fooled easily using various adversary attacks and capsule networks can overcome such attacks from the intruders and can offer more reliability in traffic sign detection for autonomous vehicles.Capsule network have achieved the state-of-the-art accuracy of 97.6% on German Traffic Sign Recognition Benchmark dataset (GTSRB).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑