摘要
随着训练数据的增加以及机器性能的提高,基于卷积神经网络的目标检测冲破了传统目标检测的瓶颈,成为当前目标检测的主流算法。因此,研究如何有效地利用卷积神经网络进行目标检测具有重要价值。首先回顾了卷积神经网络如何解决传统目标检测中存在的问题;介绍了卷积神经网络的基本结构,描述了当前卷积神经网络的研究进展及常用的卷积神经网络;重点分析和讨论了两种应用卷积神经网络进行目标检测的思路和方法,指出了目前存在的不足。最后总结了基于卷积神经网络的目标检测以及未来的发展方向。
With the increase of training data and the improvement of the performance of computers, the CNN-based object detection breaks the bottleneck of traditional object detection and has been the main method of current object detection. Therefore, it is a significant research that how to effectively utilize CNN for object detection. Firstly, this paper reviewed how to solve the problems of traditional object detection by CNN. Secondly, it introduced the basic architecture of CNN and described the current research development and widely-used CNN. Thirdly, this paper mainly analyzed and discussed two kinds of ideas and methods of the CNN-based object detection and pointed out the present deficiency. Finally, it concluded the CNN-based object detection and the future direction.
出处
《计算机应用研究》
CSCD
北大核心
2017年第10期2881-2886,2891,共7页
Application Research of Computers
基金
国家自然科学基金资助项目(61375038)
关键词
卷积神经网络
目标检测
深度学习
convolutional neural network（CNN）
object detection
deep learning
