摘要
目标检测是计算机视觉领域的一个重要领域,卷积神经网络在目标检测方面表现出了很好的检测性能。本文介绍了目标检测算法目前用到的数据集,总结了卷积神经网络在目标检测速度以及检测精度方面存在的优缺点,为更好的选择卷积神经网络算法来进行目标检测提供了一种参考依据。
Object detection is an important field in the field of computer vision.Convolution neural network has shown good performance in target detection.Firstly,this paper introduces the data sets used by the target detection algorithm,and summarizes the advantages and disadvantages of convolution neural network in target detection speed and detection accuracy,which provides a reference for choosing convolution neural network algorithm to detect target better.
出处
《南方农机》
2020年第21期38-39,44,共3页
关键词
卷积神经网络
深度学习
目标检测
机器视觉
Convolution neural network
deep learning
target detection
machine vision