A Survey of Current Research on Image Target Detection Algorithms Based on Deep Convolutional Neural Networks
-
摘要: 作为计算机领域的一个重要的研究成果,深度卷积神经网络已经广泛用于图像分类问题。随着图像分类的准确度 提高,基于卷积神经网络的图像目标检测算法已逐渐成为当前的研究热点。本文首先综述对于卷积神经网络发展有重大意义 的网络模型以及近年来的从候选框提取,回归,anchor-free三个方面提出的基于卷积神经网络的目标检测算法。最后结合卷 积神经网络及目标检测算法存在的问题对未来研究方向做出展望。Abstract: As an important research achievement in the computer field, deep convolutional neural networks have been widely used in image classification problems. With the improvement of the accuracy of image classification, image target detection algorithms based on convolutional neural networks have gradually become a current research hotspot. This article first reviews the network models that are of great significance to the development of convolutional neural networks and the recent years of candidate frame extraction, regression, and anchor-free object detection algorithms based on convolutional neural networks. Finally, combined with the problems of convolutional neural networks and target detection algorithms, prospects for future research directions are made.
-
[1] Jégou,S,Drozdzal M,Vazquez D,et al.The One Hundred Layers Tiramisu:Fully Convolutional DenseNets for Semantic Segmentation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).IEEE,2016. [2] Bengio Y,Louradour J,Collobert R,et al.Curriculum learning [C]//Proceedings of the 26th Annual International Conference on Machine Learning,ICML 2009,Montreal,Quebec,Canada,June 14-18,2009.ACM,2009. [3] Li X,Liu Z,Luo P,et al.Not all pixels are equal:Difficultyaware semantic segmentation via deep layer cascade[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2017. [4] Brostow G J,Shotton J,Fauqueur J,et al.Segmentation and recognition using structure from motion point clouds[C]//European conference on computer vision.Springer,Berlin,Heidelberg,2008. -
点击查看大图
计量
- 文章访问数: 65
- HTML全文浏览量: 17
- PDF下载量: 12
- 被引次数: 0
下载: