基于深度学习的图像物体检测与分类
发布时间：2018-07-16 15:08
【摘要】：图像物体检测与分类既是计算机视觉领域的基础,同时也是视觉领域的核心内容。图像物体检测与分类与人们生活密切相关。近年来,由于深度学习方法在ImageNet ILSVRC竞赛辉煌的成果,图像物体检测和分类的研究越来越活跃。大数据时代的到来给人工智能的发展提供前所未有的机遇,在这个时代背景下,深度学习在包括图像物体检测等方面取得的突破性进展并非偶然。R-CNN首次提出了被广泛采用的基于深度学习的物体检测流程,并首先采用选择性搜索提出候选区域,利用深度卷积网络从候选区域提取特征,然后利用支持向量机等线性分类器基于特征将区域分为物体和背景。本文通过对R-CNN模型进行改进,实现一个基于深度学习的图像物体检测与分类系统。首先,对于区域检测模块进行改进,在检测窗生成模块使用检测速率更高的Edge Boxes算法代替选择性搜索。其次,我们对R-CNN进行改进,打破传统的分级训练思想,修改了 R-CNN的网络结构,通过端对端的训练方式,提高了目标检测和分类算法在PASCAL VOC数据集的平均准确率(mAP)。此外,我们基于R-CNN改进的目标检测与分类算法减少了训练阶段的缓存空间,提高了空间利用率。最终我们的目标检测与分类算法在PASCAL VOC数据集获得了 56.8的mAP,相比DPM v5模型提升70%,相比R-CNN提升了 10%。此外,以往的研究注重于检测效果和分类效果的提升,侧重于在数据方面的研究。然而,基于卷积神经网络的可视化工作也是十分有必要的。因此,本文在CNN特征提取可视化也做了很多工作。可以发现,随着网络层数的增加,学习到的特征语义越来越抽象,越能从语义上概括图像的特征。
[Abstract]:Image object detection and classification is not only the foundation of computer vision field, but also the core content of vision field. Image object detection and classification are closely related to people's life. In recent years, the research of image object detection and classification has become more and more active due to the brilliant achievements of deep learning methods in ImageNet ILSVRC. The arrival of the big data era provides an unprecedented opportunity for the development of artificial intelligence. The breakthrough in depth learning, including image object detection, is not accidental. R-CNN proposes a widely used object detection process based on depth learning for the first time. The feature is extracted from candidate region by deep convolution network, and then the region is divided into object and background based on feature by linear classifier such as support vector machine (SVM). In this paper, an image object detection and classification system based on depth learning is implemented by improving R-CNN model. Firstly, the region detection module is improved, and the Edge boxes algorithm with higher detection rate is used to replace the selective search in the window generation module. Secondly, we improve R-CNN, break the traditional hierarchical training idea, modify the network structure of R-CNN, and improve the average accuracy (mAP) of target detection and classification algorithm in Pascal VOC dataset through end-to-end training. In addition, our improved target detection and classification algorithm based on R-CNN reduces the buffer space in the training phase and improves the space utilization ratio. Finally, our target detection and classification algorithm obtains 56.8 mAPs in Pascal VOC dataset, 70 steps higher than DPM v5 model and 10 parts higher than R-CNN model. In addition, previous studies have focused on the improvement of detection and classification effects, as well as on data. However, visualization based on convolutional neural networks is also necessary. Therefore, this paper has done a lot of work in CNN feature extraction visualization. It can be found that with the increase of the number of network layers, the feature semantics learned becomes more and more abstract, and the feature of the image can be summarized more semantically.
【学位授予单位】：北京邮电大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：TP391.41
本文编号：2126769
[Abstract]:Image object detection and classification is not only the foundation of computer vision field, but also the core content of vision field. Image object detection and classification are closely related to people's life. In recent years, the research of image object detection and classification has become more and more active due to the brilliant achievements of deep learning methods in ImageNet ILSVRC. The arrival of the big data era provides an unprecedented opportunity for the development of artificial intelligence. The breakthrough in depth learning, including image object detection, is not accidental. R-CNN proposes a widely used object detection process based on depth learning for the first time. The feature is extracted from candidate region by deep convolution network, and then the region is divided into object and background based on feature by linear classifier such as support vector machine (SVM). In this paper, an image object detection and classification system based on depth learning is implemented by improving R-CNN model. Firstly, the region detection module is improved, and the Edge boxes algorithm with higher detection rate is used to replace the selective search in the window generation module. Secondly, we improve R-CNN, break the traditional hierarchical training idea, modify the network structure of R-CNN, and improve the average accuracy (mAP) of target detection and classification algorithm in Pascal VOC dataset through end-to-end training. In addition, our improved target detection and classification algorithm based on R-CNN reduces the buffer space in the training phase and improves the space utilization ratio. Finally, our target detection and classification algorithm obtains 56.8 mAPs in Pascal VOC dataset, 70 steps higher than DPM v5 model and 10 parts higher than R-CNN model. In addition, previous studies have focused on the improvement of detection and classification effects, as well as on data. However, visualization based on convolutional neural networks is also necessary. Therefore, this paper has done a lot of work in CNN feature extraction visualization. It can be found that with the increase of the number of network layers, the feature semantics learned becomes more and more abstract, and the feature of the image can be summarized more semantically.
【学位授予单位】：北京邮电大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：TP391.41
【参考文献】
相关期刊论文 前3条
1 黄凯奇;任伟强;谭铁牛;;图像物体分类与检测算法综述[J];计算机学报;2014年06期
2 余凯;贾磊;陈雨强;徐伟;;深度学习的昨天、今天和明天[J];计算机研究与发展;2013年09期
3 孙志军;薛磊;许阳明;王正;;深度学习研究综述[J];计算机应用研究;2012年08期
相关硕士学位论文 前3条
1 边云龙;基于深度学习的视频中的体育类型检测技术的研究[D];北京邮电大学;2015年
2 王恒欢;基于深度学习的图像识别算法研究[D];北京邮电大学;2015年
3 杜骞;深度学习在图像语义分类中的应用[D];华中师范大学;2014年
，本文编号：2126769
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/2126769.html
