基于改进的Faster R-CNN的目标检测与识别

Target Detection and Recognition Based on Improved Faster R-CNN

摘要: 近年来，随着深度学习不断的发展，基于深度学习的图像研究与应用已经在很多领域取得了优异的成绩。RCNN网络与全卷积网络等技术框架使得目标检测技术发展越来越迅速。Faster R-CNN算法被提出并广泛应用于目标检测和目标识别领域。在本文中，主要研究了基于Faster R-CNN算法对自制办公用品数据集中的图像进行的目标检测。相较于RCNN系列算法，Faster R-CNN提出了区域建议网络，同时将特征抽取、候选框提取、边界框回归、分类整合到一个网络当中，使得综合性能有很大改进。本文提出基于AlexNet改进的Faster R-CNN算法，在提取特征时，数据集通常具有大量高密度的连续性特征，而激活函数具有稀疏性，解决了目标小且背景复杂情况下的办公用品目标检测问题，提高了检测速度和检测精度。

Abstract: In recent years, with the continuous development of in-depth learning, image research and appli-cation based on in-depth learning has achieved excellent results in many fields. RCNN network and full convolution network make the development of target detection technology more and more rapid. Faster R-CNN algorithm has been proposed and widely used in the field of target detection and recognition. In this paper, we mainly study the object detection based on Faster R-CNN algo-rithm for the image in the data set of self-made office supplies. Compared with RCNN series algo-rithms, Faster R-CNN proposes a regional recommendation network, and integrates feature ex-traction, candidate box extraction, boundary box regression and classification into a network, which greatly improves the overall performance. In this paper, an improved Faster R-CNN algorithm based on activation function is proposed. When extracting features, the data set usually has a large number of high-density continuity characteristics, while the activation function is sparse, which solves the problem of target detection of office supplies under small targets and complex background, and improves the detection speed and accuracy.