基于改进Faster R-CNN的小目标检测算法  

A small object detection algorithm based on improved Faster R-CNN

作　　者：邓姗姗 黄慧 马燕[1] DENG Shan-shan;HUANG Hui;MA Yan(School of Information and Mechanical Engineering,Shanghai Normal University,Shanghai 201418,China)

机构地区：[1]上海师范大学信息与机电工程学院,上海201418

出　　处：《计算机工程与科学》2023年第5期869-877,共9页Computer Engineering & Science

基　　金：国家自然科学基金(61501297)。

摘　　要：针对图像纹理细节等高频特征在基于卷积神经网络模型的特征提取过程中丢失,从而导致小目标检测效果较差的问题,提出一种多层频域特征融合的目标检测算法。算法以Faster R-CNN为基础框架,使用高频增强后的图像和对比度增强后的图像作为算法输入样本,提高了待检测图像质量;针对总像素面积较小的目标,更改RPN网络中的锚点尺度,并利用多尺度卷积特征融合的方法,融合来自不同特征层的特征,解决了小目标在深层特征图中特征信息丢失的问题。实验结果表明,所提算法在DAGM 2007数据集上具有良好的性能,平均精度均值mAP达到了97.9%,在PASCAL VOC 2007测试集上对小目标的mAP也明显优于原始Faster R-CNN的。In order to solve the problem that the high-frequency features such as image detail texture are lost in the process of feature extraction based on the convolutional neural network model to result in poor detection of small object,a target detection algorithm based on multi-layer frequency domain feature fusion is proposed.The algorithm uses the Faster R-CNN algorithm as the basic framework,and uses high-frequency enhanced images and contrast-enhanced images as input samples of the algorithm to improve the detection image quality.For objects with a small area,the scale of anchor point in the RPN network is changed.The multi-scale convolution feature fusion method is used to integrate features from different feature layers to solve the problem that the feature information of small objects is lost in the deep feature map.The experimental results show that the algorithm has good performance on the DAGM 2007 data set and the mAP reaches 97.9%.The algorithm has significantly better mAP for small objects in the PASCAL VOC 2007 data set than the original Faster R-CNN.

关 键 词：Faster R-CNN 小目标检测 特征融合 图像增强 深度学习 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]