自动化与信息工程2025，Vol.46Issue(4)：35-42,8.DOI:10.12475/aie.20250405
结合超分重建的室内指示牌检测方法
Indoor Signage Detection Method with Super-resolution Reconstruction
袁飞 1饶娆 1周光海 2陈伟斌1
作者信息
- 1. 广东技术师范大学自动化学院,广东 广州 510450
- 2. 广州南方测绘科技股份有限公司,广东 广州 510663
- 折叠
摘要
Abstract
To address the low detection accuracy of distant indoor signage,this paper proposes an indoor signage detection method with super-resolution reconstruction.Analysis of the monocular camera perspective imaging model reveals that the imaging pixels of signage decrease with increasing shooting distance.By applying super-resolution reconstruction to images containing indoor signage,the resolution of signage images is enhanced,thereby improving detection accuracy.Comparative experiments on the SVHN dataset and a laboratory dataset demonstrate that images reconstructed at 2×and 4×super-resolution using SRCNN,SRResNet,and SRGAN super-resolution reconstruction neural network model significantly outperform non-reconstructed images in signage detection accuracy.关键词
超分重建/室内指示牌检测/相机透视成像模型/指示牌成像计算方法/目标检测算法Key words
super-resolution reconstruction/indoor signage detection/camera perspective imaging model/signage imaging calculation method/object detection algorithms分类
信息技术与安全科学引用本文复制引用
袁飞,饶娆,周光海,陈伟斌..结合超分重建的室内指示牌检测方法[J].自动化与信息工程,2025,46(4):35-42,8.
