建筑垃圾堆放点样本集构建与优化研究

李思琦; 刘扬; 杜明义; 张敏; 辛超; 姚毅; 马腾跃

doi:10.13205/j.hjgc.202003007

建筑垃圾堆放点样本集构建与优化研究

doi: 10.13205/j.hjgc.202003007

李思琦¹,
刘扬^1,2,
杜明义^1,2,
张敏¹,
辛超¹,
姚毅¹,
马腾跃¹

1. 北京建筑大学测绘与城市空间信息学院, 北京 102616;
2. 北京建筑大学北京未来城市设计高精尖创新中心, 北京 100044

基金项目:

国家重点研发计划课题（2018YFC0706003）。

详细信息

作者简介:
李思琦(1995-),女,硕士研究生,主要研究方向为机器学习遥感识别。837391242@qq.com

计量
- 文章访问数: 192
- HTML全文浏览量: 29
- PDF下载量: 4
- 被引次数: 0
出版历程
- 收稿日期: 2019-11-07

CONSTRUCTION AND OPTIMIZATION OF SAMPLE SET OF CONSTRUCTION WASTE DUMP

1. School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, China;
2. Beijing Advanced Innovation Center for Future Urban Design, Beijing University of Civil Engineering and Architecture, Beijing 100044, China

摘要

摘要: 为更好地解决手工制作的建筑垃圾堆放点样本集效率低、数据量少，难以支撑基于深度学习的遥感图像目标检测算法训练需求的问题，采用基于像素的遥感分类方法构建建筑垃圾堆放点样本集，在此基础上结合直方图均衡化，CS-LBP算子约束以及迁移学习的方法对Wasserstein生成对抗模型（WGAN）进行优化，实现了样本集扩充。研究结果表明：相对于纯手工制作的样本集，基于像素的遥感分类方法可以显著提升样本集制作的效率；同时，经过WGAN优化后，生成样本模拟了原始数据的颜色与纹理特征分布规律，增加了原始数据的多样性，满足了扩充样本集的需求。
- 建筑垃圾堆放点 /
- 样本集构建 /
- WGAN /
- 数据增强 /
- CS-LBP算子
Abstract: The unregulated stacking of urban construction waste endangered the environment and the safety of citizens. In order to identify the stacking points of construction waste, aiming at the problem that there was no stacking point sample set for construction waste, this paper used the pixel based remote sensing classification method to build a sample set. On this basis, the adaptive histogram averaging, CS-LBP operator constraints and migration learning were combined to optimize the Wasserstein generative adversarial networks(WGAN) and generate samples to expand the sample set. The experimental results showed that the pixel based remote sensing classification method improved the efficiency of the artificial sample set, and the WGAN optimized method could effectively inherit the color and texture features of the original data to meet the needs of expanding the sample set.
- construction waste dump /
- sample set construction /
- WGAN /
- data enhancement /
- CS-LBP operator

HTML全文

参考文献(15)

杨壮. 面向Bin Picking的虚拟样本集构建及智能识别方法的研究[D].上海:华东理工大学,2019.

鄢文苗,任东,黄应平,等.基于SVM土壤重金属污染评价的训练样本集构建[J].武汉大学学报(理学版),2019,65(3):316-322.

陈泓佑,和红杰,陈帆,等.基于子样本集构建的DCGANs训练方法[J/OL].自动化学报:1-10[2019-10-09

].https://doi.org/10.16383/j.aas.c180677.

赵树阳, 李建武. 基于生成对抗网络的低秩图像生成方法[J]. 自动化学报, 2018, 44(5):829-839.

牛斌,吴鹏,马利,等.一种基于生成对抗网络的行为样本集扩展方法[J].计算机技术与发展,2019(7):43-48.

SWAIN M J, BALLARD D H. Color indexing[J]. International Journal of Computer Vision, 1991, 7(1): 11-32.

庄福振, 罗平, 何清, 等. 迁移学习研究进展[J].软件学报,2015, 26(1): 26-39.

JIANG J, ZHAI C X. A two-stage approach to domain adaptation for statistical classifiers[C]//The 16th ACM Conf. on Information and Knowledge Management. New York: ACM Press, 2007: 401-410.

FANG M, YIN J, ZHU X Q. Transfer learning across networks for collective classification[C]//The 2013 IEEE 13th Int’l Conf. on Data Mining, 2013: 161-170.

DAI W Y, XUE G R, YANG Q, et al. Co-Clustering based classification for out-of-domain documents[C]//The 13th ACM Int’l Conf. on Knowledge Discovery and Data Mining. New York: ACM Press, 2007: 210-219.

DAI W Y, JIN O, XUE G R, et al. Eigentransfer: a unified framework for transfer learning[C]//The 24th Int’l Conf. on Machine Learning. San Francisco: Morgan Kaufmann Publishers, 2009: 193-200.

YANG Y, NEWSAM S. Bag-of-visual-words and spatial extensions for land-use classification[C]//The 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, San Jose,USA, 2010.

GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Advances in Neural Information Processing Systems, 2014, 3:2672-2680.

ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein GAN[EB/OL]. https://arxiv.org/pdf/1701.07875.pdf. 2018-02-23.

HEIKKIL M, PIETIK I, NEN M, et al. Description of Interest Regions with Local Binary Patterns[J].Pattern Recognition,2009,42(3):425-436.

施引文献

资源附件(0)

访问统计