期刊
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
卷 36, 期 4, 页码 822-848出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/13658816.2021.1980883
关键词
Object identification; convolutional neural network; object convolutional position; deep learning
类别
资金
- National Natural Science Foundation of China [42090012, 41771452, 41771454]
Object-based convolutional neural networks (OCNNs) have shown great performance in land-cover and land-use classification, with the proposed morphology-based binary tree sampling (BTS) method outperforming other competing methods by generating evenly distributed object convolutional positions (OCPs). Further experiments suggest that the efficiency of BTS can be improved with multi-thread technology implementation.
Object-based convolutional neural networks (OCNNs) have achieved great performance in the field of land-cover and land-use classification. Studies have suggested that the generation of object convolutional positions (OCPs) largely determines the performance of OCNNs. Optimized distribution of OCPs facilitates the identification of segmented objects with irregular shapes. In this study, we propose a morphology-based binary tree sampling (BTS) method that provides a reasonable, effective, and robust strategy to generate evenly distributed OCPs. The proposed BTS algorithm consists of three major steps: 1) calculating the required number of OCPs for each object, 2) dividing a vector object into smaller sub-objects, and 3) generating OCPs based on the sub-objects. Taking the object identification in land-cover and land-use classification as a case study, we compare the proposed BTS algorithm with other competing methods. The results suggest that the BTS algorithm outperforms all other competing methods, as it yields more evenly distributed OCPs that contribute to better representation of objects, thus leading to higher object identification accuracy. Further experiments suggest that the efficiency of BTS can be improved when multi-thread technology is implemented.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据