Multi-Label Remote Sensing Image Classification with Latent Semantic Dependencies

Remote Sensing

Jingbo Lin¹  Junchao Ji¹  Weipeng Jing¹  Guangsheng Chen¹  Houbing Song² 

[1] College of Information and Computer Engineering, Northeast Forestry University, Harbin 150036, China;Department of Electrical Engineering and Computer Science, Embry-Riddle Aeronautical University, Daytona Beach, FL 32114, USA;

关键词: multi-label;    remote-sensing image;    CNN-RNN;    attention;    dependencies;   

DOI  :  10.3390/rs12071110

来源: DOAJ

【 摘 要 】

Deforestation in the Amazon rainforest results in reduced biodiversity, habitat loss, climate change, and other destructive impacts. Hence obtaining location information on human activities is essential for scientists and governments working to protect the Amazon rainforest. We propose a novel remote sensing image classification framework that provides us with the key data needed to more effectively manage deforestation and its consequences. We introduce the attention module to separate the features which are extracted from CNN(Convolutional Neural Network) by channel, then further send the separated features to the LSTM(Long-Short Term Memory) network to predict labels sequentially. Moreover, we propose a loss function by calculating the co-occurrence matrix of all labels in the dataset and assigning different weights to each label. Experimental results on the satellite image dataset of the Amazon rainforest show that our model obtains a better $F_2$ score compared to other methods, which indicates that our model is effective in utilizing label dependencies to improve the performance of multi-label image classification.

【 授权许可】

Unknown