A New CBAM-P-Net Model for Few-Shot Forest Species Classification Using Airborne Hyperspectral Images

Long Chen,Guoqi Chai,Xiaomin Tian,Xiaoli Zhang,Erxue Chen

doi:10.3390/rs13071269

Abstract

High-precision automatic identification and mapping of forest tree species composition is an important content of forest resource survey and monitoring. The airborne hyperspectral image contains rich spectral and spatial information, which provides the possibility of high-precision classification and mapping of forest tree species. Few-shot learning, as an application of deep learning, has become an effective method of image classification. Prototypical networks (P-Net) is a simple and practical deep learning network, which has significant advantages in solving few-shot classification problems. Considering the high band correlation and large data volume associated with airborne hyperspectral images, how to fully extract effective features, filter or reduce redundant features is the key to improving the classification accuracy of P-Net, in order to extract effective features in hyperspectral images and obtain a high-precision forest tree species classification model with limited samples. In this research, we embedded the convolutional block attention module (CBAM) between the convolution blocks of P-Net, the CBAM-P-Net was constructed, and a method to improve the feature extraction efficiency of the P-Net was proposed, although this method makes the network more complex and increases the computational cost to a certain extent. The results show that the combination strategy using Channel First for CBAM greatly improves the feature extraction efficiency of the model. In different sample windows, CBAM-P-Net has an average increase of 1.17% and 0.0129 in testing overall accuracy (OA) and kappa coefficient (Kappa). The optimal classification window is 17 × 17, the OA reaches 97.28%, and Kappa reaches 0.97, which is an increase of 1.95% and 0.0214 along with just 49 s of training time expended, respectively, compared with P-Net. Therefore, using a suitable sample window and applying the proposed CBAM-P-Net to classify airborne hyperspectral images can achieve high-precision classification and mapping of forest tree species.

Highlights

Fine-grained tree species classification is the basis of forest management planning and interference monitoring, which is conducive to the scientific management and effective use of forest resources
We proposed a convolutional block attention module (CBAM)-Prototypical networks (P-Net) model by embedding a CBAM module into the prototypical networks, analyzed the influence of the convolutional attention module on the network operation efficiency and results, optimized the prototypical networks structure and tuning parameters, proposed a training sample size and method suitable for tree species classification based on airborne hyperspectral data, and discussed the classification performance of CBAM-P-Net on hyperspectral images under the condition of few-shot
Taking the sample data from the 5 × 5 to the 29 × 29 window as the input, rotating and flipping the sample, and applying prototypical networks for classification, the results are shown in 19 × 19 window compared to the 17 × 17 window, and decreases from the 21 × 21 to the 23 × 23 window, increases again from the 25 × 25 to the 29 × 29 window, and the testing accuracy reaches the maximum in the 29 × 29 window

Summary

Introduction

Fine-grained tree species classification is the basis of forest management planning and interference monitoring, which is conducive to the scientific management and effective use of forest resources. 2021, 13, 1269 of hyperspectral image application [1,2,3], and it plays an important role in the fine-grained classification of tree species [4]. Deep learning can extract high-level and semantic features [5,6]. Its objective function focuses directly on classification, and completes the process of data feature extraction and classifier training automatically. The complex feature extraction and selection process is replaced by a simple end-to-end deep workflow [7,8]

Objectives

Methods

Results

Conclusion