Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery.
Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery.
复制标题
DOI：
10.3390/jimaging6090097
复制
发表时间：
2020-09-17
影响因子：
3.2
通讯作者：
Agnew A
中科院分区：
文献类型：
--
作者：
Bhuiyan MAE;Witharana C;Liljedahl AK;Jones BM;Daanen R;Epstein HE;Kent K;Griffin CG;Agnew A
深度学习（DL）卷积神经网络（CNN）已被快速应用于极高空间分辨率（VHSR）卫星图像分析。基于DLCNN的计算机视觉（CV）应用主要针对标准红、绿色、蓝色（RGB）图像中的日常物体检测，而地球科学遥感应用则侧重于多光谱（MS）图像中的地质物体检测和分类。MS图像包括来自反射光谱的近和/或中红外区域的RGB和窄光谱通道。这项探索性研究的中心目标是了解MS波段统计在多大程度上控制DLCNN模型预测。我们支架我们的分析案例研究，使用北极苔原永久冻土地貌特征称为冰楔多边形（IWP）作为候选地理对象。我们选择Mask RCNN作为DLCNN架构，从八波段Worldview-02 VHSR卫星图像中检测IWP。设计了一个系统的实验，以了解选择最佳的三波段组合在模型预测的影响。我们的任务是五个队列的三波段组合加上统计措施，以衡量输入MS波段的光谱变异性。对于两种不同的波段组合（海岸蓝、蓝、绿色（1，2，3）和绿色、黄、红（3，4，5）），候选场景产生了F1分数的高模型检测精度，范围在0.89至0.95之间。标测工作流程通过表现出低随机误差和系统误差来辨别IWP，对于条带组合（1、2、3），分别为0.17-0.19和0.20-0.21。结果表明，Mask-RCNN模型的预测准确性受到输入MS波段的显着影响。总的来说，我们的研究结果强调了考虑输入MS波段的图像统计数据的重要性，以及当DLCNN架构仅限于三个光谱通道时，仔细选择DLCNN预测的最佳波段。
Deep learning (DL) convolutional neural networks (CNNs) have been rapidly adapted in very high spatial resolution (VHSR) satellite image analysis. DLCNN-based computer visions (CV) applications primarily aim for everyday object detection from standard red, green, blue (RGB) imagery, while earth science remote sensing applications focus on geo object detection and classification from multispectral (MS) imagery. MS imagery includes RGB and narrow spectral channels from near- and/or middle-infrared regions of reflectance spectra. The central objective of this exploratory study is to understand to what degree MS band statistics govern DLCNN model predictions. We scaffold our analysis on a case study that uses Arctic tundra permafrost landform features called ice-wedge polygons (IWPs) as candidate geo objects. We choose Mask RCNN as the DLCNN architecture to detect IWPs from eight-band Worldview-02 VHSR satellite imagery. A systematic experiment was designed to understand the impact on choosing the optimal three-band combination in model prediction. We tasked five cohorts of three-band combinations coupled with statistical measures to gauge the spectral variability of input MS bands. The candidate scenes produced high model detection accuracies for the F1 score, ranging between 0.89 to 0.95, for two different band combinations (coastal blue, blue, green (1,2,3) and green, yellow, red (3,4,5)). The mapping workflow discerned the IWPs by exhibiting low random and systematic error in the order of 0.17–0.19 and 0.20–0.21, respectively, for band combinations (1,2,3). Results suggest that the prediction accuracy of the Mask-RCNN model is significantly influenced by the input MS bands. Overall, our findings accentuate the importance of considering the image statistics of input MS bands and careful selection of optimal bands for DLCNN predictions when DLCNN architectures are restricted to three spectral channels.