Land classification in satellite images by injecting traditional features to CNN models

ABSTRACT

Deep learning methods have been successfully applied to remote-sensing problems for several years. Among these methods, CNN-based models have high accuracy in solving the land classification problem using satellite or aerial images. Although these models have high accuracy, this generally comes with large memory size requirements. However, it is desirable to have small-sized models for applications, such as the ones implemented on unmanned aerial vehicles, with low memory space. Unfortunately, small-sized CNN models do not provide as high accuracy as with their large-sized versions. In this study, we propose a novel method to improve the accuracy of CNN models, especially the ones with small size, by injecting traditional features into them. To test the effectiveness of the proposed method, we applied it to the CNN models SqueezeNet, MobileNetV2, ShuffleNetV2, VGG16 and ResNet50V2 having size 0.5 MB to 528 MB. We used the sample mean, grey-level co-occurrence matrix features, Hu moments, local binary patterns, histogram of oriented gradients and colour invariants as traditional features for injection. We tested the proposed method on the EuroSAT dataset to perform land classification. Our experimental results show that the proposed method significantly improves the land classification accuracy especially when applied to small-sized CNN models.

KEYWORDS:

• land classification
• satellite images
• CNN models
• traditional features

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work is supported by TUBITAK under project no 221N393 and under the umbrella of ERA-NET Cofund ForestValue project ForestMap.