Deep-Learning Convolutional Neural Networks for scattered shrub detection with Google Earth Imagery

TL;DR

This paper demonstrates that CNN-based methods, combined with data-augmentation and transfer learning, outperform traditional OBIA techniques in detecting protected shrub species from Google Earth imagery, offering faster and less labor-intensive land cover mapping.

Contribution

It introduces a CNN-based approach for plant species detection in high-resolution satellite images, showing improved accuracy and efficiency over existing OBIA methods.

Findings

CNN models outperform OBIA in shrub detection accuracy

Transfer learning enables model generalization across images

Method reduces human supervision in land cover mapping

Abstract

There is a growing demand for accurate high-resolution land cover maps in many fields, e.g., in land-use planning and biodiversity conservation. Developing such maps has been performed using Object-Based Image Analysis (OBIA) methods, which usually reach good accuracies, but require a high human supervision and the best configuration for one image can hardly be extrapolated to a different image. Recently, the deep learning Convolutional Neural Networks (CNNs) have shown outstanding results in object recognition in the field of computer vision. However, they have not been fully explored yet in land cover mapping for detecting species of high biodiversity conservation interest. This paper analyzes the potential of CNNs-based methods for plant species detection using free high-resolution Google Earth T M images and provides an objective comparison with the state-of-the-art OBIA-methods. We consider as case study the detection of Ziziphus lotus shrubs, which are protected as a priority habitat under the European Union Habitats Directive. According to our results, compared to OBIA-based methods, the proposed CNN-based detection model, in combination with data-augmentation, transfer learning and pre-processing, achieves higher performance with less human intervention and the knowledge it acquires in the first image can be transferred to other images, which makes the detection process very fast. The provided methodology can be systematically reproduced for other species detection.