Tree level change detection over Ahmedabad city using very high resolution satellite images and Deep Learning
This work addresses urban forestry monitoring for local authorities, but it is incremental as it applies an existing deep learning method to a new dataset.
The study tackled tree-level change detection in Ahmedabad, India, using high-resolution satellite images and a YOLOv7 instance segmentation model, achieving a maximum accuracy of 80% for tree detection with a 2% false segmentation rate after hyperparameter tuning.
In this study, 0.5m high resolution satellite datasets over Indian urban region was used to demonstrate the applicability of deep learning models over Ahmedabad, India. Here, YOLOv7 instance segmentation model was trained on well curated trees canopy dataset (6500 images) in order to carry out the change detection. During training, evaluation metrics such as bounding box regression and mask regression loss, mean average precision (mAP) and stochastic gradient descent algorithm were used for evaluating and optimizing the performance of model. After the 500 epochs, the mAP of 0.715 and 0.699 for individual tree detection and tree canopy mask segmentation were obtained. However, by further tuning hyper parameters of the model, maximum accuracy of 80 % of trees detection with false segmentation rate of 2% on data was obtained.