The MIS Check-Dam Dataset for Object Detection and Instance Segmentation Tasks
This work provides a new dataset for automating the detection of irrigation structures in agriculture, but it is incremental as it applies existing methods to a new domain.
The authors introduced the MIS Check-Dam dataset for detecting and mapping check-dams in satellite imagery, and evaluated various object detection and instance segmentation methods on it, achieving competitive performance with top methods like Mask R-CNN reaching mAP scores around 0.85.
Deep learning has led to many recent advances in object detection and instance segmentation, among other computer vision tasks. These advancements have led to wide application of deep learning based methods and related methodologies in object detection tasks for satellite imagery. In this paper, we introduce MIS Check-Dam, a new dataset of check-dams from satellite imagery for building an automated system for the detection and mapping of check-dams, focusing on the importance of irrigation structures used for agriculture. We review some of the most recent object detection and instance segmentation methods and assess their performance on our new dataset. We evaluate several single stage, two-stage and attention based methods under various network configurations and backbone architectures. The dataset and the pre-trained models are available at https://www.cse.iitb.ac.in/gramdrishti/.