iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images

Abstract

Existing Earth Vision datasets are either suitable for semantic segmentation or object detection. In this work, we introduce the first benchmark dataset for instance segmentation in aerial imagery that combines instance-level object detection and pixel-level segmentation tasks. In comparison to instance segmentation in natural scenes, aerial images present unique challenges e.g., a huge number of instances per image, large object-scale variations and abundant tiny objects. Our large-scale and densely annotated Instance Segmentation in Aerial Images Dataset (iSAID) comes with 655,451 object instances for 15 categories across 2,806 high-resolution images. Such precise per-pixel annotations for each instance ensure accurate localization that is essential for detailed scene analysis. Compared to existing small-scale aerial image based instance segmentation datasets, iSAID contains 15$\times$ the number of object categories and 5$\times$ the number of instances. We benchmark our dataset using two popular instance segmentation approaches for natural images, namely Mask R-CNN and PANet. In our experiments we show that direct application of off-the-shelf Mask R-CNN and PANet on aerial images provide suboptimal instance segmentation results, thus requiring specialized solutions from the research community. The dataset is publicly available at: https://captain-whu.github.io/iSAID/index.html

arXiv commentCVPR'19 Workshops (Detecting Objects in Aerial Images). The dataset is publicly available at: https://captain-whu.github.io/iSAID/index.html

References in corpus (5)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Land cover mapping at very high resolution with rotation equivariant CNNs: towards small yet accurate models
• SpaceNet MVOI: a Multi-View Overhead Imagery Dataset
• xView: Objects in Context in Overhead Imagery
• Striking the Right Balance with Uncertainty

Cited by in corpus (11)

• An Empirical Study of Remote Sensing Pretraining
• LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
• Bridging the Gap Between Computational Photography and Visual Recognition
• Panoptic Segmentation Meets Remote Sensing
• Bounding Box-Free Instance Segmentation Using Semi-Supervised Learning for Generating a City-Scale Vehicle Dataset
• Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis
• MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results
• Automatic characterization of boulders on planetary surfaces from high-resolution satellite images
• RarePlanes: Synthetic Data Takes Flight
• Multilingual Vision-Language Pre-training for the Remote Sensing Domain
• Transport-Related Surface Detection with Machine Learning: Analyzing Temporal Trends in Madrid and Vienna