xView: Objects in Context in Overhead Imagery
By Darius Lam, Richard Kuzma, Kevin McGee, Samuel Dooley, Michael Laielli, Matthew K. Klaric, Yaroslav Bulatov, Brendan McCord. 2018
431 citations recorded by the source corpus.
We introduce a new large-scale dataset for the advancement of object detection techniques and overhead object detection research. This satellite imagery dataset enables research progress pertaining to four key computer vision frontiers. We utilize a novel process for geospatial category detection and bounding box annotation with three stages of quality control. Our data is collected from WorldView-3 satellites at 0.3m ground sample distance, providing higher resolution imagery than most public satellite imagery datasets. We compare xView to other object detection datasets in both natural and overhead imagery domains and then provide a baseline analysis using the Single Shot MultiBox Detector. xView is one of the largest and most diverse publicly available object-detection datasets to date, with over 1 million objects across 60 classes in over 1,400 km^2 of imagery.
Subfields: Computer Vision and Pattern Recognition, Media Technology, Remote Sensing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Junwei Han
- Luc Van Gool
- Dacheng Tao
- Gong Cheng
- Trevor Darrell
- Ming-Hsuan Yang
- Xiaogang Wang
- Jitendra Malik
In Media Technology
In Remote Sensing
Citations in the corpus
- 3D Instance Segmentation of MVS Buildings (2021, methodology): “Compared to other remote sensing imagery datasets, such as SpaceNet [51] and xView [52], our dataset has higher resolution and richer angles of pitch.”
- FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery (2021, methodology): “xView [28] WorldView-3 1 million 1,127 2000-4000 60 HBB PNG Y”
- Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark (2022, neutral): “, 2018), xView (Lam et al., 2018), VisDrone (Zhu et al.”
- Geography-Aware Self-Supervised Learning (2020, methodology): “For object detection, we use the xView dataset [15] consisting of high resolution satellite images captured with similar sensors to the ones in the fMoW dataset.”
- Tiny Object Detection in Aerial Images (2021, background): “5 trainval set [1], xView training set [19], VisDrone2018-Det trainval set [20], Airbus Ship trainval set1 and DIOR trainval+test sets [3].”
- Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, methodology): “2) SODA-A AI-TOD : AI-TOD is built on several publicly available datasets, including DIOR [20], DOTA [30], VisDrone [159], xView [157], and Airbus-Ship 4 .”
- Self-Supervised Pretraining Improves Self-Supervised Pretraining (2021, background): “Aerial: xView [28] is a 36-class object-centric, multilabel aerial imagery dataset [39133/2886/2886].”
- Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection (2022, background): “xView [26] is one of the largest publicly available datasets for object detection from satellite imagery.”
- SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery (2022, background): “…satellite image datasets have been carefully curated in the past few years, including Functional Map of the World (fMoW) [17], BigEarthNet [18], xView [19], SpaceNet [20], annotating these datasets requires specialized skills and is more expensive than traditional computer vision datasets.”
- Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, background): “The recently released xView [27] dataset provides a wide range of categories and”
- SpaceNet: A Remote Sensing Dataset and Challenge Series (2018, background): “A recently released satellite imagery dataset is xVIEW [11], which contains 1400 km(2) of 30 cm satellite imagery; labels, however, consist of bounding boxes that are not ideal for foundational mapping of buildings or roads.”
- Object Detection in 20 Years: A Survey (2019, background): “xView [93] 2018 The largest remote sensing detection dataset so far.”