NWPU VHR-10 Dataset is a 10-class geographic remote sensing dataset for space object detection. It has 650 images containing targets and 150 background images, totaling 800 images. The target types include 10 categories including aircraft, ships, oil tanks, baseball fields, tennis courts, basketball courts, track and field fields, ports, bridges and cars.

This dataset was released by Northwestern Polytechnical University in 2014. Related papers include "Multi-class geospatial object detection and geographic image classification based on collection of part detectors", "A survey on object detection in optical remote sensing images" and "Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images".