UAV-MapVQA

UAV imagery

Near-nadir drone and aerial frames from four public sources in three countries. Every frame shown here was registered to the map; from each source we sample 3,500 frames for the benchmark, spread over the flights to keep scenes diverse.

Four sources, three countries

Platforms range from a consumer DJI drone over Austin to survey cameras flown along the US coasts before and after hurricanes. All frames look nearly straight down.

DatasetCountry and areaCameraIn the source datasetCandidatesRegistered to the mapWith ≥ 4 SAM3 buildingsSampledImage sizeMedian GSDMedian footprintYears

GSD: ground sampling distance, the ground size of one pixel. Footprint: ground area covered by one frame, from the registered corners. GSD, footprint and years are for the sampled frames. Candidates: AirLock frames subsampled from 10 Hz video; USGS frames with at least four mapped OSM buildings under the GNSS footprint and at most 10% overlap within a flight; all VETRA and UAV-VisLoc frames.

From candidate frames to the benchmark sample

frames per source

How the 3,500 frames per source are chosen

Each source contributes the same number of frames, so no single platform dominates. Within a source, frames are spread over a grid of 1 km cells, every cell getting the same quota in turn, so that densely flown trajectories do not crowd out the rest of the flight area.

Frames with at least four SAM3 buildings come first: four is the minimum for every option of a grounding question to be a real, distinct building, and enough anchors to estimate the image–map offset. Within a cell, frames with more buildings are preferred.

Where the frames are

Each dot is the GNSS position logged with an original UAV image that passed UAV-to-map registration. Switch to the benchmark sample to see the 3,500 frames chosen per source. Zoom in to see the registered footprints, and select a dot for its metadata.

How the sources differ

The same building can be 20 pixels wide or 400. Computed over the 3,500 sampled frames per source: dots mark the median, the band the middle half, the line the 5th to 95th percentile. Hover a row for exact values.

Ground sampling distance

centimetres per pixel, log scale

Ground footprint

area covered by one frame, log scale

SAM3 buildings per frame

detections with score ≥ 0.5, log scale

SAM3 cars per frame

detections with score ≥ 0.5, log scale; frames without cars are left out

Which way the image's top edge faces

Heading of the image's up direction, clockwise from north, from the registered corners. Few frames are north-up, so a model cannot assume the image and the map share an orientation.

Altitude and footprint

The sources record altitude against different references, so the paper reports altitude above ground level (AGL). Across the 14,000 benchmark frames, AGL ranges from 104 to 1,508 m with a median of 452 m. AirLock covers the low range, UAV-VisLoc and VETRA the middle, and USGS-RSCC mostly flies at about 280 m.

Footprint area grows with the square of altitude, so each camera forms a line of slope two on log axes, offset by its field of view.

SourceImagesAGL medianAGL rangeFootprint median
USGS-RSCC3,500281 m218–1,508 m103,700 m²
AirLock3,500397 m104–462 m118,200 m²
UAV-VisLoc3,500538 m220–860 m191,100 m²
VETRA3,500662 m206–1,480 m141,200 m²
Total14,000452 m104–1,508 m133,600 m²

Benchmark sample, from the paper's appendix.

Scatter plot of flight altitude above ground against ground footprint area on log axes, one colour per source.
Altitude against footprint for the 14,000 benchmark frames, on log axes. Shaded bands are the 50, 80 and 95% highest-density regions of each source.

Frame