Comparison
Indoor vs Outdoor Video Data Collection
Short answer
Indoor and outdoor egocentric capture differ mainly in lighting and depth sensing: indoor conditions are controllable but limited in variety, while outdoor conditions add direct sun, moving shadows and long range that stereo depth handles better than active depth sensors. Firsthand samples daylight, low light, mixed, indoor and outdoor conditions directly in the capture matrix rather than defaulting to one setting.
Spec comparison
Indoor vs outdoor capture, side by side.
Evaluation criteria
Eight things to check on any vendor.
- Lighting variability
- Indoor lighting can be held steady across a session; outdoor lighting changes with sun position, cloud cover and cast shadows, which a policy trained only indoors will not have seen.
- Depth sensor choice
- Active depth sensors that work well indoors can struggle outdoors in bright sun. Stereo depth is pixel-aligned with the RGB view and works outdoors where active sensors struggle.
- Environment and mobility
- Outdoor capture typically covers more ground and more varied surfaces than a fixed indoor space, which matters for mobility and navigation-adjacent skills.
- Sampling across the matrix
- A capture spec that only samples one setting leaves a gap. Firsthand’s conditions matrix samples daylight, low light, mixed, indoor and outdoor together rather than defaulting to whichever is easiest to schedule.
Red flags
Walk away when you see these.
- A vendor whose sample footage is entirely indoor, with no stated ability to capture outdoor conditions.
- Active depth-sensor footage shot outdoors in direct sun without checking whether the sensor still returns clean depth.
- A capture spec that does not name indoor/outdoor as an explicit condition to sample.
Scoring template
Score candidates against your skill spec.
Copy this table, weight each criterion for your use case, and score each vendor on the same free or paid sample.
FAQ
Common questions.
Does Firsthand capture outdoor video data?
Yes. Firsthand’s catalog includes outdoor segments (“Outdoor & mobility” and “Outdoor & public space”), and the capture conditions matrix explicitly samples indoor and outdoor settings alongside daylight, low light, mixed and cluttered conditions.
What is the main difference between indoor and outdoor data collection?
Lighting and depth sensing. Indoor lighting is controllable and repeatable; outdoor lighting changes with sun position and cast shadows. Active depth sensors work reliably indoors but can struggle outdoors in bright sun, where stereo depth holds up better because it stays pixel-aligned with the RGB view.
Why does outdoor capture matter for robot learning?
A policy trained only on indoor footage has not seen the lighting variability, longer sightlines and mixed surfaces that outdoor environments introduce. Sampling both settings in the capture matrix closes that gap rather than leaving it for deployment to reveal.
Should I use stereo or active depth for outdoor capture?
Stereo depth is generally the better fit outdoors because it is pixel-aligned with the RGB view by construction and does not depend on projecting a pattern that direct sunlight can wash out, unlike many active depth sensors.
Can I request a specific mix of indoor and outdoor footage?
Yes. Indoor/outdoor is one of the conditions sampled in a custom collection’s capture matrix, alongside lighting and clutter, so you can weight the mix toward whichever conditions your policy needs most.
Last reviewed: 2026-09-23
Judge it on your own skill spec.
Get the free 40-episode sample pack, or send us your target skills and hours for a scoped quote.