While surveys from fixed cameras are suitable for traffic measurement on selected traffic places of importance (roads, junctions, pathways), drone footages are ideal for high-height videos (50-250m) overviewing a big scene, be it a large intersection, roundabout, superhighway or part of a town.

For each of the two types of footage, we have developed a special kind of processing to deliver the best output. GoodVision Drone Camera Processing is trained specifically for high altitude drone views with higher resolutions, giving accurate results on both top-down and tilt scenes. It is also the best processing option for videos from cameras fixed in big heights.

To achieve the accurate results, please make sure to follow these requirements.

Requirements table

Viewpoint

static

Object distance

25-250m

Resolution

UHD/4K (3840 x 2160) for high altitude footages (100-250m)

2K (2560 x 1440), Full HD (1920 x 1080) for lower altitude footages (50-100m)

Frame rate

FPS 25-30 (15 as a minimum)

Shutter speed

see standard camera processing guidelines

Scene lighting

see standard camera processing guidelines

Obstacles

see standard camera processing guidelines

Autofocus

shall be turned off

Time-lapse

not advisable

Camera/Hardware producers

any

Video length

unlimited, min. duration 1 minute

Video file size

25 GB per single video file

200 GB per multiupload processing

(please contact us in case of a bigger video file)

1. Static viewpoint

GoodVision Video Insights can detect traffic objects from unstable or moving cameras but for the tracking purposes and compact vehicle trajectories, it is necessary to have a stable fixed view. Moving camera would cause moved trajectories on the analytics page and make a proper analysis impossible.

That is easier to achieve by static cameras placed on posts, houses etc. and harder by a footage from a flying drone. We have introduced a stabilization procedure for drone processing which helps to "hold" the scene fixed for slight shaking and shivering of a drone but always try to avoid any unnecessary motion, rotation, zoom etc. when making a drone footage. The more stable the camera will be, the better results you' ll receive.

It is advisable to check your recording before uploading it to our system. If there is a moving part of the footage (like recording when flying, landing, zooming or getting to the best tracking spot), consider removing the moved track from the video which you want to have processed. You would still get accurate results but it is much easier and more transparent to do the analysis when the trajectories are compact.

Also beware when uploading multiple drone videos to a single Data Source in GoodVision application. Video multiupload is possible both in one pack and sequentially but if you intend to put more videos into one Camera (e.g. because of more drone take-offs for monitoring the same place, more chunks of videos etc.), try to make the single recordings as stable and consistent as possible. For recordings with moved or different view, better place them to separate Camera folders.

If everything goes well, the system will reward you with amazing performance like this:

2. Object distance

For a successful drone processing, the footage can be taken both from UHD drone or fixed cameras in heights from 50 to 250 meters above the ground or from the monitored traffic objects. Meaning that on 250m high scenes with top-down or steep view, the objects would be this far and the results will be accurate.

Be careful with camera tilt on drone footage, if the camera is not angled directly downwards, object distance would be much greater for objects further away. Good Vision Video Insights can still deliver results for bigger distances but cannot guarantee a proper accuracy for objects too far away.

For this reason we recommend top-down drone footage but if you require a tilt scene for your analysis, try to record in lower heights than the maximal 250m. Top-down view is best for higher altitude footage and highway/road traffic focus, whilst angled camera on low altitude flights will allow for better detection of smaller objects like bicycles and motorcycles.

3. Resolution

Camera resolution heavily influences the quality of the video and the quality of the computer vision processing. For footage taken in bigger heights 100-250m, the input resolution shall be UHD/4K (3840 × 2160/4096 × 3112) as this allows even the smaller objects to be recognized reliably from higher altitudes.

For videos from lower heights (up to 100m) the footage can be of 2K (2560 x 1440), or FULL HD (1920 x 1080) resolution for flights around 50m. GoodVision can provide the declared accuracy level and detect objects of 20px size with drone processing on ultra-HD footage.

4. Frame rate

Frame rate of the video defines the fluency of the object’s motion and affects the tracking ability of the video analytic system. For Drone High-Detail Processing, ideal frame rate is 30 frames per second. Bigger FPS than 30 does not bring any serious impact to detection quality. On the other hand, FPS lower than 15 might cause tracking problems on various kinds of scenes. Our recommendation regarding frame rate for drone footage is 25-30 FPS, considering FPS 15 as a minimum for results to be delivered.

5. Traffic objects

Drone camera processing is trained to bring accurate results about the ground traffic from up to 250m high altitudes. From these heights, it would be inaccurate to track pedestrians as smallest traffic objects on the scene. The pedestrian class is thus removed from the outputs and data for pedestrians are not available for videos processed via drone processing.

If you are interested in pedestrian data for your drone footage, it has to be recorded in lower heights around 30m above the ground. In that case, the low-drone processing option will deliver data for all traffic objects including pedestrians.

6. Night recording

Even more than by standard fixed cameras, the monitored scene shall be illuminated to a certain level in case of drone footage for the system to be able to track traffic objects reliably. Generally, drone processing is suitable for day recordings and has clear limits by night. Usually scenes from urban areas, city highways etc. have enough artificial lights and are completely fine for night processing. But be careful with recording in rural areas or empty roads by night and always have in mind the rule that the objects have to be visible and recognizable by human eye in order to be detectable by the artificial intelligence.

7. Camera focus

The scene should be focused at the video start and no further focusing shall be applied. We have noticed on DJI footage that sometimes the drone tries to auto-focus during the recording which makes scenes to blur temporarily - we strongly recommend turning off the auto-focus while recording.

8. Camera hardware

GoodVision Video Insights accepts digital video footage from any type of camera with standard optics.

9. Other recommendations

  • For recommendations regarding aspects of the scene (weather conditions, obstacles in view) or camera parameters (shutter speed, lens quality and distortion) please see fixed camera processing guidelines.

  • By drone footage, processing of time-lapse videos is limited and it is not advisable to use time-lapse function while making a drone footage.

  • Minimum video duration for processing is 1 minute. Feel free to upload and process any type of footage adhering to the above mentioned guidelines. Beware, especially by longer drone recordings (or recordings consisting of many video files - more drone flights), it is important to have stable and consistent viewpoint among the files.

  • Maximum size of 1 video file is currently set to 25 GB, and 200 GB per processing of multiple video files. Please contact us in advance when you intend to upload bigger files.

Did this answer your question?