41–50 of 79 posts
Has anyone seen any nice examples of work done with the open LiDAR data?
Has anyone seen any nice examples of work done with the open LiDAR data?
I've been using LIDAR data for doing canopy height modeling, and screening remote areas for possible exceptional/champion trees prior to checking it out in person.
Haven't put anything online yet because I'm very new to GIS and this sort of thing, and am still getting over the horror of what it takes to build a functioning workspace and data pipeline.
("Just take this TIFF and convert it to a CSV" is a phrase I never thought would make sense, but here it does.)
Self driving cars have lowered some LIDAR costs a factor of 20, with a promise of far more. I wonder if this can translate over into archeology and geology. Imsaw one project at SIGGRAPH using a cheap LIDAR.
"the power to deploy these technologies at scale will only be deployed to fight serious crime" [proceeds to use dragnet to crack down on people dumping stuff in the woods]
"the power to deploy these technologies at scale will only be deployed to fight serious crime" [proceeds to use dragnet to crack down on people dumping stuff in the woods]
Anyone know where I could license/purchase hi-res LIDAR scans for use in game development?
The data from the Puget Sound LIDAR Consortium [1] is freely available, you just need to ask for an account. (Not 100% sure on licensing terms, though.) Seattle / King County just finished a rescan in 2016/2017 and the data is stunningly good. [2] Really good consistency and density. The DLM/classification/cleanup seems excellent. [1] http://pugetsoundlidar.ess.washington.edu/ [2] (private, need an account) http://pu…
Self driving cars have lowered some LIDAR costs a factor of 20, with a promise of far more. I wonder if this can translate over into archeology and geology. Imsaw one project at SIGGRAPH using a cheap LIDAR.
eg, a typical high-quality survey will involve:
- Something like a Leica ALS80 [1]
- A Cessna + good Pilot, the plane needs to be really well instrumented.
- A team of surveyors on the ground to establish ground controls, and occupy points for GPS RTK calculations
- A bunch of post-processing to normalize the data, remove birdies and pits, do ground classifications, etc. (The raw data from the sensor before the processed point cloud is built is really really raw.)
A much cheaper approach which seems to be catching on is UAV photogrammetry. It's processing intensive, but no special sensors are required, and in the end you still get a pointcloud. Sensefly is a company that makes these types of UAVs.
[1] https://leica-geosystems.com/en-us/products/airborne-systems...
I have a question about self-driving cars (SDCs). Some time ago it was mentioned that SDCs can't use deep-learning because it is not sufficiently reliable, and that instead techniques like LiDAR should be used to recognize objects. However, this made me wonder: how does the car recognize road-signs and traffic lights?
I think you're confusing things. Deep Learning is a method of machine learning. LiDAR is a tool that collects depth data. Using Deep Learning on flat image data to try and detect depth is unreliable, hence SDCs use LiDAR to detect depth. They also use image data from the visible spectrum and beyond to read road signs. etc.
Or is DL classification at 100% accuracy?
For those unaware, all scientific press releases in the UK must express areas in football pitches, and volumes in double-decker buses.
It is unhelpful when it’s 32 million of them, and especially so when the size of a football field is variable.
Sure, maybe the local, community field you and me play on, but not the ones where "real" matches are played. They have a standard size.
FIFA for example have the dimensions in their first law: http://www.fifa.com/mm/Document/FootballDevelopment/Refereei...
Probably they mean a standard football field.