All hail the new AI speed camera
Discussion
Sporky said:
Sorry, being thick - what are KSI, RTM, and FTP in this context?
Don't worry, no-one can know all acronyms for all subjects! 
KSI : Killed or seriously injured (in road traffic accidents as recorded by Police).
RTM : Regression to the mean.
FTP method : Four time periods method.
RTM is an effect caused by how speed camera sites are selected,
and the FTP method is the method I developed to remove RTM from data at speed camera sites.
https://speedcamerareport.co.uk/rtm-regression-to-...
Sporky said:
Sorry, being thick - what are KSI, RTM, and FTP in this context?
KSI Killed or Seriously injured. KILLED: Human casualties who sustained injuries which caused death less than 30 days (before 1954, about two months) after the collision. Confirmed suicides are excluded.
SERIOUS INJURY An injury for which a person is detained in hospital as an “in-patient”, or any of the following injuries whether or not they are detained in hospital: fractures, concussion, internal injuries, crushings, burns (excluding friction burns), severe cuts, severe general shock requiring medical treatment and injuries causing death 30 or more days after the collision.
An injured casualty is recorded as seriously or slightly injured by the police on the basis of information available within a short time of the collision. This generally will not reflect the results of a medical examination, but may be influenced according to whether the casualty is hospitalised or not. Hospitalisation procedures will vary regionally.
RTM Regression to the Mean
As the linked report below says it's just a fancy way of saying "returning to normal"
FTP Four Time Periods.
See more here, https://speedcamerareport.co.uk/rtm-regression-to-...
Edited Dave clearly types more rapidly, thought it was worth including specifics around KSI
FIF said:
An injured casualty is recorded as seriously or slightly injured by the police on the basis of information available within a short time of the collision. This generally will not reflect the results of a medical examination, but may be influenced according to whether the casualty is hospitalised or not. Hospitalisation procedures will vary regionally.
So all "crash cash" claiming whiplash and needing a "cut out" would be recorded as Serious? From my experience a lot of extractions are for the mere fact there could be a possible spinal injury, not the wrong thing to do given the risk to patients, but makes road sound more dangerous if its recorded as "Serious" injury despite it coming to nothing or being about whiplash cash.Also, Dave, I am truly amazed at what you have done, and that official reports are using your method..
Over the years there's been some utter devious behaviour with camera placements and speed limit reductions. We once had a fairly rural B road reduced from NSL to 30 and 40 essentially based on a single incident involving a stolen vehicle containing a couple of TWOCers who ran out of talent trying to outrun the pursuit.
mjb1 said:
These cameras are only for seat belt and mobile phone infringements - they don't measure or record speed (at least the one trialled in D&C last year didn't).
So it's ok to drive past one as fast as you like as long as you've got your seatbelt on and are using hands free...
Yes. This thread has gone way off topic into a debate about speed cameras. So it's ok to drive past one as fast as you like as long as you've got your seatbelt on and are using hands free...
helix402 said:
mjb1 said:
These cameras are only for seat belt and mobile phone infringements - they don't measure or record speed (at least the one trialled in D&C last year didn't).
So it's ok to drive past one as fast as you like as long as you've got your seatbelt on and are using hands free...
Yes. This thread has gone way off topic into a debate about speed cameras. So it's ok to drive past one as fast as you like as long as you've got your seatbelt on and are using hands free...
NFT said:
Also, Dave, I am truly amazed at what you have done, and that official reports are using your method..
Cheers, NFT. It's rare for my work to be appreciated, thanks! Officials have acknowledged that my FTP method is accurate, but no official (tax-payer funded) report has yet used it TMK.
The RAC Foundation (a charity) did use my FTP method but did not determine when the SSP was, they just assumed it was a particular 3 year period.
If they had been right, they would have had an accurate report.
The largest group of cameras in their report, though, were the fixed cameras in Thames Valley,
and that was the group that I had the database for!
The SSP was actually 5 years (not the 3 they had assumed).
So there are 4 reports that have used my FTP method properly TMK, 2 by me and 2 by Professor M Maher.
All 4 found increases in fatal and serious collisions at the speed camera sites.
But thanks again!
Are these AI cameras subject to requirements for 'warning' signs in the area, like other speed cameras? or do they circumvent that by having the signs on the van ...? will they be operated by civilian S/CAMERA partnerships like the current roadside van ones? what tolerance / calibration do they operate to ?
wondering if AECOM Dr behind them is really interested in improving road safety ... or the profit ...?
wondering if AECOM Dr behind them is really interested in improving road safety ... or the profit ...?
Gassing Station | Speed, Plod & the Law | Top of Page | What's New | My Stuff