Member Info for TheLongestShot

ah the tyranny of word count.

Anyway, Is the thing that the eye is looking at the vehicle in front (should be the same vehicle for many frames/minutes. Is the eye looking at a road lane with nice easy to see edges. Is it reading a sign - it needs to track as the sign approaches. Is it drawn to lateral movements as cars change lanes or person/child approaches the road/lane from the side. Is it following an object and still watching through from the side windows - was it a sign, a vehicle or a pretty girl - (sorry just classify that as a person we don't want to get in to trouble - of course it could be like Amazon and prompt that you normally look at X just in case you missed it!)

JC, I have been thinking.

Apologies, my first thoughts on labelling was that there is a whole world outside of the vehicle and that is a lot to label - is it a bike, a kangaroo, a human with a bike or an umbrella or shopping bags. Walking with a child a dog or horse etc. Having a single researcher driving to generate data didn't seem to make sense, but that would only be part of the job. It could be 2 weeks on a test site with volunteers, but some driving would be required. those tests would require labelling.

I then read the See patent and started to get more excited as I realised that we have 3 billion km of driving data - yes most is of drowsy drivers, but here is the key part that I forgot about: many or even most gen 2 Guardian's have forward facing cameras. Sure they only record for the seconds before and after an event, but we have road data. Some is triggered by the driver pressing the button to capture "the idiot in front" others will be of drivers not looking, but given the vast volume of data a reasonable amount of snippets should be usable with a driver looking ahead and the front camera seeing the view in front.

Ok, here comes the best bit. Guardian has the front and driver facing cameras mounted in the same unit with fixed geometry - far better than a car where the cameras could be separated and be at different angles in different vehicles. In Guardian, they are effectively on the same height (y axis) same forward distance (z axis) and on the X axis they are only separated by a few fixed cm (parallel to the axle) SEE also know the relative angles (say ~180 degrees apart), but again it is fixed.

Now we have a nice data set to work with. Now as discussed in the Patent, they still have to find the driver and the eyes and determine the gaze direction (this is SEE after all). The eye positions in the 2-d picture are done, then you need the distance to the eyes well we know the size of an eye, so that is another triangle and you have the distance. Now take the gaze from the eyes and draw that forward and work out where it lands on the 2-d forward facing image.

This bit is a bit trickier, so we use a bit of cunning - roads are "generally" horizontal (they mentioned measuring a slope) but I was a physicist, so I will assume an infinite horizontal surface for now. Lets say that the truck driver's eyes are 6 foot up and the guardian is at roughly the same height (only 1 foot above or below). Now you can intersect the gaze with the perfect horizontal road. Re do the maths for different heights and separations of the guardian and the fixed point stretches from a circle to an ellipse. Maybe 2-5 metres long and 1 metre wide. But on the 2-d camera image that corresponds to a more circular blob. Now assume that there was a truck in the way with a nice vertical back. The maths still works out the with the same circular blob location.
Now just need to label roads or trucks. Add in rapid movement laterally and see if eye follow

I will blame you ;) for my early enthusiasm at 8.4 and 8.8 when the price stopped on its way down and but then started to climb again.
But now averaged down to 4.5 so comfortable again. I will keep adding ...

Terry,

Can I come and work in you office? - Either for the free shares or because you just pay them so well that they can splash out on so many shares.

My next target is to upgrade from minnow to tiddler (or is it the other way around)

Chasing every possible RFQ would need more pre-sales, more tech sales, management spread wider. And if we did bid low enough to win we then need even more engineers to deliver. And if we don't win , then we have got too many extra expensive staff

JC I would think that sunglasses, mask, hat, are more likely. Perhaps, behaviours too: turning, smoking, eating
Possibly, counting occupancy, babies, handbags etc

Hi JC,

I like the idea of using eye convergence or measuring the focal length plane to choose whether or not to make the screen transparent.

The core of this patent was from 2014; but now real-estate that is the rear view mirror area is too valuable to be transparent as that is where all the forward facing cameras and gubbins are located.

or do we have to add an extra 30 months to get to the "the date of application of this Regulation". In which case can't launch a new model without Camera DMS in 30 months + 24 months = 4.5 years, and all new cars will need it in 6.5 years - that fits with the 70% in 2026 estimate???

But the smart OEMs will skip option B and go straight to C

Zeq,

SemiCast's photo shows the dates of the various DMS optioms https://twitter.com/semicast_res/status/1193843405220122625/photo/1

Then on page 17 of Annex ii it explains the codes

B:
Date for refusal to grant EU type-approval: [the date of application of this Regulation]

Date for the prohibition of the registration of vehicles, as well as the placing on the market and entry into service of components and separate technical units: [24 months after the date of application of this Regulation]

C:
Date for refusal to grant EU type-approval: [24 months after the date of application of this Regulation]

Date for the prohibition of the registration of vehicles, as well as the placing on the market and entry into service of components and separate technical units: [48 months after the date of application of this Regulation]

My translation.
B: If you launch a new model you need "Type approval", you won't get Type approval without at least a coffee cup by the end of 2019. In 2 years, you won't be able to sell any vehicle without "coffee cup"

C: After 2 years, you can't launch a new model "type approval" without Camera DMS. After 4 years, you can't sell any cars without Camera DMS

Confusingly Driver availability monitoring for L3 Handover is B5 Where the 5 indicates it is mandatory in automated vehicles

@MissyCummings is an academic vehicle safety professional (ex US Navy Pilot too)

One obvious answer of that each OEM gives their work to 3 suppliers. So if any one has a supply issue due to manufacturing or labour problems, they are at least not completely stopped.

However, we are not manufacturing. They can split how the camera and led modules are supplied.

If they have a software solution, and See went bust or went on strike it wouldn't affect OEM production as the software is already delivered.
That is part of the reason that Xylinx now supply the OEMs with chips directly - it reduces the risk to the OEMs.

Of course that does still leave us as the essential company that they have to contract with. But as you may have noticed, OEMs still have plenty of leverage for now when it comed to not signing contracts yet!

Final count at just over 24 hours was 58 readers who took the time to vote. Who knows how many read without signing in so couldnt vote. Not a bad number and since yesterday was so busy I imagine many just skimmed the posts over only part of the day. Thanks all

Chris, this is the key section for me in that article :

Two years ago, with its autonomous driving tech still in development, Toyota said that it will make many of its patents related to this field available for free. It may not have grabbed headlines then, but in light of all the new developments, it’s beginning to look like a bid for world domination.

The reason why personal computers are so ubiquitous now is because Compaq (now owned by HP) dared to build an IBM (now no longer building PCs) Perconal Computer clone that could run the same formerly proprietary software on its hardware. All it took was their brazen act for IBM PC compatible clones to proliferate and turn PC's into a household appliance.

Not just cars: Toyota wants to be a household name image

By sharing patents to its tech, Toyota hopes to do the same and encourage the adoption of their hardware, protocols, and standards over any other competitors. With the Arene development platform, Toyota can easily offer development kits for any budding software company to develop apps for their vehicles. All it takes is for Toyota to start its own vehicle app store to verify, monitor, and distribute third party apps.

Just like how Google quickly overtook Apple in the smart phone Arena, Toyota hopes to overtake all other tech companies in the mobility arena with their hardware and software.

Last night at 21:25 I posted a quick survey:
I guess I was surprised but how many were in the room at the CMD.

We know there is a core group of regular posters here and a fair sized group of occasional posters. But how many read but never post.

If you haven't done so, please recommend the ORIGINAL POST so we can get an indication of the size of the regular readership, it is currently mid-way down page 3

It achieved 15 in 30 minutes, 30 in 2 hours and now is showing 45

No ego, just research. Thanks

Not worried about the short term price myself. I haven't got any money for a top up! But we are a microcosm. Inside the bubble we understand that we are looking at 5x, 10x some may believe far more is possible but it is a way off. But unless the needle starts to move no one will pay attention. The more it can move steadily up now the better our final exit price will be?

I guess I was surprised but how many were in the room at the CMD.

We know there is a core group of regular posters here and a fair sized group of occasional posters. But how many read but never post. Can you please recommend this post so we can get an indication of the size of the regular readership?

No ego just research. Thanks

So, I am convinced. Much of the LSE have been convinced. Some were convinced years ago and are disappointed with where we are. Lombard have bought in, some IIs have left us.

So the big question is how much will the analysts write about SEE, how many eyes will see it and how will the SP move in the near term?

Maybe the flights to the UK are easier than to get to VW / Volvo

So "naughty boys" who were at the CMD, if you haven't let us know already - how was it for you?

Thanks JW,

I take it that you mean that are saying that Airlines / OEMs / Tier 1s / Hauliers are starting to knock on our door rather than us having to persuade them to listen to us?