Jump to content

Anyone Using Artificial Intelligence With Their Gold Detectors?


Recommended Posts

17 minutes ago, Chase Goldman said:

I think where AI and AR would be most useful as an adjunct to detecting is by mapping out ground coverage of the detectorists coil.

Doesn't the GPZ7000 do something like this (using its built-in GPS)?

Do people really want to be told the reason they found a good target with a brand new detector in a site they had previously detected was due to never having gotten the previous coil(+detector) over it in the first place?  😏

  • Haha 1
Link to comment
Share on other sites


19 minutes ago, Chase Goldman said:

The problem to be solved is accurately tracking the coil as it is swung through the site.  GPS does not cut it from a precision standpoint, but use of a stationary drone that is tracking and tracing the coil may be just the ticket.

Thank you for the insight. Initially I can't think of any solution to this but I really like your thinking. I'll have a ponder and see if anything comes to mind. I imagine the surveying industry will be the first to solve some precise gps that can get down to consumer cost. They have a lot of really interesting things with lidar and AI but I haven't seen anything around gps. I'm sure other members on this forum have a lot more knowledge than me around it.

Once the accurate gps is solved and smart glasses become common I'm sure combining them wouldn't be impossible.

  • Like 1
Link to comment
Share on other sites

20 hours ago, GB_Amateur said:

This paragraph seems to contradict itself.  "...Not a huge amount of training data is needed."  Then the next sentence:  "...over millions of iterations it starts to learn."  (emphasis mine)

 

Thanks for your reply 🙂 

I had worded the sentence badly. It goes through the set amount of data millions of times.

I'll check out the detector with the GPS that you mentioned in your last post.

Link to comment
Share on other sites

18 hours ago, Mike_Hillis said:

You should buy a metal detector and join us.   

All I want to see/experience/hear is the object's density as compared to a standard, with an audio output that tells me how close the signal response is to the standard.

Hi Mike,

Thanks! I potentially will end up doing so. 

It sounds like detectors can already tell you the density compared to a set standard, or is this not the case?

Link to comment
Share on other sites

Hi Jasong,

Thank you for your post, it's got a lot of really good insight. 

What are your thoughts on the longer post I made about training an AI at each specific site? 

I also love Alpha Zero! It's so exciting the things that are being made 🙂 

Link to comment
Share on other sites

1 hour ago, Ben201000 said:

I imagine the surveying industry will be the first to solve some precise gps that can get down to consumer cost.

To do this accurately you need to move away from GPS as it can only be accurate at best to within 6 feet.  Fractions of an inch matter in coil coverage.  I'm thinking a portable local solution.  Perhaps consisting of laser tracking of a coil target monitored and recorded with precise positioning data coupled/integrated with visual information using a drone or drones hovering over the search area.  Think golf ball flight tracking and virtual first down marker lines across the video display of a football field.

  • Like 3
Link to comment
Share on other sites

1 hour ago, Ben201000 said:

It goes through the set amount of data millions of times.

We may be getting "too deep into the weeds" or discussing something that is less important than much that has been written in other posts.  At the risk of this...

Plowing through limited data too many times leads to a well-known machine learning flaw known as 'overfitting'.  The resulting model does well if you give it one of the events from the training sample, but if that training set doesn't cover the space of existing conditions very well it can be way off while give the misleading impression it's accurate.

  • Like 1
Link to comment
Share on other sites

Inertial navigation using accelerometers and then dead reckoning is far more accurate than GPS for moving systems. It's sufficient for things like general ground sensing. When used in combination with mag sensors and coil data, you could achieve sub-inch resolution easily. 

Essentially you would make the ground it's own reference frame while swinging the coil using inertial navigation, and then tie that high resolution work "chunk" to a traditional lat/lon reference frame via GPS. 

  • Like 2
Link to comment
Share on other sites

I might be old school, probably because I am old, but for me I like to be in control of the high level intelligence elements.  Sure ground balance, ground tracking, EMI elimination are great features to have and enable the detector and the detectorist to focus on the actual signals of interest but I enjoy training my ears and my mind to learn the sounds of a gold target vs trash or ground noise and it is this element of the hobby that gives me excitement, pleasure and joy.  Each gold field can produce slightly different target sounds and again part of the challenge/fun is to learn those sounds and develop the skill to predict if a pre-dug target is going to be gold or trash.  I still tend to dig most targets anyway but after a few hours of digging trash targets in a particular area I get satisfaction from knowing that I can reach a 90%+ probability of predicting gold vs trash.  IMO it is this HUMAN intelligence skill that differentiates great detectorists from average ones. 

I do enjoy the convenience of technology for every day tasks but I have observed over my lifetime that as technology get smarter the human get dumber.  After Velcro came out kids forgot how to tie their shoes.  After google maps came out people forgot how to read maps.  Even common sense has fallen by the wayside when you read stories of people that are so reliant on technology that they can't even solve simple every day problems. 

Sure the computing power behind AI learning can achieve things in hours or days that would take the human brain years or decades to learn but I will never underestimate to power of the human mind that is a result of thousands of years of evolution in the REAL world. 

Do you really want an AI based, all knowing, detector to reduce you down to the mere unintelligent functions of swinging and digging? 

  • Like 4
Link to comment
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
×
×
  • Create New...