Help detecting snakes using AI

For those of you with programming experience, I have some questions, if you'd be so kind as to read them.

I want to work on a project where I train a camera to detect snakes in real time and track them while within the camera range. So, pretend I have a backyard here in AZ and I suspect there are snakes, but there are also other critters running around, so if general motion detection is recommended that wouldn't help.

I don't know anything about programming so before I consider investing time or money, I'd like to know if this is feasible/how it works.

  1. Is the the type Of project I can tackle using the online AI programming courses? My thoughts where of using youtube videos of snakes for this project.
    1. How difficult would a project like this be for someone with no programming experience. What language would be used?
    2. If I paid someone to create the basic program how much would do you think it would cost?

Thank you

Comments (34)

Most Helpful
Nov 12, 2022 - 2:23am
GoingToBeAnMD, what's your opinion? Comment below:

Just a quick brain dump:

  1. You wouldn't use video, you'd use still images that you pull from that video. So it's not a video problem, it's an image problem. If you want to sound really professional, it's an "image processing" problem
  2. Your biggest challenge will be training data. You'd need all kinds of pictures of snakes in all kinds of environments and positions. You'd basically need to recreate all of the potential ways that snakes could be in real life at any time (day, night, big snakes, small snakes, coiled, extended, on the floor, on a rock, etc).  If you think about all the permutations of all those requirements (e.g. on a rock, coiled, at night; on a rock, coiled, during the day, etc.) then you should realize that you need A LOT of training data. Tens-of-thousands of images or more.
  3. Your aim should be to create an algorithm that removes bias and can act independently as your snake spotter. This has been hard to do with the exact kind of "animal spotting" problem you describe. There is a famous example where a researcher did the same thing for a type of endangered wolf. They thought their program worked, but what they really did was accidentally create an algorithm that detects snow because all of the known photos of this wolf (i.e. the training data I'm describing above) contained snow. 

I will leave it up to you if this is something that you really want to pursue. 

*
  • 5
Nov 12, 2022 - 5:08pm
IncomingIBDreject, what's your opinion? Comment below:

Your biggest challenge will be training data. You'd need all kinds of pictures of snakes in all kinds of environments and positions. You'd basically need to recreate all of the potential ways that snakes could be in real life at any time (day, night, big snakes, small snakes, coiled, extended, on the floor, on a rock, etc).  If you think about all the permutations of all those requirements (e.g. on a rock, coiled, at night; on a rock, coiled, during the day, etc.) then you should realize that you need A LOT of training data. Tens-of-thousands of images or more

Just want to point out that cameras can collect audio data as well, which would be more informative and require less data than purely relying on visual cues.  

Array

  • 1
Learn More

300+ video lessons across 6 modeling courses taught by elite practitioners at the top investment banks and private equity funds -- Excel Modeling -- Financial Statement Modeling -- M&A Modeling -- LBO Modeling -- DCF and Valuation Modeling -- ALL INCLUDED + 2 Huge Bonuses.

Learn more
Nov 14, 2022 - 7:43am
GoingToBeAnMD, what's your opinion? Comment below:

You should be too busy with therapy to be posting here, son. 

*
Nov 14, 2022 - 1:32pm
prospectivepe, what's your opinion? Comment below:

how tf are you gonna detect snakes with audio? also audio data is hard to work with and requires a good bit of math if you want to train a model based on audio inputs.

Nov 12, 2022 - 5:11pm
TheBusinessAdministrationMajor, what's your opinion? Comment below:

GoingToBeAnMD

Just a quick brain dump:

  1. You wouldn't use video, you'd use still images that you pull from that video. So it's not a video problem, it's an image problem. If you want to sound really professional, it's an "image processing" problem
  2. Your biggest challenge will be training data. You'd need all kinds of pictures of snakes in all kinds of environments and positions. You'd basically need to recreate all of the potential ways that snakes could be in real life at any time (day, night, big snakes, small snakes, coiled, extended, on the floor, on a rock, etc).  If you think about all the permutations of all those requirements (e.g. on a rock, coiled, at night; on a rock, coiled, during the day, etc.) then you should realize that you need A LOT of training data. Tens-of-thousands of images or more.
  3. Your aim should be to create an algorithm that removes bias and can act independently as your snake spotter. This has been hard to do with the exact kind of "animal spotting" problem you describe. There is a famous example where a researcher did the same thing for a type of endangered wolf. They thought their program worked, but what they really did was accidentally create an algorithm that detects snow because all of the known photos of this wolf (i.e. the training data I'm describing above) contained snow. 

I will leave it up to you if this is something that you really want to pursue. 

If I don't have the capital now, I'll have the capital some day... I'm doubling down on this.

I was thinking if it's long and slithering its a snake. Then make sure it doesn't detect a hose because the hose wouldn't be slithering. I'd only be looking at the snake in my lawn. If I used something like infrared, I think I could. I think Sagemaker will work

How easy would it be to build an algo/ how much would it cost?

Nov 12, 2022 - 5:27pm
GoingToBeAnMD, what's your opinion? Comment below:

It all depends on who you hire. I have a team of absolute killers that does this type of work for my function but I pay them quite a bit to be good. 

*
  • 1
Nov 14, 2022 - 12:29am
KnowsNothing, what's your opinion? Comment below:

Download snek from internetz, train machine learning model on snek, run object detection preprocessing to output snek and objectz, run snek detector on output to detect snek.

Can be done, yes, but is this seriously worth his time?

(Also, I have no idea why I decided to go cacographic on you... Seemed funny at the time.)

Nov 14, 2022 - 7:42am
GoingToBeAnMD, what's your opinion? Comment below:

User name checks out. 

*
Nov 12, 2022 - 5:31pm
Short Caller, what's your opinion? Comment below:

To be fair the best way to detect a snake wouldn't necessarily be through static image processing given that they are very difficult to distinguish from their environment but more like through motion detection.

Nov 12, 2022 - 5:55pm
GoingToBeAnMD, what's your opinion? Comment below:

I appreciate your thoughts but let's not do Level 1 thinking here:

  1. The kid said he wanted video, let's do video
  2. I've been answering with the assumption that "snakes" may be a euphemism for other things he may want to detect or create an algorithm for. That's fair play. I want people to realize that writing algorithms (any algorithm) is fucking hard. 
  3. Motion detectors are going to give you all sorts of false-positives and you'd need something very, very high end to detect a snake moving. I used to work in physical security with cameras, access control, stuff like that. The good stuff always costs a ton of money. 
  4. If you did this as a business you could have people set up their own cameras and then your algorithm takes over from there, get recurring revenue from the subscription to your algorithm hosted on your own servers. That's a completely defensible model, no one gets your IP. With motion detectors, any setup you make people can copy by buying the same stuff - a horribly indefensible business model. Why would you want that? 

I appreciate your thoughts

*
  • 5
Nov 12, 2022 - 6:36pm
TheBusinessAdministrationMajor, what's your opinion? Comment below:

Correct as noted above big fish are the end game, but I figured snake detection would work too and be something I could try out.

Basically my thought was if I can't capture a slithering snake from a picture. As t moves the snake slithers and its body oscillates side to side. The video angle would be static and Arial. I guess I don't need AI for this since this will always be constant. I just want to detect the moving image on a screen. Looks like Python with OpenCV or tensorflow might work.

Nov 13, 2022 - 5:00am
BigKahunaBanker🏄🍹🍔, what's your opinion? Comment below:

Bro, studied, educated SWEs routinely fuck up tasks like this even with million-dollar budgets. What makes you think you can do this by yourself with no education, no money, and no incentive beyond "but I wanna know"?

...and the Truth shall set you free
  • 1
Nov 16, 2022 - 8:05pm
Pug, what's your opinion? Comment below:

Every SWE was once someone who didn't know how to code

“The three most harmful addictions are heroin, carbohydrates, and a monthly salary.” - Nassim Taleb
Nov 13, 2022 - 1:38pm
Fugue, what's your opinion? Comment below:

You can probably train a support vector machine to analyze stills from the video capture and identify a pre-determined list of critters. 

Array

Nov 14, 2022 - 10:20am
TechBanking, what's your opinion? Comment below:

This reminds me of the hot dog/not a hot dog episode of Silicon Valley with Jin Yang 

  • 1
Nov 14, 2022 - 2:32pm
ThreeSixThree, what's your opinion? Comment below:

Velit in veritatis veritatis. Adipisci temporibus et non illo unde quod. Aut numquam magnam repudiandae vitae sed ea. Ut natus voluptate inventore facilis eveniet porro quam. Repudiandae temporibus veniam reiciendis.

Dolor eos voluptatum voluptates ut culpa officiis. Sit necessitatibus nihil distinctio harum necessitatibus sunt explicabo. Doloribus hic commodi molestias id dolorum quia deleniti.

Borrow at 3, Lend at 6, Golf at 3
Nov 18, 2022 - 11:02am
Sir Desmond Glazebrook, what's your opinion? Comment below:

Perferendis consequatur et dolores consequatur qui nam. Ab reprehenderit rerum est non officia alias praesentium. Tenetur voluptatum voluptates quis fuga asperiores molestiae sed aut. Suscipit est illum aut non quidem et.

Omnis possimus dignissimos in praesentium eum voluptatem veniam quam. Tenetur saepe tempora reiciendis qui. Qui architecto qui est nesciunt.

Sit delectus voluptatem quas. Mollitia at non quis qui. Voluptatum rerum perferendis nisi. Mollitia dolor natus incidunt dolores nihil.

Start Discussion

Career Advancement Opportunities

November 2022 Investment Banking

  • Jefferies & Company (▲08) 99.6%
  • Lincoln International (= =) 99.3%
  • Financial Technology Partners (+ +) 98.9%
  • Evercore (▽01) 98.5%
  • Bank of America Merrill Lynch (▲01) 98.1%

Overall Employee Satisfaction

November 2022 Investment Banking

  • PJT Partners (= =) 99.6%
  • Evercore (▲02) 99.3%
  • Greenhill (▲06) 98.9%
  • Canaccord Genuity (▲15) 98.5%
  • William Blair (= =) 98.1%

Professional Growth Opportunities

November 2022 Investment Banking

  • PwC Corporate Finance (▲14) 99.6%
  • Lincoln International (▲03) 99.3%
  • Jefferies & Company (▲04) 98.9%
  • William Blair (▽02) 98.5%
  • Evercore (▽01) 98.1%

Total Avg Compensation

November 2022 Investment Banking

  • Director/MD (10) $613
  • Vice President (38) $392
  • Associates (217) $255
  • 2nd Year Analyst (138) $163
  • 3rd+ Year Analyst (19) $160
  • 1st Year Analyst (463) $153
  • Intern/Summer Associate (88) $151
  • Intern/Summer Analyst (334) $92