outline from gadient mask

  • 201 Replies
  • 12155 Views
*

keghn

  • Trusty Member
  • ********
  • Replicant
  • *
  • 673
Re: outline from gadient mask
« Reply #165 on: September 03, 2017, 11:44:07 pm »
 Well in the first video your program is rip roaring fast. I the next video it look like it is going really fast at doing nothing? A bug?
What is really going on?   

*

yotamarker

  • Trusty Member
  • ********
  • Replicant
  • *
  • 593
    • battle programming
Re: outline from gadient mask
« Reply #166 on: September 04, 2017, 02:51:51 pm »
it detects the objects in the picture then the objects in those detected objects.

in the second video it runs faster because I took out marking the detected outline pixels.

in the case of the leaf girl nothing was detected because of all the leaves, I think it is best to use motion detection
for her cases  because it is faster and offers detection for more special cases than specific color detection

*

keghn

  • Trusty Member
  • ********
  • Replicant
  • *
  • 673
Re: outline from gadient mask
« Reply #167 on: September 04, 2017, 08:20:26 pm »
 Can you change the thresh hold higher. Sorry do not remember if you are using a company's software, edge
detector or are using your own. That is based on neighboring kernel squares. Like was discussed earlier? 

*

yotamarker

  • Trusty Member
  • ********
  • Replicant
  • *
  • 593
    • battle programming
Re: outline from gadient mask
« Reply #168 on: September 14, 2017, 08:00:03 pm »

*

keghn

  • Trusty Member
  • ********
  • Replicant
  • *
  • 673
Re: outline from gadient mask
« Reply #169 on: September 19, 2017, 03:32:08 pm »

*

keghn

  • Trusty Member
  • ********
  • Replicant
  • *
  • 673
Re: outline from gadient mask
« Reply #170 on: September 19, 2017, 10:01:38 pm »

*

yotamarker

  • Trusty Member
  • ********
  • Replicant
  • *
  • 593
    • battle programming
Re: outline from gadient mask
« Reply #171 on: September 21, 2017, 11:32:35 am »
todays puzzle :
how do you make an A.EYE recognize groups such as :
employees , customers, dolls, bots, Japanese people, palm trees

*

yotamarker

  • Trusty Member
  • ********
  • Replicant
  • *
  • 593
    • battle programming
Re: outline from gadient mask
« Reply #172 on: September 23, 2017, 10:40:08 am »
today I learned I can't use class attributes(vars) in shared procedures  ;D

*

ivan.moony

  • Trusty Member
  • *********
  • Terminator
  • *
  • 781
  • look, a star is falling
    • Structured Type System
Re: outline from gadient mask
« Reply #173 on: September 23, 2017, 10:45:22 am »
I it is about object oriented programming, there should be public and private modifiers. Private would be visible only inside the object, while public should be visible everywhere. There should also be other modifiers for i.e. visibility over inheritor classes.
Wherever you see a nice spot, plant another knowledge tree :favicon:

*

keghn

  • Trusty Member
  • ********
  • Replicant
  • *
  • 673
Re: outline from gadient mask
« Reply #174 on: September 25, 2017, 08:44:55 pm »
 The difference between people and palm trees can be just done by there outline.

 Each out line are made up of sub features. Such as straight lines, corners, and curves.
 Which bring up a important topic of what is a straight line. It is a line that goes in between two parallel lines. And you want to use the parallel lines for data not the real line. Because there can be thousands of type of crooked lines that cans
stay withing the parallel lines. 
  Which will end up being a chain code of two points that the line goes threw.

 In video out line jump around and do crazy thing. So you need to track outlines back to the selfie for the classification:

https://selff.ee/


*

yotamarker

  • Trusty Member
  • ********
  • Replicant
  • *
  • 593
    • battle programming
Re: outline from gadient mask
« Reply #175 on: September 26, 2017, 09:20:50 pm »
but the question was about groups.

*

korrelan

  • Trusty Member
  • ********
  • Replicant
  • *
  • 746
  • Look into my eyes! WOAH!
    • Google +
Re: outline from gadient mask
« Reply #176 on: September 27, 2017, 12:59:33 pm »
Quote
how do you make an A.EYE recognize groups such as :
employees , customers, dolls, bots, Japanese people, palm trees

You use feature detection not the objects outline… pretty sure I mentioned this really early on in this thread.

Outlines are very unreliable; the object can be partially occluded or colour/ contrast boundaries can deform/ impose a false outline etc.

 :)
It thunk... therefore it is!

*

yotamarker

  • Trusty Member
  • ********
  • Replicant
  • *
  • 593
    • battle programming
Re: outline from gadient mask
« Reply #177 on: September 27, 2017, 05:12:59 pm »
I was thinking sampling less pixels for the classifier

*

keghn

  • Trusty Member
  • ********
  • Replicant
  • *
  • 673
Re: outline from gadient mask
« Reply #178 on: September 28, 2017, 04:43:25 pm »
 if you mean looking at to blobs of crowds from a distance then to randomly pinpoint sampling within each blob. Then yes. 
 Using a uncle Bob classifier will not detect other people. Because it is "over fitting". It needs
more "biasing" to generalize on others.

How Support Vector Machines work / How to open a black box: 

« Last Edit: September 28, 2017, 05:18:05 pm by keghn »

*

yotamarker

  • Trusty Member
  • ********
  • Replicant
  • *
  • 593
    • battle programming
Re: outline from gadient mask
« Reply #179 on: September 28, 2017, 07:02:19 pm »
for a refreshing and unexpected change the A.eyes next level was reached easily.
to be continued