Predator: A Visual Tracker that Learns from its Errors

แชร์
ฝัง
  • เผยแพร่เมื่อ 9 พ.ย. 2024

ความคิดเห็น • 23

  • @Ishpeck
    @Ishpeck 13 ปีที่แล้ว +1

    Is Google going to do a tech talk explaining why they ruined definition searches?

  • @runbyway
    @runbyway 13 ปีที่แล้ว

    How did you compute median from LK tracker? I assume LK will return velocity (u,v) ..Did you find the orientation from this (u,v) magnitude and find the median from this orientation ?
    For the trajectory- the P learning, did you predefined smooth spline equation for trajectory that object will follows?
    For the N learning , you said sth about local maxima. Did you compute the confidence weight from the updated model of median flow tracker (median LK?)

  • @user-xs7uq3pk6l
    @user-xs7uq3pk6l 9 ปีที่แล้ว +1

    Thats pretty good! Thats is open source project?

    • @DeepSeaLugia
      @DeepSeaLugia 7 ปีที่แล้ว +1

      a bit late now, but yes :b
      github.com/zk00006/OpenTLD

  • @lennyhome
    @lennyhome 13 ปีที่แล้ว

    @ekalic2 How do you measure "robustness and speed" exactly? What are the units of measurement? Do "computer vision" people ever agreed on a method on how to do that? And LK is nothing but half of KLT. I'm sorry but it doesn't make it any better.

  • @lennyhome
    @lennyhome 13 ปีที่แล้ว

    @ekalic2 Yes, of course. Nothing personal. What I'm dissatisfied with is the whole field of "computer vision". I think it's not science and that it is just a big bag of tricks borrowed from other fields and re-branded. Stuff like that. And I don't have to introduce myself. Think about me as a random encounter in Final Fantasy, except I lurk into the youtube comments sections.

  • @ekalic2
    @ekalic2 13 ปีที่แล้ว

    @lennyhome Predator does not use KLT tracker. The fact that you don't know the difference between KLT and LK justifies your somewhat naive comment. With respect to failures. Sure, Predator is not the ultimate solution to all tracking problems. But if you show me a state-of-the-art tracker that outperforms Predator in terms of robustness and speed, I will give you 100$ ;)

  • @lennyhome
    @lennyhome 13 ปีที่แล้ว

    @runbyway How do you do that? The answer is: you don't have to. In the computer vision field you make a speech and just pretend you can do it better than somebody else.

  • @diracleo
    @diracleo 8 ปีที่แล้ว

    is it true that Predator became TLD, which became OpenTLD, which became CMT? They are all basically the same tracker, right?

    • @anfedres
      @anfedres 8 ปีที่แล้ว

      Nope... TLD and OpenTLD are similar... CMT is completly different

  • @lennyhome
    @lennyhome 13 ปีที่แล้ว

    In other words this "Predator" is just the good old KLT with a fancy name, fancy features added, a rambling about "feeding back the error" and it fails pretty often outside of specially made demos. Am I right?

  • @magnuswootton6181
    @magnuswootton6181 ปีที่แล้ว

    this is cool for doing 3d with maybe.

  • @runbyway
    @runbyway 13 ปีที่แล้ว

    Don't bother that guy @ekalic2 .. if you have time hope you can answer my question below

  • @michal1337
    @michal1337 13 ปีที่แล้ว

    Terminators are close :D

  • @ekalic2
    @ekalic2 13 ปีที่แล้ว

    @InPursuitOfALife Predator is open source already.

  • @amidunet
    @amidunet 11 ปีที่แล้ว

    i think 0MoTheG is jealous of you Zdenek hihi

  • @ekalic2
    @ekalic2 13 ปีที่แล้ว

    @runbyway The answers to your questions are discussed in my ICIP'10 and CVPR'10 papers. Please see my website (google zdenek kalal).

  • @0MoTheG
    @0MoTheG 13 ปีที่แล้ว

    isn't this adaptive filtering? naming control-theory is rather confusing.

  • @runbyway
    @runbyway 13 ปีที่แล้ว

    @lennyhome I'm sorry.. i'm not asking you.. i'm asking @ekalic2

  • @0MoTheG
    @0MoTheG 13 ปีที่แล้ว

    @coolman9999uk "pretty close to how we see and track objects with the human eye"
    I certainly don't do it that way, speak for yourself. Even animals are much smarter than that.

  • @lennyhome
    @lennyhome 13 ปีที่แล้ว

    @ekalic2 In no other field it would be acceptable for a system to fail because a bird decided to perch somewhere nor it would be acceptable to present a product with no exact specifications and clearly stated operational limits expressed in centimeters, lumens or what have you. Something that can be proven or disproven, you know. And don't worry. I know you don't have any valid answer to the points I'm making. Nobody in computer vision does nor cares.

  • @Ishpeck
    @Ishpeck 13 ปีที่แล้ว

    Is Google going to do a tech talk explaining why they ruined definition searches?