How computers learn to recognize objects instantly | Joseph Redmon

How computers learn to recognize objects instantly | Joseph Redmon

Ten years ago, researchers thought that getting a computer to tell the difference between a cat and a dog would be almost impossible. Today, computer vision systems do it with greater than 99 percent accuracy. How? Joseph Redmon works on the YOLO (You Only Look Once) system, an open-source method of object detection that can identify objects in images and video — from zebras to stop signs — with lightning-quick speed. In a remarkable live demo, Redmon shows off this important step forward for applications like self-driving cars, robotics and even cancer detection.

Check out more TED talks: http://www.ted.com

The TED Talks channel features the best talks and performances from the TED Conference, where the world’s leading thinkers and doers give the talk of their lives in 18 minutes (or less). Look for talks on Technology, Entertainment and Design — plus science, business, global issues, the arts and more.

Follow TED on Twitter: http://www.twitter.com/TEDTalks
Like TED on Facebook: https://www.facebook.com/TED

Subscribe to our channel: https://www.youtube.com/TED

50 Comments

  1. Hsu Orozco on November 22, 2019 at 6:35 pm

    I like his desktop, what is his OS? and theme ?



  2. Abu Reza on November 22, 2019 at 6:38 pm

    Look at – (1) `Picture of Dragon (Satanic Pic) in his Laptop , (2) software’s name is `Darknet’ , (3) The circle is similar to Illuminatic, (4) All are in red color …………. it is not a coincidence



  3. Spaken on November 22, 2019 at 6:39 pm

    The terminators will definitely use some version of his code



  4. matuopm on November 22, 2019 at 6:40 pm

    sound is broken somehow



  5. Faheem Rehman on November 22, 2019 at 6:40 pm

    what if we want to target only one particular person and ignoring others???



  6. Swapnil Parmar on November 22, 2019 at 6:44 pm

    awesome…!!!!



  7. Brindha Senthilkumar on November 22, 2019 at 6:44 pm

    Wonderful explanation. The computer vision is one of the great challenge in Robotics and anonymous vehicles, this algorithm will act most appropriate like the biological model vision. It is going to strive its effort in Pathology domain as well…



  8. HSU 徐TE-JUI 得瑞 on November 22, 2019 at 6:45 pm

    amazing



  9. Root Sharp on November 22, 2019 at 6:46 pm

    Finally a Ted talk actually works for something. Thank you local Thor. We appreciate technology.



  10. Anand Uikey on November 22, 2019 at 6:46 pm

    More video show me please send me link your videos



  11. Habibullah mayar on November 22, 2019 at 6:46 pm

    I love it great



  12. Devanshu Sachdev on November 22, 2019 at 6:47 pm

    Mind blowing!



  13. Roman Pfneudl on November 22, 2019 at 6:47 pm

    Oh damn – it sort of pains me to see how people (the audience) struggle to see the awesomeness and achievement of this person. He probably could have lit a fart for more total applause.



  14. David d on November 22, 2019 at 6:50 pm

    This looks like mostly bullshit and is bullshit. How the f**k is he processing things so quickly on a normal pc.



  15. Aye Chan Aung Thwin on November 22, 2019 at 6:51 pm

    I was looking for the Genius and I found the Alien.



  16. Murtuja Shahmadar on November 22, 2019 at 6:51 pm

    Here, We discuss about the Google’s awesome feature called Google Colab, Google Colaboratory and Colab Notebook. We give you information about What is Google Colab ? and also discuss the What is Google Colaboratory Notebook ?
    https://www.techfoul.com/2019/10/google-colab-what-is-google.html



  17. patham9 on November 22, 2019 at 6:51 pm

    And yet the computer still can’t tell the difference between a cat and a dog without having been trained on the specific differences to express beforehand, meaning the misleading example that motivated the talk still doesn’t work. Else, a good talk.



  18. Milandu Keith Moussavou Boussougou on November 22, 2019 at 6:53 pm

    Does any one knows if the source code is open source?



  19. Big Mac on November 22, 2019 at 6:53 pm

    Computers do not recognise instantly the recognise at the speed of the processor



  20. Hsiang-Yeh Hwang on November 22, 2019 at 6:54 pm

    Nice!!!!!!!!



  21. ҉K҉N҉I҉G҉H҉T҉F҉I҉R҉E҉6҉6҉ on November 22, 2019 at 6:54 pm

    i am not sure if its save to be opensource…



  22. Suleyman Natsir on November 22, 2019 at 7:00 pm

    how can we access the darknet technology ?



  23. nosense on November 22, 2019 at 7:00 pm

    not sure if darknet is the best name



  24. imshafay on November 22, 2019 at 7:03 pm

    Anyone who can post the link for the github code ?



  25. EasyBreadToast on November 22, 2019 at 7:04 pm

    Youtube recognized me for watchimg related videos like these.



  26. Stephen M on November 22, 2019 at 7:04 pm

    Easier to stalk your crush now – what a time to be alive.



  27. Ayush ShaZz on November 22, 2019 at 7:05 pm

    I did not find answer for " How computers learn to recognise objects instantly " in the whole video … Just saw recognising objects instantly !!!!



  28. Marshall Redmon on November 22, 2019 at 7:07 pm

    Wow….. me and this guy has the same last name



  29. NinjaOnANinja on November 22, 2019 at 7:08 pm

    This is how America should be with everything, just, I created this, here you go. But instead we got a bunch of greedy bastards holding the world back trying to make money on a good idea and if they never get what they want, the world loses in the tech.

    That is the kind of mind set that is dooming society. What they have done here is created something and let anyone have access so they can now create even more. That is what we need.



  30. Nicholas Pitti on November 22, 2019 at 7:11 pm

    5:45 on m’laptop



  31. XxM1THRAND1RxX on November 22, 2019 at 7:11 pm

    I’m still waiting for the explanation of how computers learn to recognize objects.



  32. JEEN Bhawani's Channels on November 22, 2019 at 7:11 pm

    Highly appreciable work by this dude..
    Bro you daknet is so sophesticated and you open sourced it….you are a hero



  33. suraj singh on November 22, 2019 at 7:12 pm

    5:42 parrot as a teddy bear



  34. Pearl * Tears on November 22, 2019 at 7:15 pm

    why do i get the feeling that all those times i had to prove i wasnt a Robot……
    and then haveing to choose all the boxes with a picture of some kind of objects but only choose the boxes containing the 1 object…..

    wow would you look at that….instead of having to Pay Someone or Instead of doing the Hours them selves and having to Run the programming of it over and over them selves by teaching the computer how and what to focus on…..

    they had us do it for them….FOR FREE

    the outcome this technology……



  35. Jayesh Kanodia on November 22, 2019 at 7:16 pm

    only one question: How computers learn to recognize objects instantly?



  36. Blake Edwards on November 22, 2019 at 7:17 pm

    Amazing! Thank you for open sourcing this. I will be using it as a part of my smart dorm room project I am building !



  37. Raja Haseeb on November 22, 2019 at 7:20 pm

    can we recognize faces with that technique?



  38. グエンクアン on November 22, 2019 at 7:21 pm

    I thought he is going to explain about cnn.



  39. Amit Kharel on November 22, 2019 at 7:21 pm

    Watch it’s final result by me:
    https://youtu.be/F8-6kqiT0ps
    (TUTORIAL SOON)



  40. George Pipis on November 22, 2019 at 7:25 pm

    You can have a look at an example here:
    https://predictivehacks.com/object-detection-with-yolo/



  41. Christakxst on November 22, 2019 at 7:25 pm

    So great that darknet comes with an open source licence !!



  42. Fernando Galetto on November 22, 2019 at 7:25 pm

    I loved this demonstration, thanks for creating YOLO, i have done a project using YOLO to detect 3 classes (person, hat, vest), the idea is to use it to detect wether the workiers on construction sites are wearing appropiate PPEs or not. i trained it with a custom dataset and is running on a Raspberry PI with an Intel NCS2, you can see my results here: https://youtu.be/rFMc3FNQFL4



  43. federico sananes on November 22, 2019 at 7:25 pm

    for a second it thought he had an invisible skateboard but I like darknet all the same.



  44. Keval Rajpal on November 22, 2019 at 7:26 pm

    wonderful work👏👏👏👏



  45. Lalit Kumawat on November 22, 2019 at 7:28 pm

    Can I get the link for the code ..



  46. Bar Kazzaz on November 22, 2019 at 7:28 pm

    How can anyone like this video?
    Did you get an answer? This is just an ad for a very poorly named company…



  47. Isuru Nanayakkara on November 22, 2019 at 7:28 pm

    Dude, I want that red, hellish interface ‘theme’ or whatever. What’s it called?



  48. NAME494 on November 22, 2019 at 7:29 pm

    3:22 skateboard lol



  49. Manu Vi on November 22, 2019 at 7:33 pm

    UW!!!!!!!



  50. NinjaOnANinja on November 22, 2019 at 7:33 pm

    Computers don’t learn to recognize things instantly. The title is misleading. They teach the computer to recognize things and it just recognizes them. But if you took the stop sign and altered it, it wouldn’t recognize it. That is because it isn’t learning, it is programmed. It isn’t AI. AI would be able to know it is a stop sign even when it looks nothing like one, just as an example.