FTLinuxCourse - Tin tổng hợp mới nhất không thể bỏ lỡ
  • Home
  • Lập Trình Linux
  • Công Nghệ
  • Máy Tính
No Result
View All Result
  • Home
  • Lập Trình Linux
  • Công Nghệ
  • Máy Tính
No Result
View All Result
FTLinuxCourse - Tin tổng hợp mới nhất không thể bỏ lỡ
No Result
View All Result

How computers learn to recognize objects instantly | Joseph Redmon

admin by admin
April 7, 2020
in Lập Trình Linux
37
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:

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:
Like TED on Facebook:

Subscribe to our channel:

Nguồn: https://ftlinuxcourse.com

Xem thêm bài viết khác: https://ftlinuxcourse.com/tin-tuc-ve-linux

Xem thêm Bài Viết:

  • Trải nghiệm mới hay ho với hướng dẫn cài Mac Os trên vmware
  • Bật mí cách cài đặt ssl miễn phí lên Let’s Encrypt
  • Tuyệt chiêu tạo usb boot kali linux đơn giản dành cho bạn
  • Hướng dẫn chi tiết từ A – Z các bước cài đặt Python trên Windows 10
  • Bật mí quy trình cài đặt Kali Linux trên Vmware đúng chuẩn và chi tiết
Tags: Youtube
Previous Post

THỰC HIỆN CHỈ THỊ 16 CỦA THỦ TƯỚNG CHÍNH PHỦ: NHIỀU NGƯỜI DÂN VẪN CHỦ QUAN, THIẾU Ý THỨC

Next Post

Quản lý phần cứng Linux | Linux Tutorial | Trần Văn Bình | Oracle DBA AZ

Next Post
Quản lý phần cứng Linux | Linux Tutorial | Trần Văn Bình | Oracle DBA AZ

Quản lý phần cứng Linux | Linux Tutorial | Trần Văn Bình | Oracle DBA AZ

Comments 37

  1. Dhiraj singh says:
    3 years ago

    Want to know more

    Reply
  2. Souvik Das says:
    3 years ago

    What's the second detection algorithm that he executed? Is that Fast RCNN?

    Reply
  3. Adham Saheb says:
    3 years ago

    Does anyone know how it was ran on a phone ?

    Reply
  4. Emad Boctor says:
    3 years ago

    Image annotation interface(for object detection) check https://github.com/emadboctorx/labelpix

    Reply
  5. Swagatam Guha says:
    3 years ago

    hello. how this system works ?

    Reply
  6. dumbcreaknuller says:
    3 years ago

    still doesn't solve the unsupervised learning problem because if you solved unsupervised learning, you would not need to pretrain any object at all, instead the program could just figure out on its own how to classify what object based on information alone from the outside having nothing to build on to begin with other than the method of the learning algorithms itself. example, what if i wanted to make the network recognize sound or words at the same time as detecting people and animals. what if i wanted to make the program think that the sound it heard was directly related to a portion of the screen and treat that portion as a separate object until the program had done this same process over and over and over making different version of part of the screen as that particular object until it can tell background from actual object. it means the program must find part of a image to be more of one object that other parts where each versions of this audio based guess of graphics narrow down what a object is as a separate object discarding what is not a object or another object from what its previous version was thinking was the object of iterest. let say a program just make a section of the image a cut based on aproximity and angle and start learning what ever pattern in it and decides its a dog even it could be part of a table or bed at the same time but over time of repetition is able to separate the real dog from other objects. what i means is what if you just start by training in junk with certain keywords of jumble and try to make the network over time detect real objects and classify real names to them by guessing. this way, you chould be able to make unsupervised learning work. just think of how a child think the name dog is spelled dol and over time learning its spelled dog. anyway if such a system like yolo could have incorporated somthing like i suggest, it could have a real advantage of realtime tracking of what at first will be detected junk and classified jumble. this way, you don''t need to pretrain any data but let it train itself over time or teach itself over time. what it would do would be like a human getting everything wrong at first past the baby stage and then become more and more human as it learns. i hope there is some real superintelligent human out there that want to make a unsupervised version of yolo that stated out as a complete idiot of a program and over time become very acurate in predicting what object is what, and with what name.

    Reply
  7. Godwin George says:
    3 years ago

    This is really great, but i had some installation issues while installing darkflow in my laptop.
    Any one who know this willing to help me?

    Reply
  8. ismail oujaa says:
    3 years ago

    جيد جدا

    Reply
  9. Sarvagya Mamgain says:
    3 years ago

    can someone tell When I train YOLO for custom detection via my own dataset, it is again and again giving error that "STB Reason : Could not fopen" to the image path stored on Training line being exectuted

    Reply
  10. Tapa says:
    3 years ago

    Now you can do this in 3 lines of code. Jeez, how far we come in 3 years

    Reply
  11. Oussa bly says:
    3 years ago

    where can I get the maven dependency please if useable for java…

    Reply
  12. ETechno Tricks says:
    3 years ago

    watch these interesting video about Face recognition,,
    watch these interesting video about Face recognition,,

    https://www,youtube.com/watch?v=5JtDSi4FUPQ&t=42s

    Reply
  13. norkator says:
    3 years ago

    I'm using Yolo v3 on security camera application. Yolo is perfect for sorting as example cars and people fast with slower hardware. Then you can use other specific algorithms to do other detection's from these sorted objects like car -> license plates, people -> faces (train model to detect persons). Yes it's making mistakes but this computer vision is not nothing simple. This video doesn't answer any questions -> better start from their paper: https://pjreddie.com/media/files/papers/YOLOv3.pdf

    Reply
  14. Uthael Killeanea says:
    3 years ago

    4:11 and 15s after that is the closest to "HOW computers learn…"
    I hoped for more details when I clicked on this.

    Reply
  15. Robert Antonio says:
    3 years ago

    I usually dont do this but i recommend cyberspaceintelligence@gmail.com or hackgoodness on instagram for any phone spying or gps tracking services. with their help , I was able to spy on my wifes phone to see alll her text messages, phone calls, facebook messenger chats, whatsapp chats and more! they were able to install my iphone 8 as the mirror phone so i was viewing everything remotely without stress! just contact cyberspaceintelligence@gmail.com or hackgoodness on instagram for help

    Reply
  16. WOOSAL says:
    3 years ago

    What is his distro?

    Reply
  17. Genomul Uman says:
    3 years ago

    I like it how all maniacs use misleading examples like "self driven cars" instead of just stating the truth: we need this kind of technology for instant face recognition for mass surveillance. Good job "Washington University graduates" from all over the world!

    Reply
  18. Akira says:
    3 years ago

    maybe they should put someone else in charge to name things

    Reply
  19. Classix says:
    3 years ago

    3:22 skateboard

    Reply
  20. Feralz says:
    3 years ago

    hooman detected. must kill. hooman.

    Reply
  21. Nogardtist says:
    3 years ago

    i wonder why kinect died
    and youtube AI gets more weapons

    Reply
  22. Reuben M.D. says:
    3 years ago

    3:22 Computer thinks there's a skateboard there 🙂

    Reply
  23. Eric Adair says:
    3 years ago

    point it out some mmore 2 late yet ?

    Reply
  24. movax20h says:
    3 years ago

    A stop sign is a freisbee. A parot is a person. Detects backpack where there is not a backpack. Pretty good, but I wonder how current state of the art systems perform.

    Reply
  25. Feldenkrais with Alfons says:
    3 years ago

    "thanks for putting this into the public domain free for anyone to use" – China.

    Reply
  26. LifeInTags says:
    3 years ago

    Where can I download this application?

    Reply
  27. Jonathan Lutz says:
    3 years ago

    – Doctor: Let's try this in the body
    – AI: I found a suitcase

    I'm joking, very good work ! Thank you

    Reply
  28. Vlad Gidea says:
    3 years ago

    Asta-i Bara?

    Reply
  29. luit meinen says:
    3 years ago

    Of course this is really amazing, but I do find it funny that at certain points the system thought a parrot was a pizza, a stop sin was a frisbee and a tripod was skis :p

    Reply
  30. Ola Østbyhaug says:
    3 years ago

    hold da phone, is that obama?

    Reply
  31. Ítalo de Pontes Oliveira says:
    3 years ago

    3:10 detect "remote" in the arm

    Reply
  32. Manos Chalvatzopoulos says:
    3 years ago

    he went fullmetal alchemist on his presentation

    Reply
  33. x X _ K J C O M P U T Ξ R _ X x says:
    3 years ago

    3:22 it said skateboard

    Reply
  34. Angery Angery says:
    3 years ago

    5:42 Parrots are now Teddy Bears. Change my mind because you cant

    Reply
  35. SumriseHD says:
    3 years ago

    This audience is so horrible.. urgh…

    Reply
  36. Chad Thaddeus says:
    3 years ago

    China took it and built an advanced facial recognition system. Thanks, Darknet!

    Reply
  37. Piotr Adamowicz says:
    3 years ago

    Spends 7 minutes, never actually says how they work, except that his works well . I want my 7 minutes back.

    Reply

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Xem Thêm

Những điều bạn có thể chưa biết về Thánh sim Hi Vietnamobile

Những điều bạn có thể chưa biết về Thánh sim Hi Vietnamobile

January 17, 2021
Xiaomi Mi 10 Pro thiết kế thời thương, màn hình cong ấn tượng

Xiaomi Mi 10 Pro thiết kế thời thương, màn hình cong ấn tượng

June 1, 2021
Địa chỉ in bao bì nhựa tại Đà Nẵng chiết khấu cao

Địa chỉ in bao bì nhựa tại Đà Nẵng chiết khấu cao

January 26, 2021
Địa chỉ bán đèn tuýp LED Philips uy tín và chất lượng trên thị trường?

Bán đèn tuýp led Philips – Skyled

July 27, 2020
Lựa chọn chủ đề in áo thun phù hợp

Lựa chọn dịch vụ in áo thun cotton cần lưu ý gì?

August 2, 2020
Cần xác định được điểm đặt pallet cao nhất để mua xe

Bí quyết chọn mua xe nâng điện đẩy tay

August 3, 2020

Về Chúng Tôi

Báo ftlinuxcourse.com 24h – Đón xem những tin tức mới nhất về tình hình chính trị, xã hội, an ninh trật tự, văn hóa – giải trí, thể thao, thông tin trong ngày.

  • Liên Hệ
  • Chính Sách Bảo Mật

© 2023 JNews - Premium WordPress news & magazine theme by Jegtheme.

No Result
View All Result
  • Home
  • Lập Trình Linux
  • Công Nghệ
  • Máy Tính

© 2023 JNews - Premium WordPress news & magazine theme by Jegtheme.