Видео

lol

I actually have 4 classes: neutral, rest, gripping, carrying, but in the results I labelled them down to only 2 classes, grasped (carrying, gripping) and not grasped (neutral, rest). It is recommended for you to train your custom datasets for your application because this approach is very likely to depend on the angle, point of view. That way you can be very customizable, and you can detect 2 hands as well, since mine demo only detect 1 hand at a time, it may limit your goal. But the same code with a bit of modifications based on your total number of classes, what you labelled them can be used for multiple classes with moving hands.

@@thieulong0612 ok thanx alot

Yes I used the landmarks from Mediapipe

@@thieulong0612 well done

@@avivlohiet9839 thank you 🥰

We are making a smart surveillance system. So, we are about to use media pipe. I want to know can we detect a fight using media pipe. Utilizing the solutions being provided in media pipe, such as face detection , hand tracking , and pose estimation.

@@Abubakar-id4cx yes you can do that with Mediapipe to extract the pose and a neural network to learn and classify the behaviors

Em xem thu qua repo nay nha: github.com/thieulong/LSTM-Actions-Recognition/tree/main, anh moi update lai code voi co viet instructions a.

Hello, please check out this repo here: github.com/thieulong/LSTM-Actions-Recognition/tree/main. Very sorry for the late reply

Hello, please check out this updated Github here: github.com/thieulong/LSTM-Actions-Recognition/tree/main, I've fix a few issues and updated the scripts, I also put instructions there. Sorry for my late reply.

hey, I am having problems while running the code.....can you please help?

Hello, thank you for asking. I've updated the requirements.txt file in this repo here: github.com/thieulong/LSTM-Actions-Recognition/tree/main

Hey, feel free to contact me on WhatsApp (wa.me/+61414880612) or Telegram (t.me/thieulong) I’m happy to help 🤗

@@thieulong0612 could you also explain how we can run the code,please?

Hi Madhavi, I just use 2 mini servos SG90 9G to open & close the windows.

@@thieulong0612 Ok Thanks

Xin lỗi vì đã để bạn đợi nha do mình không hay hoạt động RUclips lắm, đây là code của project ở trên đây bạn: github.com/thieulong/Violence-Detection.git

Mấy cái này anh tự học thui à em

Anh bên CS ấy em, môn này không khó lắm đâu em đừng lo.

@@thieulong0612 em cũng học com sci, em còn 2 tuần nx em qua mel rùi, mà em chưa bik major IoT, data science v robotics, em khum bik nên chọn cái nào

github.com/thieulong/Violence-Detection.git

github.com/thieulong/Smart-Parking-System.git here it is, sorry I didn't check the RUclips notification regularly.

@@thieulong0612 is there anyway to contact u.... To clear some doubts

@@footballer_18 yea sure do you have whatsapp or facebook or something? We can have a chat

Can u give ur insta handle or Facebook??

Oh yes here: github.com/thieulong/RPI-Pan-Tilt Very sorry for my late response

It's called "Green light, red light". Based on a Korean movie "Squid game", the robot will detect whether the person in it's vision is moving or not, if the they're moving, they'll be eliminated from the game. (you can watch more here ruclips.net/video/nrchfeybHmw/видео.html&ab_channel=SquidGame)