Object Tracking with YOLOv5 and DeepSORT in OpenCV

preview_player
Показать описание

You will also get access to all the technical courses inside the program, also the ones I plan to make in the future! Check out the technical courses below 👇

_____________________________________________________________

In this video 📝 we are going to take a look at how to do easy object tracking with YOLOv5 and DeepSORT in OpenCV. First of all, we need to detect the objects, set up our tracker with the Kalman filter, and then we can do tracking on live webcam in OpenCV. In the end, we will see the results for the tracked objects.

If you enjoyed this video, be sure to press the 👍 button so that I know what content you guys like to see.

_____________________________________________________________

_____________________________________________________________

_____________________________________________________________

📞 Connect with Me:

_____________________________________________________________

🎮 My Gear (Affiliate links):
🖥️ Desktop PC:

_____________________________________________________________

Tags:
#ObjectTracking #OpenCV #ComputerVision
Рекомендации по теме
Комментарии
Автор

Join My AI Career Program
Enroll in My School and Technical Courses

NicolaiAI
Автор

Hi, I checked your github link but can't see files from this video. Hope you'll update it sooner as it would be very helpful. Thanks

oxusss
Автор

great video, the only problem I find is that model only detects single class object, even though I have removed "if == 'person'" condition.

sanskar_choudhary
Автор

Hi, thank you for the tutorial. Also could you please explain why you say it tracks nicely, but at the same time it loses object id (eg in first demo with you in frames) and gives a new id at pretty not hard conditions- just you in front of the camera. Just wanted to clarify this moment, thank you

alexandershim
Автор

Can we apply deepsort with merging a 3 cam feed.?

Inspired_insights
Автор

The yolo detector works on every frame, which is an expensive operation. How to skip some frames so that yolo can only be used for focusing later and tracking works on raw frames?

kamnsv
Автор

I am doing every thing exaclyt like you, however I am having this problem. ValueError: shapes (3, 1280, 3) and (3, 1280, 4) not aligned: 3 (dim 2) != 1280 (dim 1). Does anyone know why ? Apparently I detecting more track objects with deep sort than Yolo detection.

goncalomesquita
Автор

Hi great video, where can i get this code?

arielgonzalez
Автор

can you post a link to the video where you set up the yolodetector class please?

kiloani
Автор

Hi great video, is there a specific reason why you didn't use Yolov7 for this?

thiviruperera
Автор

Great video! does this kind of object tracking make it possible to detect the height and width of 3d objects - vehicles specifically?

thomasward
Автор

Loved the video but unable to find the py file in your github

vineetkumarmishra
Автор

the id changes even the object stills in scene byt little move

science.
Автор

how to load video src from webrct streaming

majacode
Автор

Hi great video, where can i get this code?

lizmathews