Summary
Keywords
Full Transcript
Building a complete computer vision pipeline involves more than just training a model; it’s about managing every step from raw data to deployment. In this tutorial, we’ll walk through the full workflow using Ultralytics YOLO11, covering everything from converting video to frames and annotating data to training, improving accuracy, and running real-time tracking. You’ll learn how to annotate datasets in Ultralytics YOLO format using LabelImg, create a proper dataset YAML configuration, and train your YOLO11 model on a logistics dataset. Finally, we’ll demonstrate object tracking with the trained model and discuss how these steps fit together to build efficient, production-ready vision systems. Ideal for developers, data scientists, and AI engineers aiming to master the end-to-end computer vision process, from data preparation to model evaluation and real-world inference. Chapters: 00:00 - Introduction to the computer vision pipeline 00:27 - Converting raw video to frames for annotation 01:49 - Installing and configuring the labelImg annotation tool 03:30 - Annotating data in YOLO format using labelImg 04:48 - Creating the dataset YAML file for model training 06:28 - Training the YOLO11 model on the logistics dataset 10:22 - Running object tracking with the detection model 11:14 - Conclusion and key takeaways 🔗 Logistics dataset ➡️ https://drive.google.com/file/d/1ePwbU-TpWbbuhzEAzPPbyIaBuAJNP1gn/view?usp=drive_link 🔗 Explore computer vision pipeline ➡️ https://docs.ultralytics.com/guides/steps-of-a-cv-project/ Ultralytics Resources: 🏢 About Us: https://ultralytics.com/about 💼 Join Our Team: https://ultralytics.com/work 📞 Contact Us: https://ultralytics.com/contact 💬 Discord Community: https://discord.com/invite/ultralytics 📄 Ultralytics License: https://ultralytics.com/license #computervision #yolo11 #ultralytics #objectdetection #dataannotation #machinelearning
Continue this lesson in the app
Install CourseHive on Android or iOS to keep learning while you move.
