Register for the Workshop
Date and Time
April 26, 2025 from 9:30 AM to 3:00 PM
Location
The Workshop will take place at MotionLab.Berlin, Bouchéstraße 12/Halle 20 in Berlin
Workshop Overview
This interactive workshop will guide participants through implementing computer vision techniques for autonomous driving applications. Attendees will gain practical experience working with Voxel51’s open source tools to analyze and understand the challenges in autonomous driving using the BDD100K dataset from Berkeley DeepDrive.
Bring your laptop and enthusiasm, food and drinks will be provided.
What You’ll Learn
- Fundamentals of computer vision for autonomous driving
- Exploring the BDD100K dataset and its diverse driving scenarios
- Implementing zero-shot classification for object recognition
- Working with YOLO variants for real-time object detection
- Extracting precise localization information with instance and panoptic segmentation algorithms
- Using image embeddings to extract meaningful insights from driving data
- Understanding key challenges in autonomous driving systems
Hands-On Activities
Participants will work through practical exercises using Python and Voxel51’s open-source tools to:
- Process and analyze driving imagery from diverse conditions
- Implement zero-shot classification for novel object detection
- Compare performance of different YOLO variants on autonomous driving data
- Build embeddings-based pipelines for scene understanding
- Explore approaches to handling edge cases in autonomous driving scenarios
Prerequisites
- Basic Python programming experience
- Familiarity with machine learning concepts
- Laptop with Python environment installed (setup instructions will be provided)
About the Instructors
Paula Ramos, PhD is a Senior Developer Relations Specialist at Voxel51. She specializes in helping developers implement effective computer vision solutions for autonomous systems and building a community around open-source computer vision tools.
Antonio Rueda-Toicen is an AI Engineer at Voxel51. He focuses on bridging the gap between cutting-edge computer vision research and practical autonomous driving implementations, creating accessible pathways for developers to leverage Voxel51’s technologies.
