Course Outline
Introduction to Computer Vision in Autonomous Driving <\/p>
- The role of computer vision in autonomous vehicle systems <\/li>
- Challenges and solutions in real-time vision processing <\/li>
-
Key concepts: object detection, tracking, and scene understanding
<\/li>
<\/ul>
Image Processing Fundamentals for Autonomous Vehicles <\/p>
- Image acquisition from cameras and sensors <\/li>
- Basic operations: filtering, edge detection, and transformations <\/li>
-
Preprocessing pipelines for real-time vision tasks
<\/li>
<\/ul>
Object Detection and Classification <\/p>
- Feature extraction using SIFT, SURF, and ORB <\/li>
- Classical detection algorithms: HOG and Haar cascades <\/li>
-
Deep learning approaches: CNNs, YOLO, and SSD
<\/li>
<\/ul>
Lane and Road Marking Detection <\/p>
- Hough Transform for line and curve detection <\/li>
- Region of interest (ROI) extraction for lane marking <\/li>
-
Implementing lane detection using OpenCV and TensorFlow
<\/li>
<\/ul>
Semantic Segmentation for Scene Understanding <\/p>
- Understanding semantic segmentation in autonomous driving <\/li>
- Deep learning techniques: FCN, U-Net, and DeepLab <\/li>
-
Real-time segmentation using deep neural networks
<\/li>
<\/ul>
Obstacle and Pedestrian Detection <\/p>
- Real-time object detection with YOLO and Faster R-CNN <\/li>
- Multi-object tracking with SORT and DeepSORT <\/li>
-
Pedestrian recognition using HOG and deep learning models
<\/li>
<\/ul>
Sensor Fusion for Enhanced Perception <\/p>
- Combining vision data with LiDAR and RADAR <\/li>
- Kalman filtering and particle filtering for data integration <\/li>
-
Improving perception accuracy with sensor fusion techniques
<\/li>
<\/ul>
Evaluation and Testing of Vision Systems <\/p>
- Benchmarking vision models with automotive datasets <\/li>
- Real-time performance evaluation and optimization <\/li>
-
Implementing a vision pipeline for autonomous driving simulation
<\/li>
<\/ul>
Case Studies and Real-World Applications <\/p>
- Analyzing successful vision systems in autonomous cars <\/li>
- Project: Implementing a lane and obstacle detection pipeline <\/li>
-
Discussion: Future trends in automotive computer vision
<\/li>
<\/ul>
Summary and Next Steps <\/p>
Requirements
- Proficiency in Python programming <\/li>
- Foundational understanding of machine learning concepts <\/li>
-
Familiarity with image processing techniques
<\/li>
<\/ul>
Target Audience<\/strong> <\/p>
- AI developers working on autonomous driving applications <\/li>
- Computer vision engineers focusing on real-time perception <\/li>
- Researchers and developers interested in automotive AI <\/li> <\/ul>
Custom Corporate Training
Training solutions designed exclusively for businesses.
- Customized Content: We adapt the syllabus and practical exercises to the real goals and needs of your project.
- Flexible Schedule: Dates and times adapted to your team's agenda.
- Format: Online (live), In-company (at your offices), or Hybrid.
Price per private group, online live training, starting from 4800 € + VAT*
Contact us for an exact quote and to hear our latest promotions
Testimonials (1)
Hands on and the practical
