Udemyallen

Computer Vision Bootcamp with Python (OpenCV) - YOLO, SSD

Learn object detection & tracking! Master face detection, R-CNN, YOLO, SSD, and advanced tracking algorithms (DeepSORT, ByteTrack). Includes vehicle counting.

4.4(237)
2,326students
13h 42m
Certificate
Holczer Balazs
Holczer BalazsSoftware Engineer

Course Content

Computer Vision Bootcamp with Python (OpenCV) - YOLO, SSD is an all-levels Udemy course taught by Holczer Balazs. It runs 13h 42m, is taught in English, and includes a certificate of completion. Learners rate it 4.4 out of 5 from 237 reviews, with 2,326 students enrolled. It is a paid course, last updated February 2025.

Explore the fundamentals of image processing and dive into cutting-edge computer vision techniques in this comprehensive course. You'll gain practical skills in face detection and object detection, essential for a wide range of applications, from software engineering to forensic analysis. Discover how these powerful learning algorithms are revolutionizing fields like self-driving cars, where lane detection is a critical component.

The course leverages the power of deep learning and GPUs to enable real-time video processing. Here's a detailed look at what you'll learn:

  • Image Processing Fundamentals: Build a strong foundation in computer vision theory. Understand pixel intensity values, convolution and kernels (including blur kernels and sharpen kernels), and edge detection using edge detection kernels.
  • Self-Driving Cars & Lane Detection: Learn how computer vision approaches are applied to lane detection. Master Canny's algorithm and the Hough transform for line detection based on pixel intensities.
  • Face Detection with Viola-Jones Algorithm: Explore the Viola-Jones approach for robust face detection in images and videos using the sliding-windows approach.
  • Histogram of Oriented Gradients (HOG) Algorithm: Discover how to improve upon the Viola-Jones algorithm using HOG to detect gradients and edges. Learn to construct histograms of oriented gradients and utilize support vector machines (SVMs) for classification.
  • Convolutional Neural Networks (CNNs) Based Approaches: Understand the limitations of the sliding-windows approach and explore region proposals and selective search algorithms. Delve into region-based convolutional neural networks (R-CNNs), fast R-CNNs, and faster R-CNNs.
  • You Only Look Once (YOLO) Object Detection Algorithm: Learn the YOLO approach for real-time object detection. Master constructing bounding boxes, the intersection over union (IOU) algorithm, and non-max suppression for refining detections. Includes implementation of YOLO with images and videos and training YOLO with custom datasets.
  • Single Shot MultiBox Detector (SSD) Object Detection Algorithm: Explore the SSD algorithm, focusing on constructing anchor boxes and utilizing VGG16 and MobileNet architectures. Implement SSD for real-time video processing.
  • Object Tracking Algorithms: Implement advanced object tracking algorithms including DeepSORT, ByteTrack, BoTSORT. Learn to implement a vehicle counting algorithm.

Throughout the course, we'll cover the theoretical background of face recognition algorithms and object detection before moving on to practical, step-by-step implementations.

Ready to unlock the power of computer vision? Let's begin!

$ whoami — the devs behind tutorialsearch.io

Want AI in your product? Hire the team behind TutorialSearch.io

LLM features, RAG, agents and automation wired into a real product — built by the devs who shipped this site.

5.0(913)
1h 8m
intermediate
skillshare
skillshare
5.0
29m
beginner
pluralsight
5.0(51)
1h 24m
beginner
skillshare