From the course: Introduction to Deep Learning with OpenCV
Join today to access over 24,700 courses taught by industry experts.
YOLOv3 - OpenCV Tutorial
From the course: Introduction to Deep Learning with OpenCV
YOLOv3
- [Instructor] YOLOv3 is a popular object detection algorithm. YOLO stands for You Only Look Once. In the past, detection algorithms apply the model to an image at multiple locations and scales. Highest scoring regions on the image were flagged as potential detections. YOLOv3 does things a bit differently. The neural network divides the image into regions and predicts bounding boxes and probabilities for each region. The network only needs to view the image one time, and then the bounding boxes are weighted by the predictive probabilities. We can set thresholds. So let's say we set it at 80%. Then, only if the YOLO algorithm is more than 80% sure that it has detected a dog, for example, will it draw a bounding box around it. I've taken most of this code from the OpenCV implementation of YOLO three, available on GitHub. Let's take a look at the YOLOv3 folder to understand some of the components. So YOLOv3 has been trained on the COCO dataset, which has 80 different classes of objects…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
