DSC Conference Tutorials Day 2
In preparation for the DSC Conference we were offered 2 days of online webinar-style tutorials. On the second day i started off with a webinar about :
Object detection using OpenCV
Object Detection is The mix of classification (recognizing it is a cat) and localisation (seeing where on the image the cat is).
In this tutorial we explored the applications of object detection, going from turning on a light only when a person approaches (instead of whenever anything moves) to detecting road signalisation and traffic lights in self-driving cars.
We also explored many different methods used in object detection such as :
- R-CNN (Region-based Convolutional Neural Networks)
- Fast R-CNN
- Faster R-CNN
- YOLO (You Only Look Once)
- SSD (Single Shot Detector)
- RetinaNet
- Mask R-CNN
- Cascade R-CNN
- CenterNet
- EfficientDet
Then we dove deeper into OpenCV, a library of programming functions mainly aimed at real-time computer vision. We explored the different methods of object detection in OpenCV and how to use them :
- Haar Cascade
- Template Matching
- Feature Matching
- Contour Detection
And we finally tested out an application that detects faces, mouths and eyes in a picture.
Augmented Reality - ARKit framework showcase
This second tutorial was more of a showcase of the ARKit framework for iOS, where the presenter showed us his code line by line and gave a general explanation each time. The showcase was an application that detected your face and applied a mask on it, with the mask following your face movements.