10 Image/Video-Based Apps

In this chapter, we will introduce both image labeler and video labeler apps to facilitate the process of image and video labeling. The user can then use such labeled images or videos in his/her training of network classification and regression using CNNs, like: R-CNN, Fast R-CNN, Faster R-CNN, and YOLO. For automated image and video labeling, we can use either built-in or custom automation algorithms. We can synchronize ground truth objects with other time series sensors, like LiDAR or Radar. We can use labeled data outside MATLAB environment, as well. We will also introduce the application called Experiment Manager which is basically used to carry out parametric optimization for a given training network model in one place with the flexibility to see the model goodness results in the form of plots and tables upon completion of simulation trials.

Image Labeler (IL) App

Quoted from offline MATLAB help, the Image Labeler app enables us to label ground truth data in a collection of images. Using the app, we can:

  • Define rectangular regions of interest (ROI) labels, polyline ROI labels, pixel ROI labels, polygon ROI labels, and scene labels. We use these labels to interactively label our ground truth data.
  • Use built-in detection or tracking algorithms to label our ground truth data.
  • Write, import, and use our own custom automation algorithm to automatically label ground truth. See Create Automation Algorithm for Labeling.
  • Evaluate the performance of ...

Get Machine and Deep Learning Using MATLAB now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.