1 / 20

Computer Vision Scene Classification Using Neural Nets and a Knowledge Base

Computer Vision Scene Classification Using Neural Nets and a Knowledge Base. Daniel Vevang. Object Detection. Object Detection. Object Detection Training. Object Detection. Object Detection Training. Positive Samples. Object Detection. Object Detection Training. Positive Samples.

oral
Télécharger la présentation

Computer Vision Scene Classification Using Neural Nets and a Knowledge Base

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Computer Vision Scene Classification Using Neural Nets and a Knowledge Base Daniel Vevang

  2. Object Detection

  3. Object Detection Object Detection Training

  4. Object Detection Object Detection Training Positive Samples

  5. Object Detection Object Detection Training Positive Samples Negative Samples

  6. Object Detection Object Detection Training Positive Samples Negative Samples Vector Data

  7. Object Detection Object Detection Training Positive Samples Negative Samples Vector Data XML Haarcascade tree

  8. Object Detection Object Detection Training Positive Samples Negative Samples Vector Data XML Haarcascade tree OpenCV Output: Object location and scale from an image.

  9. Object Detection Data: location and scale Scene Detection

  10. Object Detection Data: location and scale Kohonen Network Scene Detection Scene Detection

  11. Object Detection Data: location and scale NN Training Input and Output Data Kohonen Network Scene Detection Scene Detection

  12. Object Detection Data: location and scale NN Training Input and Output Data Trained Kohonen Net Kohonen Network Scene Detection Scene Detection

  13. Object Detection Data: location and scale NN Training Input and Output Data Trained Kohonen Net Kohonen Network Scene Detection Knowledge Base Scene Detection

  14. Tools: OpenCV • Diverse set of computer vision tools

  15. Objectmarker • GUI for Creating a text file of bounding box coordinates for a database of images • Additional scripting tools for creating haar xml cascades. • Eyepatch: Advanced scripting tool for training object detectors. • Warning! Stability Issues!

  16. Kohonen Net Implementation • Code modified from Karsten Kutsa • Still in the process of creating the data model for Neural Net input. • Currently looking to create 8 input nodes for each image (8*5 images) for 40 images total.

  17. Kohenen Net Implementationfor detected images A-E Example input

  18. Parameters to work with • Learning rate for Kohonen layer • Learning rate for output layer • Learning rate for step sizes • Smoothing factor for score deltas • Parameter for width of neighborhood

  19. Additional data to consider • x y location • scale of each object • Multiples of the same object

  20. Knowledge base • Possible implementation of Narl to augment the performance of the Neural Net.

More Related