Learning OpenCV 4 Computer Vision with Python by Joseph Howse

Author:Joseph Howse
Language: eng
Format: mobi, epub
Tags: COM012050 - COMPUTERS / Image Processing, COM016000 - COMPUTERS / Computer Vision and Pattern Recognition, COM051360 - COMPUTERS / Programming Languages / Python
Publisher: Packt
Published: 2020-02-20T10:36:57+00:00

Understanding NMS

The concept of NMS might sound simple. From a set of overlapping solutions, just pick the best one! However, the implementation is more complex than you might initially think. Remember the image pyramid? Overlapping detections can occur at different scales. We must gather up all our positive detections, and convert their bounds back to a common scale before we check for overlap. A typical implementation of NMS takes the following approach:

Construct an image pyramid.

Scan each level of the pyramid with the sliding window approach, for object detection. For each window that yields a positive detection (beyond a certain arbitrary confidence threshold), convert the window back to the original image's scale. Add the window and its confidence score to a list of positive detections.

Sort the list of positive detections by order of descending confidence score so that the best detections come first in the list.

For each window, W, in the list of positive detections, remove all subsequent windows that significantly overlap with W. We are left with a list of positive detections that satisfy the criterion of NMS.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.