Delegating Custom Object Detection Tasks to a Universal Classification System
This work addresses the need for easier deployment of custom object detection systems, but it appears incremental as it builds on a previously introduced concept.
The paper tackles the problem of custom object detection by proposing a universal framework that transforms a classifier into an object detector using an image grid, standardizing and simplifying implementation for custom tasks.
In this paper, a concept of multipurpose object detection system, recently introduced in our previous work, is clarified. The business aspect of this method is transformation of a classifier into an object detector/locator via an image grid. This is a universal framework for locating objects of interest through classification. The framework standardizes and simplifies implementation of custom systems by doing only a custom analysis of the classification results on the image grid.