Multi-level framework for object detection
US9477908B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 10, 2014 |
| Grant date | Oct 25, 2016 |
| Priority date | — |
| Expiry date | Aug 11, 2034 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N7/01
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The disclosure provides an approach for detecting objects in images. An object detection application receives a set of training images with object annotations. Given these training images, the object detection application generates semantic labeling for object detections, where the labeling includes lower-level subcategories and higher-level visual composites. In one embodiment, the object detection application identifies subcategories using an exemplar support vector machine (SVM) based clustering approach. Identified subcategories are used to initialize mixture components in mixture models which the object detection application trains in a latent SVM framework, thereby learning a number of subcategory classifiers that produce, for any given image, a set of candidate windows and associated subcategory labels. In addition, the object detection application learns a structured model for object detection that captures interactions among object subcategories and identifies discriminative visual composites, using subcategory labels and spatial relationships between subcategory labels to reason about object interactions.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.