Visual localization in images using weakly supervised neural network

A visual positioning and network technology, applied in the field of visual recognition systems, can solve problems such as time-consuming and non-scalable changes

Active Publication Date: 2020-01-10
SIEMENS AG
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Current approaches to machine learning-based visual localization have practical limitations, including requiring intensive manual pixel-wise or bounding-box labe

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Visual localization in images using weakly supervised neural network
  • Visual localization in images using weakly supervised neural network
  • Visual localization in images using weakly supervised neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] Aspects of embodiments of the present disclosure include a method of detecting localized regions in an image of one or more objects using a weakly supervised network. A classifier network, such as a convolutional neural network (CNN), can be trained to classify images as including features that classify objects or have conceptual classes. The captured images may be processed by a network of classifiers to classify the content of the images according to one or more categories. For example, classification can be applied to identify the presence of any anomalies in an image relative to the normal state for which it was trained. Anomalies may correspond to defects in objects depicted in the image, or to anomalies detected within normal settings. Without a priori knowledge (what shape or form the anomaly takes in the image), gradient-based inversion or backpropagation of the classifier network can be applied to discover the intrinsic properties of normal and abnormal parts ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

A system and method for visual anomaly localization in a test image includes generating, in plurality of scaled iterations, attention maps for a test image using a trained classifier network, using image-level. A current attention map is generated using an inversion of the classifier network on a condition that a forward pass of the test image in the classifier network detects a first class. One or more attention regions of the current attention map may be extracted and resized as a sub-image. For each scaled iteration, extraction of one or more regions of a current attention map is performedon a condition that the current attention map is significantly different than the preceding attention map. Visual localization of a region for the class in the test image is based on one or more of the attention maps

Description

technical field [0001] The present invention relates to artificial intelligence. More specifically, the present invention relates to the application of artificial intelligence to visual recognition systems. Background technique [0002] Visual recognition systems can apply machine learning-based methods, such as convolutional neural networks, which can involve training the system to recognize features or objects of interest in images based on learned classifications. Classification can include tangible attributes, such as identifying the presence of a particular animate or inanimate object. For example, a system can be trained to learn one or more classifications (eg, flowers, dogs, chairs), and once trained, it analyzes a series of test images to identify which images include objects of the trained classifications. [0003] Visual localization with machine learning assistance can be applied to detect anomalies within images or identify unusual objects potentially causing ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/32G06K9/62G06V10/25G06V10/764
CPCG06N3/084G06V10/25G06V10/82G06V10/764G06N3/045G06F18/2433G06N3/08G06T3/40G06T7/0002G06T2207/20084G06T2207/20216G06F18/25G06F18/217G06F18/2113G06F18/2431
Inventor 彭冠铨吴子彦扬·恩斯特
Owner SIEMENS AG
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap