Unlock instant, AI-driven research and patent intelligence for your innovation.

Model construction in a neural network for object detection

A neural network and object detection technology, applied in the direction of biological neural network models, neural architectures, neural learning methods, etc.

Inactive Publication Date: 2019-02-05
SCOPITO APS
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Image acquisition from drone detection includes massive or large volumes of data, and illustrates the problem of introducing accuracy when training or applying neural networks for image recognition

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
  • Model construction in a neural network for object detection
  • Model construction in a neural network for object detection
  • Model construction in a neural network for object detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0122]

[0123]

[0124]

[0125] figure 1 One embodiment of a computer-implemented method (100) for building (102) a model (20) in a neural network (10) for object detection (40) in a raw image (50) is shown. The method includes an act of providing (104) a neural network (10) and a GUI (80). Additionally, a training batch (60) of images comprising training images (60) is built (106) in this embodiment. The neural network (10) is configured with a set of specifications (12). These specifications can include other information about the number of layers and ensemble model variables. A GUI (80) can be configured for displaying training images (66) and for displaying user interactions (82), such as annotated objects and object classes.

[0126] The computer-implemented method (100) also includes the act of iteratively performing (108). These actions include annotating (110) objects (70) on the training images (66) and associating (112) each annotation with an object ...

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

The present invention relates to a computer-implemented method for constructing a model in a neural network for object detection in an unprocessed image, where the construction may be performed basedon at least one image training batch. The model is constructed by training one or more collective model variables in the neural net- work to classify the individual annotated objects as a member of anobject class. The model in combination with the set of specifications when implemented in a neural network is capable of object detection in an unprocessed image with probability of object detection.

Description

technical field [0001] The present invention relates to a computer-implemented method for building a model in a neural network for object detection in raw images, wherein the building can be performed based on at least one training batch of images. The model is built by training one or more ensemble model variants in a neural network to classify each annotated object as a member of an object class. Combined with a set of specifications, the model, when implemented in a neural network, enables object detection in raw images with object detection probabilities. Background technique [0002] As the volume of data grows and the need to automate tasks expands, the enormous potential of deep learning, neural networks, and cloud infrastructure to efficiently perform complex data analysis becomes increasingly apparent. [0003] Massive research and investment around the world is being poured into machine learning and deep convolutional neural networks (CNNs). Large companies and r...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/02G06N3/08G06T7/00
CPCG06N3/02G06T7/00G06N3/08G06N3/045Y02A90/10
Inventor 肯·法兰克珍妮特·B·佩德森亨利克·索尔斯戈德
Owner SCOPITO APS