Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Deformable convolutional neural network-based infrared image object identification method

A convolutional neural network and infrared image technology, applied in the field of infrared image object recognition based on deformable convolutional neural network, to achieve the effect of improving performance and recognition performance

Inactive Publication Date: 2018-09-21
GUANGDONG POWER GRID CO LTD +1
View PDF2 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the accuracy of feature extraction by the above methods still has limitations that cannot be ignored.

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
  • Deformable convolutional neural network-based infrared image object identification method
  • Deformable convolutional neural network-based infrared image object identification method
  • Deformable convolutional neural network-based infrared image object identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] A method of infrared image object recognition based on deformable convolutional neural network, such as figure 1 shown, including the following steps:

[0036] S1: Collect database samples and set training set and test set. The training set uses COCO. The images in this dataset include 91 types of targets, 328,000 images and 2,500,000 labels. And set the coding of each category in the classifier, for example, the three types of objects car, monkey, and potted plants are coded as 100, 010 and 001 respectively. The test set uses infrared images of substation equipment.

[0037] S2: Build a convolutional neural network architecture, and set the depth and width architecture of the convolutional neural network by overlapping several convolutional layers and pooling layers;

[0038] S3: Use a deformable convolution kernel for sampling in the convolutional layer, learn the offset offset by adding an additional convolutional layer, share the input feature map, and then use th...

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 invention discloses a deformable convolutional neural network-based infrared image object identification method. The method comprises the steps of constructing a training set and a test set; establishing a convolutional neural network architecture; adding a softmax classifier to the last layer, and setting an objective function; performing sampling by adopting a convolution kernel of linear ornonlinear deformation; performing pooling operation in a pooling layer by adopting a rule block sampling-based ROI pooling method which is the best in the industry at present; setting learning rate parameters according to experience; and easily performing standard back propagation end-to-end training, thereby obtaining a deformable convolutional neural network. An experiment proves that the spatial geometric deformation learning capability is introduced in the convolutional neural network, so that an identification task of an image with spatial deformation is better finished; the geometric transformation modeling capability of the convolutional neural network and the effectiveness of target detection and visual task identification are improved; and dense geometric deformation in space issuccessfully learnt.

Description

technical field [0001] The present invention relates to the fields of human-computer interaction, computer vision, and object recognition, and more specifically, to an infrared image object recognition method based on a deformable convolutional neural network. Background technique [0002] Body recognition is a very important research field in computer vision, including face recognition, handwritten digit recognition, gesture recognition and object recognition, etc. It can be widely used in human-computer interaction, image classification and image retrieval and other fields. The two main indicators to measure the quality of an object recognition system are: recognition rate and recognition speed. Generally speaking, a higher recognition rate means a relatively slow recognition speed, and a faster recognition speed means a relatively low recognition rate. Therefore, how to weigh the pros and cons has always been an unavoidable problem in the field of object recognition. ...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/084G06V20/10G06N3/045
Inventor 肖立军廖志伟邹国惠裴星宇万新宇李晨熙韩玉龙吴伟力覃佳奎姜媛
Owner GUANGDONG POWER GRID CO LTD
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
Eureka Blog
Learn More
PatSnap group products