An aerial photograph image difference detection method based on a dual network

An aerial image, difference detection technology, applied in biological neural network models, instruments, character and pattern recognition, etc., can solve the problem of difficult to select effective feature descriptors, and achieve easy expression, strong anti-interference ability, and accurate position coordinates. Effect

Active Publication Date: 2019-01-22
NORTHWESTERN POLYTECHNICAL UNIV
View PDF5 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention adds deep learning to difference detection, since deep learning does not require manual design of features, it can avoid the problem of difficult selection of effective feature descriptors in image segmentation and difference detection

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
  • An aerial photograph image difference detection method based on a dual network
  • An aerial photograph image difference detection method based on a dual network
  • An aerial photograph image difference detection method based on a dual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] Embodiments of the present invention are described in detail below, and the embodiments are exemplary and intended to explain the present invention, but should not be construed as limiting the present invention.

[0075] A kind of aerial image difference detection method based on double network in the present embodiment, comprises the following steps:

[0076] 1. Data collection and processing

[0077] Neural networks are sensitive to the data they input, so in the field of deep learning, the processing of raw data is particularly important. Correctly processed data can not only speed up the convergence speed of network training, but also achieve better training results. The following introduces the data processing process in the present invention:

[0078] 1. Data collection

[0079] The drone flies along the same planned path at different times, and at the same time uses the drone's onboard camera to collect aerial pictures along the route. This results in a serie...

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 provides an aerial photograph image difference detection method based on a dual network, comprising four parts of image acquisition and processing, building a dual network model, training the dual network model and using the model. As the depth learning is not required to design feature manually, the problem that it is difficult to select an effective feature descriptor in image segmentation and difference detection can be avoided. The depth learning method can also overcome the shortcomings of low robustness to illumination in RGB image difference detection task. At the same time, the invention adopt the object detection instead of the traditional segmentation method, which can more distinguish the single object, and the position coordinate of the object is more accurate andeasier to express. By calculating the ROI of the prediction box after detection to determine the relevant objects of the two images, it can also reduce the requirements of registration accuracy. Importantly, the invention adds the semantic information of the object, has the object class information, has stronger anti-interference ability, and can better analyze the difference types.

Description

technical field [0001] The invention belongs to the field of image processing and machine vision, and relates to a method for detecting differences of aerial images based on double networks. Background technique [0002] In recent years, with the rapid development of drones, drone aerial photography has been widely used in fields such as agronomy, geology, forests, oceans, geographic surveying and mapping, military reconnaissance, and environmental protection. We measure the earth with unprecedented precision in terms of time and space, and collect various data quickly and accurately. In the past, data was acquired from the air, usually by using satellites or aircraft. But compared to these two, UAV is a superior "air sensor". The line of sight of satellites is blocked by clouds covering more than 2 / 3 of the earth, and drones can collect data more accurately and more frequently; compared with airplanes, drones are cheaper, easier to operate, and safer. UAVs can provide hi...

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): G06K9/00G06K9/32G06K9/62G06N3/04
CPCG06V20/13G06V10/25G06N3/045G06F18/214
Inventor 布树辉李清韩鹏程
Owner NORTHWESTERN POLYTECHNICAL UNIV
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