Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Target space knowledge and two-stage prediction learning-based target detection method

A target detection and target technology, applied in the field of optical remote sensing image processing

Active Publication Date: 2018-04-03
XIDIAN UNIV
View PDF4 Cites 47 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a target detection method based on target space knowledge and two-stage predictive learning, which is used for feature extraction and target detection of high-resolution optical remote sensing images. The existing high-resolution optical remote sensing image target detection methods lack effective feature extraction, and the problems of low detection rate and high false alarm rate for large scene targets

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
  • Target space knowledge and two-stage prediction learning-based target detection method
  • Target space knowledge and two-stage prediction learning-based target detection method
  • Target space knowledge and two-stage prediction learning-based target detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0114] Experimental conditions and methods:

[0115] The hardware platform is: Titan X 12GB, 64GB RAM;

[0116] The software platform is: Ubuntu16.04.2, Caffe;

[0117] Experimental method: respectively the existing SSD target detection method and the method of the present invention

[0118] Simulation content and results:

[0119] In the simulation experiment, according to the given real marks on the data set, 80% of the targets are randomly selected as the training set, and the remaining 20% ​​of the targets are used as the test set, and the detection rate and false alarm rate are calculated as evaluation indicators.

[0120] The evaluation results are shown in Table 2, wherein, Alg1 is the method of SSD, and Alg2 is the method of the present invention.

[0121] Table 2. The present invention and comparison method obtain the detection rate and the false alarm rate of various targets in the simulation experiment

[0122]

[0123]

[0124] Analysis of results:

[01...

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 target space knowledge and two-stage prediction learning-based target detection method. By utilizing various data conversion methods, a sample number is increased and samplediversity is improved; two deep neural networks including SSD and newly designed RefineNet are trained; for a prediction target with a relatively high probability in a primary prediction result of theSSD, the accuracy of judgment is further improved through the RefineNet; and by establishing peculiar spatial structure constraint rules of the target, the wrong prediction is reduced, thereby obtaining a final detection result. Compared with a few existing methods, the method provided by the invention has the advantages that visual and spatial characteristics of a remote sensing target are considered at the same time; and end-to-end target candidate selection, feature extraction and classified locating are realized by utilizing the deep networks with excellent feature extraction capabilities, so that the detection rate of the remote sensing target is remarkably increased and the false alarm rate is reduced.

Description

technical field [0001] The invention belongs to the technical field of optical remote sensing image processing, relates to applications in the field of image target detection, and in particular to a target detection method based on target space knowledge and two-stage predictive learning. Background technique [0002] Object detection is a fundamental problem in the field of aerial and satellite imagery analysis and plays a vital role in numerous applications such as environmental monitoring, geological hazard monitoring, land use and cover mapping, geographic information system updates, precision agriculture, and urban planning. [0003] Looking back at the development of object detection in optical remote sensing images, there are four main types of methods: object detection based on template matching, object detection based on knowledge, object detection based on object image analysis, and object detection based on machine learning. At present, with the development of aer...

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): G06K9/00G06K9/62
CPCG06V20/13G06V2201/07G06F18/214
Inventor 侯彪任仲乐焦李成朱浩赵暐刘旭孙其功马文萍
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products