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

Remote sensing image small target detection method based on improved YOLOv3

A small target detection and remote sensing image technology, applied in the field of deep learning and target detection, can solve problems such as the inability to fully reflect the positional relationship between the two frames, the direction in which the overlapping prediction frames need to move closer, unfavorable search and identification, and many interference factors. To achieve the effect of improving the receptive field, performance improvement, and training speed

Pending Publication Date: 2022-01-25
YANSHAN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 1. Most of the targets are small in scale, with only dozens of pixels, which is not conducive to finding and identifying;
[0004] 2. The background is complex and there are many interference factors, such as shooting angle, lighting changes, similar targets, object occlusion, etc., which can easily lead to misjudgment and is not conducive to detection
Using this method to calculate the loss cannot fully reflect the positional relationship between the two frames, the coincidence degree, and the direction in which the predicted frames need to move closer, so the loss function needs to be improved

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
  • Remote sensing image small target detection method based on improved YOLOv3
  • Remote sensing image small target detection method based on improved YOLOv3
  • Remote sensing image small target detection method based on improved YOLOv3

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0072] A small target detection method for remote sensing images based on improved YOLOv3, which specifically includes the following steps:

[0073] Step 1: Obtain training remote sensing images to form a data set, convert the annotation information of the data set into VOC format, and randomly divide it into a training verification set and a test set at a ratio of 9:1. Each set does not interfere with each other, and there are no identical pictures. Prevent data from being polluted. Cross-validation is used during training, that is, the training and verification set is randomly divided into a training set and a verification set at a ratio of 8:1. The training set is used for model training and weight update, and the verification set is used to verify the model obtained at the end of each round of training. Evaluate.

[0074] Step 2: Improve the Neck. With the deepening of the Darknet-53 network, the extracted target features will change from more to less, from concrete to a...

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 remote sensing image small target detection method based on improved YOLOv3, and belongs to the technical field of deep learning and target detection. The method comprises the steps: preprocessing a data set; optimizing a YOLOv3 network, and adding a cavity convolution group module, a feature enhancement module and a channel attention mechanism module in Neck; carrying out online data enhancement; performing forward reasoning; improving a loss function; and selecting the YOLOv3 network model with the highest detection precision and recall rate on the verification set to load the network, and the like. According to the method, the loss function is improved, and the cavity convolution group module, the feature enhancement module and the channel attention mechanism module are added into the YOLOv3 original network to improve the YOLOv3 detection network, so that the performance is obviously improved, the target detection in the remote sensing image is more comprehensive and higher in precision, and the training speed and the overall detection precision are improved.

Description

technical field [0001] The invention relates to the field of deep learning and target detection, in particular to a method for detecting small targets in remote sensing images based on improved YOLOv3. Background technique [0002] With the development of deep learning and neural networks, computer vision has developed rapidly. In this field, target detection and recognition technology has been widely studied and applied in practice, which brings great convenience to people's life. For example, when applied to drones, it can automatically identify specific targets in remote sensing images, and can replace manual work to efficiently complete this repetitive work. However, the following problems exist in many target detection work: [0003] 1. Most of the targets are small in scale, with only dozens of pixels, which is not conducive to finding and identifying; [0004] 2. The background is complex and there are many interference factors, such as shooting angle, lighting cha...

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): G06V20/13G06V10/44G06V10/764G06V30/19G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F18/241
Inventor 李国强常轩
Owner YANSHAN 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