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

Remote sensing target detection method based on content awareness

A technology of content perception and target detection, which is applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as ignorance and different content information, and achieve the effect of improving accuracy and realizing high-quality detection

Pending Publication Date: 2022-01-07
HENAN UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, on the same target object, multiple suggested regression boxes with the same IoU can be obtained, but the content information contained in these regression boxes is different, and the inventor found that the content information contained in the regression boxes plays a key role in the subsequent calculation process However, the current frame regression strategy ignores the role of the content information contained in these regression frames in the subsequent calculation process

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 target detection method based on content awareness
  • Remote sensing target detection method based on content awareness
  • Remote sensing target detection method based on content awareness

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Such as figure 1 As shown, the remote sensing target detection network used in the embodiment of the present invention includes a feature extraction network, an RPN network, a classification module, a regression module and a content perception module; as a possible implementation mode, the remote sensing target detection network used in the embodiment of the present invention ResNet101 is used as the backbone network, and the FPN architecture is used to construct the feature pyramid as the feature extraction network, and then three horizontal anchor boxes are preset on the P3, P4, P5, P6, and P7 layers of the feature extraction network, and the feature map obtained by the feature extraction network High-quality proposal regions are given by the RPN network. The remote sensing target detection method provided by the embodiment of the present invention is based on the content awareness module, such as figure 2 As shown, it specifically includes the following steps:

[...

Embodiment 2

[0051] High aspect ratio has always been a big problem in rotating target detection. Some high aspect ratio objects will be difficult to match suitable positive samples in the RPN stage due to the fixed size of the anchor frame, which makes the high aspect ratio object Detection performance has been poor. In order to solve this problem, the embodiment of the present invention designs a loss function that can make the remote sensing target detection network pay more attention to the aspect ratio in the regression process, denoted as L wh . The basic idea of ​​this embodiment is to make the remote sensing object detection network pay more attention to the change of the aspect ratio during the regression process by calculating the difference between the aspect ratio of the predicted frame and the real frame.

[0052] On the basis of the foregoing embodiments, the embodiments of the present invention specifically further include the following steps:

[0053] S201: The content pe...

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 a remote sensing target detection method based on content awareness. The method comprises the following steps: obtaining coordinate information of a prediction frame according to information output by a regression module, and obtaining coordinate information of a real frame from an original remote sensing image; positioning on the maximum feature map according to the coordinate information of the prediction frame and the coordinate information of the real frame to obtain feature information v* and v contained in the prediction frame and the real frame respectively; determining a common minimum horizontal enclosing rectangle of the prediction frame and the real frame, and taking out an area where the minimum horizontal enclosing rectangle is located from the maximum feature map, and recording the area as a feature map x; respectively setting contents which do not belong to the real frame and the prediction frame on the feature map x to be 0 to obtain a feature map f1 corresponding to the real frame and a feature map f1* corresponding to the prediction frame; calculating the similarity between the feature map f1 and the feature map f1*, taking the similarity as a content consistency loss Lfeed, and constraining the regression of the anchor frame based on the content consistency loss Lfeed.

Description

technical field [0001] The invention relates to the technical field of satellite remote sensing, in particular to a content-aware-based remote sensing target detection method. Background technique [0002] Horizontal object detectors, such as R-CNN, fastR-CNN, faster R-CNN, YOLO, are designed for detecting horizontal objects. These methods usually use horizontal bounding boxes (HBB) to capture objects in natural images. Different from horizontal object detection tasks, arbitrary orientation object detection relies on oriented bounding boxes (OBBs) to capture objects in arbitrary orientations. Current object-oriented detection methods are generally extended from horizontal object detectors. For example, R2CNN uses a Region Proposal Network (RPN) to produce the HBB of text, and incorporates different scales of ensemble ROI features to regress the parameters of the OBB. R2PN incorporates bounding box orientation parameters into the RPN network, and develops a rotated RPN net...

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): G06V20/13G06V10/40G06V10/764G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/24
Inventor 朱小柯张冀统陈小潘袁彩虹王毓斐
Owner HENAN UNIVERSITY
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