Unlock instant, AI-driven research and patent intelligence for your innovation.

A Panoramic Image Object Detection Method Based on Spherical Projection Grid and Spherical Convolution

A panoramic image and spherical projection technology, applied in the field of panoramic image target detection, can solve the problems of difficult detection and large deformation, and achieve the effects of good detection results, strong reusability and strong robustness

Active Publication Date: 2020-12-01
WUHAN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Different from images captured by ordinary flat cameras, the process of spherical expansion will inevitably introduce large errors, and the targets on panoramic images usually have greater deformation and are more difficult to detect

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
  • A Panoramic Image Object Detection Method Based on Spherical Projection Grid and Spherical Convolution
  • A Panoramic Image Object Detection Method Based on Spherical Projection Grid and Spherical Convolution
  • A Panoramic Image Object Detection Method Based on Spherical Projection Grid and Spherical Convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] Firstly, a neuron network (Grid-based Spherical CNN, GS-CNN) based on spherical projection grid and spherical convolution is constructed according to the method of the present invention. Then get the training sample data, attached figure 1 Shows the process of building a training sample library. attached figure 2 It is a panoramic image of a street scene in a certain place captured by a ladybug panoramic camera. The objects of interest on the image mainly include 4 categories: street lights, crosswalks, road warning lines, and vehicles. The original panoramic images were reprojected into Driscoll-Healy square grid images, and these panoramic images were resampled to a suitable resolution (600×600 pixels) in combination with computer video memory and the target size of interest. Then manually mark all the four types of targets on the image, including the bounding box and category information of the target.

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 relates to a panoramic image target detection method based on spherical projection grid and spherical convolution. The existing panoramic images and target annotation files are used to build a sample library, and the neural network based on spherical projection grid and spherical convolution is trained to learn the characteristics of the target of interest on the panoramic image. The trained network model is used to detect objects in new panoramic images, so as to realize automatic identification and bounding box positioning of objects of interest on panoramic images. Using the spherical projection grid method, the feature map of the candidate frame obtained by the region proposal network is projected onto the spherical grid with preset resolution, and then the rotation invariant features are extracted by spherical convolution, and then the final classification is performed to obtain a panoramic view. Better detection results for objects of interest on images. The invention has the following advantages: strong robustness, more suitable for target detection tasks on panoramic images; and higher recognition accuracy for objects with large deformation on panoramic images.

Description

technical field [0001] The invention relates to a panoramic image target detection method based on spherical projection grid and spherical convolution, which can be used in the fields of automatic positioning and identification of interested targets in street view images, urban supervision, vehicle detection, driverless driving and the like. Background technique [0002] Image object detection is a basic task in computer vision and photogrammetry, and it plays an extremely important role in autonomous driving, urban supervision, change detection, pedestrian tracking, license plate recognition, virtual reality, and human-computer interaction. So far, there have been many studies on the method of target detection. The early target detection methods were mainly based on the sliding window strategy, using a window with a designed size to traverse the entire image to find the target. Such methods are usually inefficient and cannot achieve high accuracy. Convolutional neural 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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06N3/04G06K9/32
CPCG06V10/25G06N3/045G06F18/214
Inventor 季顺平余大文
Owner WUHAN UNIV