Aerial image moving object detection and elimination method based on high-resolution texture generation

A technology for object detection and moving objects, which is applied in the field of image processing and 3D scene modeling, and can solve the problems of distorted texture and dislocation of 3D scene models.

Active Publication Date: 2019-07-19
BEIHANG UNIV
View PDF8 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the embodiment of the present invention provides a method to solve the ghosting of moving objects, the distortion of 3D scene models and the texture of image super-resolution reconstruction results caused by the position changes of moving objects such as vehicles or pedestrians during the aerial photography process. Misalignment and other issues

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
  • Aerial image moving object detection and elimination method based on high-resolution texture generation
  • Aerial image moving object detection and elimination method based on high-resolution texture generation
  • Aerial image moving object detection and elimination method based on high-resolution texture generation

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0148] Example 1: 3D modeling using aerial images of self-flying drones.

[0149] The data used here is the shooting result of the drone flight, and the 3D modeling is carried out using Smart3D. Figure 14a and Figure 14b Some aerial images for 3D modeling, such as Figure 14a and Figure 14b As shown, the objects inside the circular frame remain stationary, while the objects inside the square frame move. Figure 15a and Figure 15b It is the effect after Smart3D three-dimensional reconstruction, such as Figure 15a and Figure 15b As shown, there are problems such as texture mapping errors or model distortions, such as pits on the road surface, red is directly pasted as a texture (model without ups and downs), and model distortion due to incomplete character modeling. It can be seen that moving objects have a huge impact on the 3D reconstruction results.

[0150] Considering that the image resolution of the self-flying UAV aerial photo atlas is 7360*4912, according to...

Embodiment 2

[0153] Embodiment 2: Carry out image super-resolution reconstruction experiment using online aerial photography atlas:

[0154] In order to prove the versatility of the above method for detecting and eliminating moving objects in aerial photographs provided by the embodiment of the present invention, the online aerial photograph atlas is the data used in the image super-resolution reconstruction experiment of the present invention. Image super-resolution reconstruction was performed by PhotoShop. Figure 18a and Figure 18b It is a partial image of the reconstruction map used this time. Such as Figure 18a and Figure 18b As shown in , the vehicles in the box are moving, and the vehicles in the circle remain stationary. After Photoshop super-resolution reconstruction, such as Figure 19 As shown, the vehicles in the box have ghosts, and the vehicles in the circle remain solid. It can be seen that moving objects have a huge impact on the super-resolution results of the or...

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 an aerial image moving object detection and elimination method for high-resolution texture generation. The method comprises the steps of detecting a suspicious object from theaerial image; screening the suspicious object to obtain a moving object and masking the moving object; removing the moving object by carrying out image restoration on the mask region, so that the problems of image super-resolution texture reconstruction effect caused by position change of moving objects such as vehicles or pedestrians in the aerial photography process and model distortion and texture error mapping in three-dimensional modeling can be effectively improved and solved. Moreover, the appropriate texture pictures are selected for eliminating the moving object according to differentconditions, so that the image after the moving object is eliminated is closer to the real condition of the ground; besides, according to the aerial image moving object detection and elimination method provided by the embodiment of the invention, the moving object under the dynamic background can be effectively detected, and the method is not limited to the adjacent frame images with high overlapping degree, such as videos, and is especially suitable for the condition of lower overlapping degree, such as aerial images, etc.

Description

technical field [0001] The invention relates to the technical fields of image processing and three-dimensional scene modeling, in particular to a method for detecting and eliminating moving objects in aerial images generated by high-resolution textures. Background technique [0002] Automated 3D modeling based on aerial images to form high-resolution 3D terrain models is an important requirement in many fields such as virtual reality and augmented reality. How to create higher-definition texture images and more accurate 3D models under the condition of limited camera conditions or flight environment is the key to various applications. [0003] Most of the existing 3D scene modeling is carried out directly by using aerial photographs and 3D modeling software. In the actual aerial photography process, due to the influence of flight altitude and flight environment, the aerial photography process usually lasts for a long time, and the vehicles and pedestrians in it change a lot...

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): G06T7/223G06T3/40G06T5/00G06T7/11G06T7/41
CPCG06T7/223G06T7/11G06T7/41G06T3/4053G06T2207/10021G06T5/77
Inventor 龚光红李莹李妮孙琳
Owner BEIHANG 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap