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

Depth image frame generation method and device, computer equipment and storage medium

A technology of depth images and image frames, applied in the field of image processing, can solve the problems of long time-consuming calculation of depth maps, large image resolution, and insufficient changes in the edges and heights of DSM objects, and achieve the effect of reducing the time-consuming calculation.

Pending Publication Date: 2021-10-12
GUANGZHOU XAIRCRAFT TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventor found that the existing technology has the following defects: the image resolution of the aerial photography is large, and the calculation of the depth map takes a long time. If the image is down-sampled by a certain proportion, although the calculation time can be reduced, the The edge of the object and the edge with a height difference in the point cloud data are not obvious enough, so the edge and height change of the object in the DSM calculated by using the point cloud data are not obvious enough

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
  • Depth image frame generation method and device, computer equipment and storage medium
  • Depth image frame generation method and device, computer equipment and storage medium
  • Depth image frame generation method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] figure 1 It is a flowchart of a method for generating a depth image frame provided by Embodiment 1 of the present invention. This embodiment is applicable to the case where a matching depth image frame is obtained within a certain time-consuming range based on a high-definition image frame obtained by aerial photography. The method can be executed by a device for generating a depth image frame, the device can be implemented by software and / or hardware, and generally can be integrated in a terminal or server with data processing functions. Correspondingly, such as figure 1 As shown, the method includes the following operations:

[0051] S110. Acquire an original image frame to be processed.

[0052] First of all, the application scenario of the embodiment of the present invention is briefly introduced: in order to form a DSM in a set area (a certain farmland or an orchard, etc.), it is necessary to obtain multiple continuous aerial photos of the area through a surveyin...

Embodiment 2

[0064] figure 2 It is a flowchart of a method for generating a depth image frame provided by Embodiment 2 of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiment. In this embodiment, each of the original image frames is calculated. The operation of obtaining the target depth image frame matching the original image frame based on the depth information of the target pixel point is further refined. Correspondingly, such as figure 2 As shown, the method of this embodiment may include:

[0065] S210. Acquire the original image frame to be processed.

[0066] S220. From the original image frame, select a target pixel according to a preset number of pixel intervals.

[0067] S230. Acquire sparse point cloud data corresponding to the original image frame, and calculate a depth range of the target depth image frame according to depth information of each point cloud data point in the sparse point cloud data.

[0068] In this embodiment,...

Embodiment 3

[0087] Figure 3a It is a flow chart of a method for generating a depth image frame provided by Embodiment 3 of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiment. After the target depth image frame, point cloud data is generated based on the above multiple target depth image frames, and the operation of generating a matching DSM based on the point cloud data is further refined. Correspondingly, such as Figure 3a As shown, the method of this embodiment may include:

[0088] S310. Acquire the original image frame to be processed.

[0089] S320. From the original image frame, select target pixel points according to the preset number of pixel point intervals.

[0090] S330. Calculate depth information of each of the target pixel points in each of the original image frames to obtain a target depth image frame that matches the original image frame.

[0091] S340. Fusion target depth image frames respectively corresponding to the plu...

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

Embodiments of the invention disclose a depth image frame generation method and apparatus, a computer device and a storage medium. The method comprises the steps of obtaining a to-be-processed original image frame; in the original image frame, selecting target pixel points according to a preset pixel point interval number; and calculating depth information of each target pixel point in each original image frame to obtain a target depth image frame matched with the original image frame. According to the technical scheme provided by the embodiment of the invention, while the image feature information of each pixel point in the original image frame is reserved, only the depth information of the selected target pixel point in the original image frame is calculated, so that the final target depth image frame is obtained, the time consumption of calculation and the amount of image information are taken into account, while the calculation time consumption of the depth map is greatly reduced, the obvious object edge and the obvious change of the height fall in the finally obtained DSM can be maintained.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, to a method, device, computer equipment, and storage medium for generating a depth image frame. Background technique [0002] With the continuous development of drone shooting technology, with the help of aerial photography drones, ground image maps can be quickly collected, fully automated 3D modeling can be realized, and DSM (Digital Surface Model, digital surface model) and DOM (Digital Orthophoto Map, digital surface model) can be output. Forward image map) and other results. [0003] At present, the MVS (Multi-view Stereo) method can be used to calculate the point cloud data of the entire scene from the images captured by the aerial drone. The general process is as follows: First, a stereo matching pair is formed based on the current frame image and the adjacent frame image, and then the depth map of the current frame is calculated based on ...

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): G06T7/55G06T5/50
CPCG06T7/55G06T5/50G06T2207/10028G06T2207/20221
Inventor 池鹏可
Owner GUANGZHOU XAIRCRAFT TECH CO LTD