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

Feature recognition method, device, pan-tilt camera and storage medium

A technology of feature recognition and feature classification, applied in character and pattern recognition, computer components, instruments, etc., can solve the problems of large resource occupation, inability to guarantee the effect of feature recognition processing, low processing efficiency, low image processing stability, etc., to achieve Improve computing processing efficiency, occupy less resources, and improve stability

Active Publication Date: 2022-03-22
SHANGHAI MOSHON TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the images taken by existing smart cameras are usually high-definition images. When the camera performs feature recognition, the high-definition images need to be compressed before being sent to the processor for feature recognition. The processing efficiency is low and the resources are relatively large. Large can not guarantee a stable feature recognition processing effect
Therefore, the existing technology of using cameras for feature recognition still has the problems of low image processing efficiency and low image processing stability.

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
  • Feature recognition method, device, pan-tilt camera and storage medium
  • Feature recognition method, device, pan-tilt camera and storage medium
  • Feature recognition method, device, pan-tilt camera and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] The present invention provides a feature recognition method, which can be applied to a target camera. The target camera includes a main camera and a sub-camera. The resolution of the main camera is greater than that of the sub-camera. See figure 1 The flow chart of the feature recognition method shown, the method mainly includes the following steps S102 to S106:

[0028] Step S102, using the primary camera and the secondary camera to capture images synchronously.

[0029] The main camera and the auxiliary camera of the above-mentioned target camera are controlled to collect images synchronously. Since the relative positions of the above-mentioned main camera and the auxiliary camera are fixed (such as, the main camera and the auxiliary camera are distributed horizontally or vertically), in order to make the above-mentioned main camera and the auxiliary camera The target objects in the images captured by the secondary camera are as identical as possible, and the distance...

Embodiment 2

[0047] For the feature recognition method provided in Embodiment 1, the embodiment of the present invention provides a feature recognition device, which can be applied to the controller of the target camera. The target camera includes a main camera and a secondary camera, and the resolution of the main camera is greater than Secondary camera resolution, see figure 2 A structural schematic diagram of a feature recognition device is shown, which includes the following modules:

[0048] The image acquisition module 21 is configured to use the main camera and the auxiliary camera to acquire images synchronously.

[0049] The feature recognition module 22 is configured to acquire the target image collected by the secondary camera, perform feature recognition on the target image, and obtain feature keywords of the target image.

[0050] The feature matching module 23 is configured to obtain a high-definition image corresponding to the target image from the images collected by the ...

Embodiment 3

[0062] Corresponding to the methods and devices provided by the foregoing embodiments, see image 3 Shown is a schematic structural view of a pan-tilt camera, an embodiment of the present invention also provides a pan-tilt camera, the pan-tilt camera includes: a main camera 31, a secondary camera 32, a processor 33 and a storage device (not shown in the figure out). A computer program operable on the processor is stored in the memory, and the processor implements the steps of the method provided by the above-mentioned embodiments when executing the computer program.

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 feature recognition method, device, pan-tilt camera and storage medium, and relates to the technical field of cameras. The method includes: using a main camera and a sub-camera to collect images synchronously; wherein, the resolution of the main camera is greater than that of the sub-camera rate; obtain the target image collected by the secondary camera, perform feature recognition on the target image, and obtain the characteristic keywords of the target image; obtain the high-definition image corresponding to the target image from the image collected by the main camera, and use the characteristic keywords as the high-definition image Feature label; wherein, the target image and the high-definition image are images acquired at the same time. The invention can improve the operation processing efficiency of the pan-tilt camera and the stability of image feature recognition.

Description

technical field [0001] The invention relates to the technical field of cameras, in particular to a feature recognition method and device, a pan-tilt camera and a storage medium. Background technique [0002] With the development of visual processing technology and artificial intelligence technology, the shooting functions of handheld smart cameras are becoming more and more powerful, such as identifying the characteristics of various objects in the image during the shooting process, so that users can classify and manage the photos or videos taken . However, the images taken by existing smart cameras are usually high-definition images. When the camera performs feature recognition, the high-definition images need to be compressed before being sent to the processor for feature recognition. The processing efficiency is low and the resources are relatively large. It is impossible to guarantee a stable feature recognition processing effect. Therefore, the existing technology of ...

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): H04N5/232H04N5/225G06V20/10G06V10/40G06V10/82G06N3/04
CPCG06V20/10G06V10/40H04N23/45H04N23/665H04N23/80G06N3/045
Inventor 梁峰欧金超刘煜浦汉来
Owner SHANGHAI MOSHON TECH CO LTD