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

Target-object identification method and apparatus, and robot

A target object and recognition method technology, applied in character and pattern recognition, instruments, computer parts and other directions, can solve the problems of low accuracy and slow running speed, and achieve the effect of improving the recognition speed, improving the actual utility, and improving the recognition accuracy.

Inactive Publication Date: 2018-03-09
SHEN ZHEN KUANG CHI HEZHONG TECH LTD
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a target object recognition method and device, and a robot to at least solve the technical problems of slow operation speed and low precision of the traditional target object recognition method

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
  • Target-object identification method and apparatus, and robot
  • Target-object identification method and apparatus, and robot
  • Target-object identification method and apparatus, and robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] According to an embodiment of the present invention, an embodiment of a method for identifying a target object is provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and, Although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0022] figure 1 is a flowchart of a method for identifying a target object according to an embodiment of the present invention, such as figure 1 As shown, the method includes the following steps:

[0023] Step S102, acquiring at least one sliding window, wherein the image in each sliding window contains the target object to be identified.

[0024] Step S104, using at least one convolutional neural network to identify images in at least one sliding window to obtain an identification result of at leas...

Embodiment 2

[0103] According to an embodiment of the present invention, an embodiment of an apparatus for identifying a target object is provided, image 3 is a schematic diagram of a device for identifying a target object according to an embodiment of the present invention, such as image 3 As shown, the method includes the following steps:

[0104] The acquiring module 31 is configured to acquire at least one sliding window, wherein the image in each sliding window contains the target object to be identified.

[0105] The processing module 33 is configured to use at least one convolutional neural network to identify images in at least one sliding window to obtain an identification result of at least one sliding window, wherein the identification result at least includes: identification type and confidence.

[0106] Specifically, the above-mentioned recognition type may be the type of the target object to be recognized identified by the convolutional neural network, not necessarily the ...

Embodiment 3

[0130] According to an embodiment of the present invention, an embodiment of a robot is provided, and the robot includes: the device for recognizing a target object in any one of Embodiment 2 above.

[0131] In the above-mentioned embodiments of the present invention, after obtaining at least one sliding window, at least one convolutional neural network can be used to identify the image in at least one sliding window to obtain the recognition result of at least one sliding window, and in any sliding window When the confidence degree reaches the confidence degree threshold of one or more convolutional neural networks, the type of the target object to be identified is marked as the recognition type of any sliding window, thereby realizing the identification of the target object. Therefore, by the present invention In the above embodiment, multiple convolutional neural networks can be used to identify the sliding window to improve the recognition accuracy of the target object, and...

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 a target-object identification method and apparatus, and a robot. The method comprises steps: at least one sliding window is acquired, wherein the image in each sliding windowcontains a to-be-identified target object; at least one convolutional neural network is adopted to identify the image in at least one sliding window to obtain at least one identification result of atleast one sliding window, wherein the identification result at least comprises an identification type and confidence; and if the confidence of any one of the sliding windows reaches the confidence threshold of one or a plurality of convolutional neural networks, the type of the to-be-identified target object is labeled as the identification type of any one of the sliding windows. Thus, the technical problems of conventional methods of identifying a target object being slow in operation and low in accuracy can be solved.

Description

technical field [0001] The present invention relates to the field of object recognition, in particular, to a target object recognition method and device, and a robot. Background technique [0002] Object recognition is a key issue in the field of computer vision, and it is also of great significance in the field of artificial intelligence to judge whether a machine has "intelligent" features. A mature and stable object recognition technology can help computers understand the layout of objects within the visual range and further extract deep information of the visual range (such as judging the current scene, events, time, etc.). [0003] The traditional object recognition technology uses the sliding window technology, and uses the traditional discrimination method to judge the object type under different sliding windows. Traditional object recognition methods are not only not accurate enough (using traditional classifiers), but also their core technology relies on a large nu...

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): G06K9/62
CPCG06F18/241G06F18/214G06V10/82
Inventor 不公告发明人
Owner SHEN ZHEN KUANG CHI HEZHONG TECH LTD