Target object detection method and device

A technology of target objects and detection methods, applied in the field of target detection, can solve problems such as increasing storage space, and achieve the effect of improving efficiency and fast detection speed

Active Publication Date: 2021-01-01
BEIJING XIAOMI MOBILE SOFTWARE CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the number of slides increases or the window becomes larger, the storage space required for the tracking process will rise sharply; and since there will be overlapping areas between adjacent sliding windows, a lot of useless work has been done in the tracking process

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 detection method and device
  • Target object detection method and device
  • Target object detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

[0067] figure 1 is a flow chart of a method for detecting a target object according to an exemplary embodiment, as shown in figure 1 As shown, the method can be applied to terminals such as mobile phones, tablet computers, and cameras. The detection methods of this target object include:

[0068] Step S101. Detect the first position of the target object in the current frame image of...

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 present disclosure relates to a method and device for detecting a target object, the method comprising: detecting the first position of the target object in the current frame image of the video to be processed; in the next frame image of the current frame image, according to The first position determines an enlarged area, the enlarged area is an area occupying a preset area in the next frame of image, and the enlarged area includes the first position; the enlarged area is input to the full A convolutional network FCN model to obtain a second position of the target object in the enlarged region. This disclosure uses the FCN model for target detection. Since the enlarged area input to the FCN model is smaller than the entire frame image input to the CNN model, and there are fewer repeated areas than the CNN model using sliding windows for target detection, the detection speed is faster. , thereby improving the efficiency of detecting the target object.

Description

technical field [0001] The present disclosure relates to the field of target detection, in particular to a method and device for detecting a target object. Background technique [0002] In the related technologies, as the research on the artificial neural network becomes more and more in-depth, the deep learning method based on the artificial neural network has been successfully applied in many fields. For example: in the field of computer vision, in the field of speech recognition, and in the field of object tracking. This disclosure further studies the application of deep learning methods in the field of target detection. [0003] When detecting a target object, a CNN (Convolutional Neural Network, Convolutional Neural Network) model is usually trained by an online training method, and the CNN model is used to detect the target object and then track the target object. Specifically, a sliding window method is used in the surrounding area where the target object is located...

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): G06T7/246G06T7/277G06N3/04G06N3/08
CPCG06T7/248G06T7/277G06N3/08G06T2207/20076G06T2207/20081G06T2207/20084G06T2207/20021G06T2207/10016G06N3/045
Inventor 陈志军
Owner BEIJING XIAOMI MOBILE SOFTWARE CO LTD
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