Moving object detection method based on depth learning

A moving target and deep learning technology, applied in the field of moving target detection based on deep learning, can solve the problems of insufficient use of inter-frame correlation information, large memory and computing power, memory consumption, etc., and achieve low computing cost and small memory. Space, the effect of improving accuracy

Active Publication Date: 2017-09-01
ANHUI TSINGLINK INFORMATION TECH
View PDF3 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Taking the SSD300 model as an example, it needs to consume about 1.2GB of memory for target detection, and the detection time in the Intel i7CPU environment is at leas

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
  • Moving object detection method based on depth learning
  • Moving object detection method based on depth learning
  • Moving object detection method based on depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] Combine below Figure 1 to Figure 4 Shown, the present invention is described in further detail.

[0057] Such as Figure 1 to Figure 3 As shown, this embodiment discloses a method for detecting a moving target based on deep learning, which includes the following steps S1 to S2:

[0058] S1. Train the constructed deep neural network model to obtain a target neural network model capable of distinguishing meaningful moving targets;

[0059] S2. Using the target neural network model to detect a moving target from the currently collected scene image.

[0060] Among them, such as figure 2 As shown, step S1 specifically includes the following steps S11 to S13:

[0061] S11, improve based on the LeNet-5 convolutional neural network model, and construct a deep neural network model;

[0062] In this embodiment, the diversity of moving targets and the computational complexity of the convolutional neural network model are comprehensively considered, and the LeNet-5 convoluti...

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 moving object detection method based on depth learning, which belongs to the technical field of video image processing. The method comprises steps: a constructed depth neural network model is trained to obtain an object neural network model with an ability of identifying a meaningful moving object; and the object neural network model is used for detecting a moving object from the currently-acquired scene image. The depth learning technique and the inter-frame correlation information are used, the method consumes small memory space, and the moving object is detected accurately with a little computational cost.

Description

technical field [0001] The invention relates to the technical field of video image processing, in particular to a method for detecting moving objects based on deep learning. Background technique [0002] With the development and progress of society, more and more intelligent video surveillance devices have entered people's lives. Among them, moving target detection is the most important technology in intelligent video analysis algorithms, and it is also the basic technology for target tracking and target recognition. [0003] At present, the commonly used moving object detection method is based on background modeling, and the effect of detecting moving objects largely depends on the quality of the background model. Constructing a good background model is a current technical problem. The reason is that existing background modeling algorithms cannot be effectively and timely due to interferences such as light changes, camera shake, complex backgrounds, and target motion speeds...

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): G06T7/292G06T7/246G06N3/04
CPCG06T7/246G06T7/292G06T2207/30232G06T2207/20081G06T2207/10016G06N3/045
Inventor 张卡何佳尼秀明
Owner ANHUI TSINGLINK INFORMATION TECH
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