Target recognition system and method based on time slice convolutional neural network

A convolutional neural network and time slicing technology, applied in biological neural network models, neural architectures, character and pattern recognition, etc., to improve recognition efficiency and accuracy

Pending Publication Date: 2021-11-09
NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The challenge of this problem is how to integrate with the original deep learning method and be effectively compatible

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 recognition system and method based on time slice convolutional neural network
  • Target recognition system and method based on time slice convolutional neural network
  • Target recognition system and method based on time slice convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0049] Example 1:

[0050] Based on time-slicing target convolutional neural network recognition systems, such as figure 1 As shown, the system includes:

[0051] Dividing module 101 event stream, the event stream samples for slicing, forming a set of events, the event by the event collection is represented in a pseudo image as the dummy image in a time slice convolutional neural network input channel to the first splice feature FIG re-assigned a different weight for each channel to obtain a second characteristic diagram;

[0052] Feature extraction module 102, a second feature of an input to the convolutional neural network in the time slice feature extraction becomes the predetermined specification is characterized in FIG;

[0053] Classification module 103, wherein the predetermined specification is for converting a vector in FIG obtain maximum probability category, the recognition result as a target.

[0054] Specifically, the stream event be segmented to form a set of events, c...

Example Embodiment

[0072] Example 2:

[0073] An object identification system time slicing based on convolutional neural network, such as still figure 1 Shown, the system comprising: a segmentation module 101 an event stream, the event stream samples for slicing, forming a set of events, the event by the event collection is represented in a pseudo image as the dummy image slices convolutional neural network in a time splicing a first input channel characteristic diagram, again for each channel assigned different weights, to obtain a second characteristic diagram; feature extraction module 102, a second feature of an input to the convolutional neural network in the time slice feature extraction FIG characteristic becomes the predetermined specification; classification module 103, configured to convert the predetermined specification is characterized FIG vector, the probability of obtaining the largest category, the recognition result as a target.

[0074] Preferably, the slicing event stream during e...

Example Embodiment

[0082] Example 3:

[0083] Based on time-slicing convolutional neural network object recognition method, such as image 3 As shown, including the following steps:

[0084] Sl, the dicing step event stream, the event stream samples sliced, forming a set of events, the event represented by a set of event representation to pseudo image, the pseudo-image in a time slice convolutional neural network input channel to splice FIG first feature, re-assigned a different weight for each channel to obtain a second characteristic diagram;

[0085] S2, feature extraction step, wherein the second time slice of an input to the convolutional neural network feature extraction becomes the predetermined specification is characterized in FIG;

[0086] S3, the classification step, wherein the predetermined specification is converted FIG vector, the probability of obtaining the largest category, the recognition result as a target.

[0087] As an embodiment of the convertible, based on the time slicing co...

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 relates to a target recognition system and method based on a time slice convolutional neural network. The system comprises an event stream segmentation module used for segmenting an event stream sample to form an event set, representing the event set into pseudo images through an event representation method, splicing the pseudo images into a first feature map according to time slice convolutional neural network input channels, and then assigning different weights to each channel again to obtain a second feature map; a feature extraction module which is used for inputting the second feature map into a time slice convolutional neural network for feature extraction to obtain a feature map of a preset specification; and a classification module which is used for converting the feature map of the preset specification into a vector to obtain a target recognition result. According to the method, the event stream is segmented by using the time correlation of the event stream, and meanwhile, the method is fused with an original deep learning method and is effectively compatible with all event representation methods for target recognition, so that the recognition efficiency and precision are improved.

Description

technical field [0001] The present application relates to the technical field of target recognition, and more specifically, the present application relates to a target recognition system and method based on a time-sliced ​​convolutional neural network. Background technique [0002] Event camera is a new type of neuromorphic vision sensor, also known as dynamic vision sensor. It captures dynamic changes in the scene based on an event-driven approach and responds to pixel-level brightness changes. It has the advantages of low latency, low power consumption, high dynamic range, and high time resolution. It has attracted more and more attention from people inside and outside the industry. support. With the development of convolutional neural networks, computer vision methods have made great progress. However, due to the sparsity and asynchrony of event streams, traditional computer vision algorithms cannot be directly applied, and existing methods are mainly divided into metho...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/2415G06F18/214
Inventor 史殿习徐化池张拥军王之元沈天龙凡遵林
Owner NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI
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