Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Motion detection method based on pulse array

A technology of motion detection and pulse, which is applied in the field of motion detection based on pulse array, can solve the problems of not taking advantage of the advantages of time and space of pulse sequence

Pending Publication Date: 2021-07-13
PEKING UNIV
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This processing method does not take advantage of the spatio-temporal advantages of the pulse sequence, and also needs to convert the spatio-temporal sequence into a picture frame and then process it in the same way as the traditional 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
  • Motion detection method based on pulse array
  • Motion detection method based on pulse array
  • Motion detection method based on pulse array

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] This application provides a motion detection method based on pulse array, such as figure 1 As shown, the application provides a motion detection method based on a pulse array, comprising the following steps:

[0037] Collect spatio-temporal signals in the monitoring area to generate spatio-temporal pulse arrays;

[0038] The spatiotemporal pulse array is input into the spiking neural network, and the spiking neurons in the spiking neural network process the spatiotemporal pulse sequence with motion characteristics and generate corresponding pulses;

[0039] The motion information of different spatial positions is obtained according to the pulses generated by the spiking neural network.

[0040] The impulse neural network includes a feature extraction layer and a motion detection layer. The feature extraction layer detects motion patterns and obtains pulse sequences corresponding to different motion features. The motion detection layer detects motion models according to...

Embodiment 2

[0059] This application provides a motion detection method based on a pulse array. First, the optical signals of each spatial position in the monitoring area are collected, and at the same time, the signals of each spatial position are accumulated to obtain the signal cumulative intensity value; once a certain space When the signal cumulative strength value of the position exceeds the preset emission threshold, a pulse signal is output; the pulse signals corresponding to each spatial position are arranged into a binary sequence according to time, and the binary sequences corresponding to all spatial positions form a pulse array. image 3 It is a flow chart of motion detection of three-dimensional spatiotemporal pulse array, such as image 3 As shown, the temporal filter processing method based on the short-term plasticity model includes the following steps:

[0060] Step 1, input a two-dimensional array formed by the pulse array at each moment into the input layer; an example ...

Embodiment 3

[0072] The pulse array-based motion detection method proposed in this application currently has another retina-like camera that can generate pulse event signals. The processing flow is as follows: Figure 4 shown. Dynamic Vision Sensor (Dynamic Vision Sensor, DVS) is a visual sensor that imitates the sensitive mechanism of retinal peripheral cells to brightness changes. It generates On events and Off events by judging whether the brightness changes exceed a certain threshold. On events indicate that the threshold changes exceed a certain positive value, and Off events The event indicates that the threshold change is lower than a certain negative value; the pulse generated by DVS is expressed in the address event form of (x, y, t, p) quadruple, (x, y) is the two-dimensional spatial position of the pulse emission, and t is The timestamp of this pulse event, p represents the event polarity (On or OFF, represented by "1" and "-1" respectively). When using the pulse event generate...

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 the technical field of motion detection, in particular to a motion detection method based on a pulse array. The method comprises the following steps: collecting space-time signals of a monitoring area to generate a space-time pulse array; inputting the space-time pulse array into a pulse neural network, wherein pulse neurons in the pulse neural network process a space-time pulse sequence with motion characteristics and generate corresponding pulses; and obtaining motion information of different spatial positions according to the pulses generated by the pulse neural network. According to the method, the time-space characteristics of the pulse array obtained by the high-frequency retina camera are utilized, the visual pulse sequence is directly used as input, various motion states existing in the monitoring area are obtained, parameter information corresponding to the motion states is obtained, the output motion information can be used for object tracking, motion compensation and the like, and the accuracy of motion compensation is improved. Therefore, subsequent high-level visual tasks such as detection, recognition and tracking of high-speed visual objects based on pulse signals are facilitated.

Description

technical field [0001] The present application relates to the technical field of motion detection, and more specifically, the present application relates to a motion detection method based on a pulse array. Background technique [0002] In recent years, a lot of research progress has been made in the neural vision sensor, which is different from the traditional camera. It imitates the principle of the biological retina to generate pulse signals according to the external lighting environment, and generates pulse signals based on the changes in the light signals sampled in the monitoring area. This signal sampling mechanism has the advantages of low power consumption, high dynamic range and high time resolution, that is, it can obtain signal changes under extreme lighting conditions, and output pulses at a sampling frequency far exceeding that of traditional cameras (30 frames per second). Signal. This brain-like visual information representation method encodes more temporal ...

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): G06T7/246G06N3/04G06N3/08
CPCG06T7/246G06N3/049G06N3/08G06T2207/20081G06T2207/20084G06T2207/30232
Inventor 黄铁军郑雅菁余肇飞田永鸿
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com