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

A Modeling Method of Dynamic Visual Sensor Sample Set Based on Frame Image

A technology of visual sensor and modeling method, which is applied in the field of image recognition, can solve problems such as the inability to quickly identify targets, and achieve the effect of meeting real-time low-power processing requirements, low latency, and fast feature extraction

Active Publication Date: 2022-04-19
WUXI RES INST OF APPLIED TECH TSINGHUA UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem that the existing technology based on convolutional neural network target recognition samples has a large amount of redundant information, which leads to the problem that the target cannot be quickly identified, the present invention provides a dynamic visual sensor sample set modeling method based on frame images, which can realize Fast extraction of moving targets, and has the advantages of low latency, low storage space and high dynamic range

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
  • A Modeling Method of Dynamic Visual Sensor Sample Set Based on Frame Image
  • A Modeling Method of Dynamic Visual Sensor Sample Set Based on Frame Image
  • A Modeling Method of Dynamic Visual Sensor Sample Set Based on Frame Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Such as Figure 1 ~ Figure 4 Shown, the present invention a kind of dynamic visual sensor sample set modeling method based on frame image, it comprises the following steps:

[0041] S1: Obtain video data to be processed;

[0042] S2: Perform pixel normalization processing and pixel light intensity accumulation processing on continuous frame images in the video data to be processed;

[0043] S3: Carry out unit discretization for the processed frame image, make each pixel unit independent of each other, and obtain a single pixel unit;

[0044] S4: For each single pixel unit, calculate according to the light intensity change range between the current frame and the adjacent frame, and judge whether the trigger threshold T is reached; when the light intensity change range reaches the trigger threshold T, update the initial state and output a single Pixel unit; if the trigger threshold T is not reached, there will be no output; the specific steps are as follows:

[0045] S...

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 invention provides a dynamic visual sensor sample set modeling method based on frame images, which can realize fast extraction of moving targets, and has the advantages of low delay, low storage space, high dynamic range and the like. It includes: S1: Acquire the video data to be processed; S2: Perform pixel normalization processing and pixel light intensity accumulation processing on the continuous frame images in the video data to be processed; S3: Perform unit discretization on the processed frame images to obtain Single pixel unit; S4: For each single pixel unit, calculate according to the light intensity change range between the current frame and the adjacent frame, and judge whether the trigger threshold T is reached; S5: According to the custom storage format, store the output in step S4 Data information corresponding to a single pixel unit; custom storage formats include: address event data corresponding to a single pixel unit; S6: All stored data information is further encoded according to actual needs to form the final sample set data.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method for modeling a dynamic visual sensor sample set based on frame images. Background technique [0002] In the field of image recognition, with the development of deep learning, convolutional neural network has become an important research content in the field of computer vision, and has excellent performance in image classification, target recognition and intelligent monitoring. However, the existing CNN-based target recognition frameworks rely on huge data sets and complex training processes. Moreover, these methods all use ordinary images as samples for calculation and processing, which contain a lot of redundant information, occupy a large storage space, and also face problems such as difficulty in separating noise and effective information. These problems make the image recognition process require high hardware configuration and power consumption to meet the...

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): G06T7/246G06T7/194G06T7/13
CPCG06T7/251G06T7/194G06T7/13G06T2207/10016
Inventor 李兆麟
Owner WUXI RES INST OF APPLIED TECH TSINGHUA 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