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

Conversion event linear detection method based on pulse type image sensor

An image sensor, a technology for transforming events, applied in instruments, computer parts, character and pattern recognition, etc., can solve problems such as low computing efficiency, achieve high-speed detection, and increase adaptability.

Active Publication Date: 2021-03-05
TIANJIN UNIV MARINE TECH RES INST
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

After the appearance of the address-event sensor, there has also been an event-based line detection method, which usually requires a cache to store the entire frame of data, and when the scene changes drastically and the number of events increases, the invalid time will occupy a large amount of resources in the cache, resulting in calculation low efficiency

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
  • Conversion event linear detection method based on pulse type image sensor
  • Conversion event linear detection method based on pulse type image sensor
  • Conversion event linear detection method based on pulse type image sensor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will give a specific description of the implementation of the present invention in conjunction with examples.

[0024] as attached figure 1 As shown in , a straight line indexed by superscript (i) L (i) (ρ k (i) ,θ k (i) ) consists of two features: ρ k (i) represents the distance from the line to the origin, θ k (i) represents the line n k (i) angle with the horizontal direction. When a new event arrives, use the following two conditions to judge which line it belongs to before: (1) The distance d from the point where the event occurs to the line k (i) , (2) The angle between the normal phase of the straight line and the event direction α k (i) . The actual operation steps of line detection are as follows:

[0025] 1. Adjust the data format and organize the data into a directional event form, ie o k = [u k T ,v k T , t k ,p k...

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 conversion event linear detection method based on a pulse type image sensor. The method comprises the steps: converting a high-speed pulse into an event signal with a direction, achieving the linear parameterization through employing a least square method, calculating the activity, and judging whether an event belongs to a straight line or not. According to the method, each incoming event is fitted to a straight line by using an iterative weighted least square method, and the past event weight is attenuated exponentially, so that the algorithm can be kept effective ina violent change scene. The detection algorithm is suitable for parallelism, can be applied in real time and achieves image detection, recognition and tracking accurate to pixel points.

Description

technical field [0001] The invention relates to the field of image processing algorithms, in particular to a dynamic object detection method for a pulsed image sensor, that is, a conversion event line detection method based on a pulsed image sensor. Background technique [0002] Pulse-type high-speed image sensors have great advantages in shooting complex and high-speed changing scenes, and can be used in flight detection systems for robots and drones. Extracting straight lines from man-made environments is the basic work of machine vision, and is often used in robot recognition paths and various pattern recognition scenarios. Commonly used detection methods include classic methods based on Huffman transform, methods based on gradients, and methods based on statistics. After the appearance of the address-event sensor, there has also been an event-based line detection method, which usually requires a cache to store the entire frame of data, and when the scene changes drastic...

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): G06K9/00G06F17/11
CPCG06F17/11G06V20/00
Inventor 徐江涛张培文王相锋聂凯明高静
Owner TIANJIN UNIV MARINE TECH RES INST
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