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

Rescue task crowd map splicing system and method based on custom descriptor

A self-defined and descriptor technology, applied in the field of rescue mission crowd map stitching system, can solve the problems of unable to estimate the crowd to be rescued, and not making full use of crowd information, so as to reduce the amount of calculation, ensure effectiveness, and ensure accuracy Effect

Pending Publication Date: 2022-06-28
TONGJI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, for our scale cognitive tasks, the feature points of the existing methods are automatically generated, and the key crowd information is not fully utilized, so it is impossible to efficiently estimate the global population to be rescued

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
  • Rescue task crowd map splicing system and method based on custom descriptor
  • Rescue task crowd map splicing system and method based on custom descriptor
  • Rescue task crowd map splicing system and method based on custom descriptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] A crowd map stitching method for rescue missions based on custom descriptors, including:

[0074] Step S1: obtaining map data to be spliced;

[0075] Step S2: Detect the pedestrian position of the map data to be spliced;

[0076] Step S3: Generate a custom descriptor according to the detected pedestrian position and a descriptor to be spliced. The custom descriptor can effectively stitch pictures with less overlap and is robust to maps with sparse textures and has high accuracy , better application generalization and environmental requirements;

[0077] Step S4: For all the pictures to be spliced, the number of descriptors is detected for pairwise matching;

[0078] Step S5: Use the RANSAC algorithm to perform transformation estimation splicing and verification on the images according to the matching logarithm in descending order. The verification process can effectively correct the splicing results of the images that fail to match, and reduce the impact of difficult-...

Embodiment 2

[0114] The rescue mission crowd map splicing system based on the self-defined descriptor can realize the rescue mission crowd map splicing method based on the user-defined descriptor described in the first embodiment, including:

[0115] Data acquisition module: used to acquire map data to be spliced;

[0116] Detection module: used to detect the pedestrian position of the map data to be spliced;

[0117] Descriptor generation module: used to generate a custom descriptor and a descriptor to be spliced ​​according to the detected pedestrian position;

[0118] Matching module: used to detect the number of descriptors for pairwise matching of all images to be spliced;

[0119] Splicing verification module: It is used to perform transformation estimation splicing and verification on the image according to the matching logarithmic descending order.

Embodiment 3

[0121] The embodiment of the present invention also provides a rescue mission crowd map splicing device based on a custom descriptor, which can implement the custom descriptor-based rescue mission crowd map splicing method described in Embodiment 1, including a processor and a storage medium;

[0122] the storage medium is used for storing instructions;

[0123] The processor is configured to operate in accordance with the instructions to perform the steps of the following methods:

[0124] Obtain the map data to be spliced;

[0125] Detect the pedestrian position of the map data to be spliced;

[0126] Generate a custom descriptor and a descriptor to be spliced ​​according to the detected pedestrian position;

[0127] For all the images to be spliced, the number of matching detection descriptors is detected in pairs;

[0128] According to the matching logarithmic descending order, the images are transformed, estimated, stitched and verified.

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 rescue task crowd map splicing system and method based on a user-defined descriptor in the technical field of image splicing. The method comprises the following steps: acquiring to-be-spliced map data; detecting a pedestrian position of the to-be-spliced map data; generating a user-defined descriptor according to the detected pedestrian position and generating a descriptor according to the to-be-spliced picture; matching and detecting the number of descriptors in pairs for all to-be-spliced pictures; and carrying out transformation estimation splicing and verification on the images according to a matching logarithm descending order. The user-defined descriptor is based on the detected crowd information, the crowd information can be fully utilized, and the global situation can be perceived more efficiently.

Description

technical field [0001] The invention relates to a rescue mission crowd map stitching system and method based on self-defined descriptors, and belongs to the technical field of image stitching. Background technique [0002] Image stitching is a subtask of computer vision, and is often used in satellite image fusion, panoramic image generation and other fields. Situational awareness is an environment-based, dynamic, and holistic ability to gain insight into security risks. Based on security big data, it is a way to improve the ability to discover, identify, understand, analyze, and respond to security threats from a global perspective. It is for decision-making and action, and it is the landing of security capabilities. Among them, the cognition of crowd size in emergency situations can be regarded as an important part of situational awareness. Specifically, the task is defined as for a given number of local pictures of people to be rescued, we need to perceive the global sc...

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): G06T3/40G06T5/50G06T7/70G06T17/20
CPCG06T3/4038G06T5/50G06T17/20G06T7/70
Inventor 李莉张淼林国义衣鹏龚炜于青云
Owner TONGJI 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