A panoramic motion detection method and device

A motion detection and panorama technology, applied in the field of motion detection, can solve the problem of inaccurate motion detection, achieve accurate motion detection, overcome the inaccurate problem of motion detection, and achieve the effect of accurate motion detection

Active Publication Date: 2021-03-19
成都易瞳科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Based on the problem of inaccurate motion detection introduced by the image formed by the panoramic lens, which is different from the image formed by the ordinary camera, the present invention provides a panoramic motion detection method and device

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 panoramic motion detection method and device
  • A panoramic motion detection method and device
  • A panoramic motion detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] like figure 1 , figure 2 As shown, the motion detection method includes steps when the input is double fisheye:

[0060] 1. Obtain the center and radius of the two fisheye images from the images captured by the dual fisheye panoramic camera;

[0061] 2. Compare and calculate the images collected by the panoramic camera, and get the guess value of whether the corresponding area moves;

[0062] 3. Combined with the pre-defined weights, the guessed values ​​collected in the previous step are weighted;

[0063] 4. When the calculation result exceeds the threshold, it prompts that the panoramic camera is moving and passes on the moving area;

[0064] 5. Project the moving area into the spliced ​​2:1 panoramic image, and perform distortion correction on the area;

[0065] 6. Perform operations such as identification, video recording, photo taking, and prompting the user;

[0066] 7. The process ends.

Embodiment 2

[0068] Corresponding to the monitoring camera, the operation process includes:

[0069] 1. The motion detection algorithm first reads the pre-identified fisheye circle center and radius from the camera;

[0070] 2. Comparing and calculating the collected images to obtain the guess value of whether the corresponding area moves;

[0071] 3. According to the camera's compensation for the captured fisheye image, obtain the weighted value for judging whether to move;

[0072] 4. When the weighted value is greater than the threshold, it is considered that there is movement, and the camera is notified;

[0073] 5. The camera receives the incoming moving signal, maps the moving part to the 2:1 panoramic image stitched by the fisheye image, and frames and identifies the moving part;

[0074] 6. The camera takes pictures, records videos, prompts users and other operations;

[0075] 7. End.

Embodiment 3

[0077] like image 3 , Figure 4 As shown, the process of a panoramic camera whose input video is a 2:1 panoramic image includes:

[0078] 1. Comparing and calculating the input panoramic video to obtain the guess value of whether each area moves;

[0079] 2. Combine the weights of each area to obtain a judgment result of whether the overall panoramic video is moving. If there is movement, notify the camera and perform relevant operations;

[0080] 3. The camera receives the incoming mobile signal, performs operations such as frame selection, highlighting and identification of the moving part, takes pictures, records videos, and prompts the user;

[0081] 4. End.

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 field of moving detection, and discloses a panoramic moving detection method. The panoramic moving detection method sequentially comprises the following steps: 1, obtaining a fisheye image video or a panoramic 2: 1 image; 2, performing comparison and calculation on collected images, specifically, calculating by employing universal moving detection to obtain a predictedvalue on whether each area is moved or not; 3, calculating weight compensation values of different areas to obtain weights of the different areas; and 4, performing weighted calculation on the predicted values and the weights, and judging whether the predicted values and the weights exceed a threshold value or not, if no, ending a process, and if yes, when a double fisheye image is input, projecting a moving area to a spliced panoramic image, and when a panoramic image is input, displaying a moving detection result. According to the panoramic moving detection method, the moving detection of apanoramic lens can be implemented, and different weight compensations are provided for a panoramic camera according to different output results, so the problem that the moving detection is inaccuratedue to differences between a panoramic image generated by the panoramic camera and common imaging is overcome, and the accurate moving detection is effectively implemented.

Description

technical field [0001] The invention relates to the field of motion detection, and relates to an illumination compensation scheme and a weight compensation scheme for different imaging positions, and specifically refers to a panoramic motion detection method and device. Background technique [0002] At present, the motion detection of ordinary surveillance cameras is mainly through the background detection and calculation of each area of ​​the captured image after the rectangular partition, and then the identification of the moving area is given to realize the detection of moving objects. [0003] For a panoramic lens composed of double fisheyes, the captured images are different from ordinary lenses in the following aspects: [0004] One is that the collected image is circular, and there are some invalid images in the image, so there is no need to perform motion detection on this part; [0005] The second is that there is a large distortion in the fisheye lens, which cause...

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): H04N5/14H04N5/76H04N7/18
CPCH04N5/144H04N5/76H04N7/18
Inventor 张恩泽赖文杰胡志发成茵余黎
Owner 成都易瞳科技有限公司
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