Unlock instant, AI-driven research and patent intelligence for your innovation.

An Object Trajectory Proposal Method Based on Hierarchical Spatiotemporal Region Merging

A hierarchical and regional technology, applied in the field of computer vision, can solve the problems of not considering the characteristics of video changes, poor object trajectory proposal, etc., achieve high average trajectory intersection ratio and recall rate, and improve the effect

Active Publication Date: 2022-06-21
NANJING UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The problem to be solved by the present invention is: the existing object trajectory proposal method mainly relies on the image proposal, and then derives the video from the image, without considering the changing characteristics of the video, and failing to use the spatiotemporal characteristics of the entire video to estimate the object-likeness, resulting in Object trajectory proposals do not perform well

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
  • An Object Trajectory Proposal Method Based on Hierarchical Spatiotemporal Region Merging
  • An Object Trajectory Proposal Method Based on Hierarchical Spatiotemporal Region Merging
  • An Object Trajectory Proposal Method Based on Hierarchical Spatiotemporal Region Merging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention proposes an object trajectory proposal method based on hierarchical spatiotemporal region merging, such as figure 1 shown, including the following steps:

[0038] 1) Construct a hierarchical spatiotemporal region representation of video by matching hierarchical video frame regions of adjacent frames:

[0039] 1.1) Use an ultra-segmented contour map (ultrametric contour map) method on each video frame f to divide the video frame into a plurality of basic video frame areas, as the leaf node area in the hierarchical video frame area representation, the leaf node area The set formed is L f , where the video frame area refers to the area segmented on the video frame, and the segmentation result of the super-segmented contour map method is a small area, that is, the leaf node area, see Reference [2] for details. Iteratively merge adjacent and similar video frame areas, where the video frame area includes the leaf node area and the merged video frame are...

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

An object trajectory proposal method based on hierarchical spatio-temporal region merging, constructing a hierarchical spatio-temporal region representation of the video by matching the hierarchical video frame regions of adjacent frames on the video, and then generating candidate object trajectories by merging the hierarchical spatio-temporal regions, Finally, a comprehensive scoring mechanism that combines appearance similarity and motion similarity is used to score candidate object trajectories, and the candidate object trajectories with the highest scores are used as the final object trajectory proposal results. The method of the invention combines the appearance information and motion information of the object in the video, and utilizes the spatio-temporal characteristics of the entire video to generate object trajectory proposal results, and achieves better results than the existing methods.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and relates to an object trajectory proposal method for video, in particular to an object trajectory proposal method based on hierarchical spatiotemporal region merging Background technique [0002] The goal of object trajectory proposal is to identify regions in a video that may contain objects with a limited number of bounding box sequences. As a basic technology in the field of computer vision, this technology can be widely used in video-oriented object recognition, motion recognition, object segmentation, content retrieval and other fields. It is an important and novel research direction. [0003] The basic strategy of the existing object trajectory proposal methods is to use the image object proposal method on one or several frames of the video to obtain the bounding box that may contain objects on a single video frame, and then use the object tracker on the remaining video frames. ...

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): G06T7/215G06T7/246
CPCG06T7/215G06T7/246G06T2207/10016
Inventor 任桐炜武港山孙旭王元天
Owner NANJING UNIV