Occlusion region detection method based on image sequence optical flow and triangular mesh
A technology of triangular meshes and image sequences, applied in the field of detection, can solve the problems of robustness and accuracy of occlusion area detection, and the detection results of occluded areas do not meet actual needs, etc., and achieve high occlusion detection accuracy and reliability. , low-complexity effects
Active Publication Date: 2016-10-26
NANCHANG HANGKONG UNIVERSITY
View PDF2 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Traditional image sequence occlusion region detection methods usually adopt a strategy based on feature matching. Since the feature matching method only relies on whether a single pixel has a corresponding relationship between two consecutive frames of images to determine the occlusion of a pixel, the robustness of feature point matching And the accuracy has a great influence on the detection of occlusion areas, which often leads to the detection results of occlusion areas not meeting the actual needs
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0028] The present invention will be further described below in conjunction with drawings and embodiments. The occlusion area detection method based on image sequence optical flow and triangular mesh is explained using the RubberWhale image sequence occlusion area detection experiment:
[0029] 1) Figure 1a and Figure 1b It is two consecutive frames of RubberWhale image sequence; where: Figure 1a is the first frame image, Figure 1b is the second frame image;
[0030] figure 2 is the optical flow between two consecutive frames of the calculated RubberWhale image sequence;
[0031] 2) if image 3 As shown, the first frame image is triangulated using the Delaunay triangular mesh;
[0032] 3) Calculate the coordinates of each pixel point in the second frame image according to the result of Delaunay triangular mesh division and the optical flow between images, and establish the corresponding triangular mesh area in the second frame image according to the triangular mesh d...
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
Login to View More Abstract
The invention discloses an occlusion region detection method based on an image sequence optical flow and a triangular mesh. The occlusion region detection method comprises the steps of: calculating an optical flow between two continuous frames of an image sequence; carrying out Delaunay triangular mesh generation on a first frame image; calculating brightness variations of image pixel points and triangular regions between the two frames of images; looking for corresponding triangular regions of a second frame image according to the triangular regions of the first frame image, detecting whether an embedded pixel point exists in the corresponding triangular regions of the second frame image, and determining an occluded triangular region; determining that the embedded pixel point is occluded or the triangular region is occluded according to brightness variations of the embedded pixel point and the triangular region; and traversing all the triangular regions in the images so as to detect occlusion regions of the whole image. Compared with the existing method, the occlusion region detection method has higher precision and reliability of occlusion detection.
Description
technical field [0001] The invention relates to detection technology, in particular to an occlusion region detection method based on image sequence optical flow and triangular mesh. Background technique [0002] When there is an occlusion phenomenon in the image sequence, the pixels in the occlusion area in the image will appear "occasionally and sometimes absent" in the continuous frame images. This problem will lead to the accuracy of the image sequence moving target detection, tracking and 3D reconstruction results. Reliability is facing a big challenge. Therefore, image sequence occlusion region detection is an important research content in image processing, computer vision and other research fields, and its research results have important application significance in the fields of robot vision, UAV navigation, and vehicle assisted driving. [0003] Traditional image sequence occlusion region detection methods usually adopt a strategy based on feature matching. Since 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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/20
Inventor 张聪炫陈震和世熙汪明润江少锋
Owner NANCHANG HANGKONG UNIVERSITY