Real-time vanishing point detection method, device and equipment, and storage medium

Abstract

The invention discloses a real-time vanishing point detection method, device and equipment, and a storage medium. The method comprises the following steps: randomly extracting N line segments from edge line segments, and forming a sample set of sampling line segments; creating a group of M voting areas for each sampling line segment, and setting M voting boxes; enabling the edge line segments to sequentially intersect with the extension line of each sampling line segment one by one, and throwing the tickets to a ticket box corresponding to an interval to which the extension line of the sampling line segment belongs at the intersection point position; executing multiple rounds of vanishing point detection, and counting votes of each voting box in each round to obtain a peak vote number; judging whether the peak vote number is greater than a threshold or not; if so, obtaining the initial position of the vanishing point according to the voting box corresponding to the peak vote number, performing accurate positioning on the vanishing point, removing the vote number thrown by the line segment in the current vanishing point office from the related voting box, and performing the next round of vanishing point detection; and if not, ending the multi-round vanishing point detection process. One or more vanishing points existing in any digital image can be detected in real time.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a real-time vanishing point detection method, device, equipment and storage medium. Background technique [0002] A group of parallel lines in three-dimensional space converges to a common point on the image plane. This common point is also called the vanishing point because it is equivalent to the infinite point of the set of parallel lines in the world coordinate system. Vanishing points contain important perspective projection transformation information. The position of the vanishing point in the image domain completely determines the direction of a set of parallel lines in three-dimensional space. Furthermore, vanishing points formed by sets of coplanar parallel lines are collinear. Vanishing point detection is widely used in camera calibration, 3D reconstruction, virtual reality, robot navigation and scene tracking, vehicle automatic driving and other fields. It is an impor...

AI Technical Summary

Problems solved by technology

However, methods based on random sampling consensus algorithms are hampered by the non-exhaustive nature of the selected minimum sample set, leading to a high risk of missed vanishing point detection when the target vanishing point is underestimated or completely missing in the selected sample set

In addition, methods based on random sampling consensus algorithms are usually also affected by computational complexity and high storage requirements for processing the selected minimum sample set, often resulting in insufficient detection speed

The common disadvantage of the above methods and other existing vanishing point detection techniques is low processing efficiency, and each state-of-the-art algorithm takes more than 1 second for a single image of 640×480 pixels, which makes them unsuitable for real-time applications such as camera calibration, 3D Reconstruction, Virtual Reality, Robot Navigation and Scene Tracking

Images