Extended target tracking method and device combined with framework and generalized Hough transformation

Abstract

The invention discloses an extended target tracking method and device combined with a framework and generalized Hough transformation. The method comprises the steps that denoising processing is carried out on a current frame image to obtain a filtered smooth image; target segmentation is carried out on the smooth image by adopting an OTSU method to obtain a binary target image; framework extraction is carried out on the binary target image to obtain framework feature points; the framework feature points are located and tracked through generalized Hough transformation to obtain tracking points. Compared with a previous tracking method adopting edge points for generalized Hough transformation, the complexity of the method is greatly lowered due to the adoption of the framework points. Compared with a tracking method only based on framework extraction, the obtained tracking result is more stable, and a foundation is provided for subsequent high-precision tracking.

Description

technical field [0001] The invention relates to the technical field of target detection and tracking in a photoelectric capture and tracking system, in particular to an extended target tracking method and device combined with skeleton and generalized Hough transform. Background technique [0002] In the photoelectric capture and tracking system, as the aperture of the optical system increases and the focal length becomes longer, the long-distance point target gradually presents an expanded form. Due to degrading factors such as atmospheric turbulence, system jitter, and optical system aberrations, the imaging of the target in the system is very blurred, and the target appears as a cluster of light spots in the shape of an outline; in addition, the target has no texture information, has various shapes, and has no representation and Identify the characteristic information of the target. The target also has the characteristics of obvious attitude changes. As the target attitud...

AI Technical Summary

Problems solved by technology

Since the target has no texture and significant feature information, the attitude changes greatly, and the traditional gray-scale feature-based tracking method tends to lose the target when the target has a large attitude change. In view of this situation, the skeleton extraction feature point was used later. track stretch goals

Although this method can deal with attitude changes, the skeleton can only roughly reflect the structure of the target and cannot provide rich information. Simply using a certain skeleton point for tracking will cause tracking instability, and the tracking point will jitter or even drift.

Images