Layered template matching method based on multi-dimensional pyramid

Abstract

The invention discloses a layered template matching method based on a multi-dimensional pyramid. The method comprises the steps of clustering template data rendered offline according to viewpoint parameters during rendering, a pyramid structure under multiple dimensions is established, efficiency optimization in the matching process is achieved, and the method comprises the following steps of 1, in the offline generation process, obtaining a color map and a depth map; 2, constructing a multi-dimensional template pyramid; 3, in the online matching process, obtaining an input feature map; 4, obtaining a high-level matching result; 5, obtaining an approximate interval where the object is located, and taking the approximate interval as an ROI on the two-dimensional image; 6, performing a matching test on the template corresponding to the low-level pyramid; and 7, carrying out random sampling consistent detection on the matched attitude to obtain a final detection and attitude estimation result of the object. According to the method, the CAD model is used, the method is suitable for industrial application, quick query can be realized, and the balance between the matching speed and the matching precision is ensured.

Description

technical field [0001] The invention relates to the field of object detection and its six-degree-of-freedom attitude estimation method, in particular to a layered template matching method based on a multidimensional pyramid. Background technique [0002] Object Recognition and 6D Pose Estimation (Object Recognition and 6D Pose Estimation) is a key issue in machine vision technology. The goal is to provide the robot with information to operate the target object, and to solve the problem of what the object is and where it is. The 6D attitude acquired by the target here is the transformation between the object coordinate system and the visual sensor (camera) coordinate system, which is composed of 3D translation transformation and 3D rotation transformation. At present, object recognition and 6D attitude estimation are still important and challenging topics in the practical application of many robots, and they are also key technologies for industrial robots to complete intellig...

AI Technical Summary

Problems solved by technology

However, when the scale is unknown and the change range of the object pose is large, the number of templates can reach tens of thousands, so the poor real-time performance restricts its application in the industrial field.

Images