Method for predicting real-time pose of target object based on two-dimensional image of target object

Abstract

The invention belongs to the related technical field of pose prediction, and discloses a method for predicting a real-time pose of a target object based on a two-dimensional image of a target object.The method comprises the following steps: (1) respectively constructing a target segmentation network model and a target pose prediction network model, including: acquiring a plurality of two-dimensional images containing a plurality of target objects by using an RGB camera after internal reference calibration to obtain a target segmentation data set, determining a target segmentation network model, and training the target segmentation network model by using the target segmentation data set; (2) inputting a two-dimensional image of a target object obtained in real time into the target segmentation network model, and outputting a target mask by the target segmentation network model; and (3) inputting the processed target mask into a target pose prediction network model, wherein the target pose prediction network model performs pose prediction on a target object based on the received target mask. According to the invention, the applicability is improved, and the flexibility is better.

Description

technical field [0001] The present invention belongs to the related technical field of pose prediction, and more specifically relates to a method for predicting a real-time pose of a target object based on a two-dimensional image of the target object. Background technique [0002] Machine vision is a common technology for smart devices to perceive the surrounding environment. It is widely used in many fields such as robot operation, workpiece detection, and intelligent navigation. Using machine vision to enhance the environmental interaction capabilities of smart devices has important practical significance for smart manufacturing. Among them, the real-time detection and pose estimation of three-dimensional target objects has always been the core technology in the field of machine vision, but there are problems such as viewing angle changes, illumination changes, background interference, and target objects being occluded in complex environments, which greatly improves the abi...

AI Technical Summary

Problems solved by technology

However, in some scenarios, it is not easy to obtain the depth information of the environment or the quality of the obtained depth information is low: for example, the common depth sensors used in outdoor environments cannot obtain complete depth information; some embedded systems are limited due to space and cost requirements. It will limit the number and size of sensors used, and it cannot be equipped with depth sensors; another example is in the underwater operating environment, due to changes in the water column and its scattering characteristics, the collected depth information will contain more noise and be relatively sparse

Images