Unlock instant, AI-driven research and patent intelligence for your innovation.

Model construction method, pose estimation method and object picking device

A construction method and pose estimation technology, applied in the field of image processing, can solve the problems of limited representation ability of complex functions, lack of three-dimensional information of workpieces, hidden dangers, etc., to achieve adaptive grasping operation, improve sorting and picking ability, The effect of improving performance

Pending Publication Date: 2021-06-25
SHENZHEN HUAHAN WEIYE TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In recent years, with the rapid development of deep learning technology, the pose estimation technology based on deep learning has become the mainstream algorithm in the field of pose estimation, but most of the existing mainstream pose estimation algorithms based on deep learning rely on the Information such as color and texture has a poor recognition effect on parts with low texture and reflective surfaces in the industry, which hinders the realization of efficient automatic sorting of parts
[0004] At present, the relatively mature artificial intelligence-based machine vision grasping method is to predict the pose of the workpiece based on the two-dimensional images collected by the camera, but this method often lacks the three-dimensional information of the workpiece, and can only achieve two-dimensional pose estimation
Traditional reinforcement learning methods have great limitations when solving high-dimensional state and action space problems. Under the condition of limited samples and computing units, the ability to express complex functions is limited, and the performance in practical applications is often not ideal.
At the same time, the traditional deep reinforcement learning algorithm needs to provide a large amount of data for training. During the training process, the robot needs to continuously grasp and try and make mistakes, so that it is possible to obtain a stable picking ability; this training method has a long cycle and low efficiency. There are potential safety hazards in the actual training process, which often cannot meet the needs of industrial production applications

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Model construction method, pose estimation method and object picking device
  • Model construction method, pose estimation method and object picking device
  • Model construction method, pose estimation method and object picking device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Please refer to figure 1 , the present application discloses a method for estimating the pose of a target object, which includes steps S110-S130, which are described below.

[0046] Step S110, acquiring the scene image of the target object.

[0047] It should be noted that the target object in this embodiment may be a product on an industrial assembly line, a mechanical part in an object box, a tool on an operating table, etc., for example Figure 9 Irregularly shaped mechanical parts in a toolbox. Then, the scene image of the target object can be acquired through imaging devices such as cameras and visual sensors.

[0048] It can be understood that the scene image of the target object refers to the two-dimensional imaging results and three-dimensional imaging results of the target object in a simple or complex scene, such as RGB-D data (ie, the registration data of the color map and the depth map), the scene The image not only includes the target object, but may als...

Embodiment 2

[0061] Please refer to Figure 5 , this embodiment discloses a method for constructing a pose estimation model, which includes steps S210-S230, which are described below.

[0062] Step S210, acquiring densely fused data of the target object, where the densely fused data is obtained by fusion of two-dimensional image data and three-dimensional point cloud data of the target object through heterogeneous fusion. Two-dimensional image data and three-dimensional point cloud data are heterogeneous data located in different feature spaces, so the heterogeneous network can be used to process these two data separately, so as to preserve the structure of the two data at the same time, and make full use of object depth information and Based on the respective advantages of object image information, the surface feature points of the target object can be accurately represented with the help of dense fusion data.

[0063] It should be noted that the target object here may be a product on an...

Embodiment 3

[0110] Please refer to Figure 9 , this embodiment discloses an acquisition device for a target object, which mainly includes a sensor 41, a processor 42, a controller 43 and a motion mechanism 44, which will be described separately below.

[0111] The sensor 41 is used to collect the scene image of the target object. For the description of the scene image, please refer to the relevant content in the first embodiment above. The sensors 41 here may be some visual sensors with image acquisition functions, such as camera equipment and laser scanning equipment. The target object here may be a product on an industrial assembly line, a mechanical part in an object box, a tool on an operating table, etc., and is not specifically limited.

[0112] Processor 42 is connected to the sensor. The processor 42 is configured to output category information and pose information of the target object through the pose estimation method disclosed in Embodiment 1. For the extraction 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
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a model construction method, a pose estimation method and an object picking device. The model construction method comprises the following steps: acquiring dense fusion data of a target object; training a preset network model according to the dense fusion data, and learning to obtain a network weight parameter; forming a pose estimation model of the target object according to the network weight parameter configuration, wherein the network model comprises a backbone node layer and a head node layer, the head node layer comprises a classification layer and a regression layer, the backbone node layer is used for constructing high-level semantic information of a target object according to dense fusion data, the classification layer in the head node layer is used for processing the high-level semantic information to judge the category and score of the target object, and the regression layer in the head node layer is used for processing the advanced semantic information to predict the pose and confidence of the target object. According to the technical scheme, the panoramic information reconstruction capability of the pose estimation model on a detection scene with complex background and strong interference can be improved, so that the pose detection capability of the target object is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a model building method, a pose estimation method and an object picking device. Background technique [0002] In today's manufacturing industry, the assembly process takes a lot of time and money. In order to improve production efficiency and reduce labor costs, people have begun to explore the use of robots to realize automated assembly. As an indispensable and important link in the automated assembly process, part recognition and grasping position planning have a vital impact on the quality of assembly. Vision-based part pose determination and grasping position planning can significantly improve the automation of product assembly. Flexibility, reduce time-consuming and reduce costs, thereby improving manufacturing efficiency. Robotic automated assembly involves two key technologies: part recognition and automatic grasping. [0003] Computer vision technology plays an...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/70G06K9/00G06K9/62G06N3/08G06T5/50
CPCG06T7/70G06T5/50G06N3/08G06T2207/20081G06T2207/20084G06T2207/20221G06V20/64G06F18/25G06F18/241G06F18/214
Inventor 杨洋
Owner SHENZHEN HUAHAN WEIYE TECH