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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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 ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


