Object recognition and positioning method and device and terminal equipment
A technology of object recognition and positioning method, applied in three-dimensional object recognition, character and pattern recognition, image data processing and other directions, to achieve the effect of improving efficiency, good robustness and improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0032] figure 1 It shows a schematic flowchart of the first object recognition and positioning method provided by the embodiment of the present application, and the details are as follows:
[0033] In S101, acquire the two-dimensional image and point cloud data of the area to be measured.
[0034] The area to be detected is an area containing several objects to be identified, and multiple objects to be identified may exist in this area at the same time. For ease of description, the object to be identified is referred to as a target object hereinafter. The two-dimensional image of the area to be measured can be collected by a depth camera (such as an RGBD camera) that can collect two-dimensional images, or it can be acquired by an ordinary camera. The two-dimensional image contains the two-dimensional shape information of the object in the area to be measured . The point cloud data of the area to be measured can be directly collected by the depth camera, or can be converted ...
Embodiment 2
[0071] figure 2 It shows a schematic flowchart of the second object recognition and positioning method provided by the embodiment of the present application, and the details are as follows:
[0072] In S201, acquire the two-dimensional image and point cloud data of the area to be measured.
[0073] S201 in this embodiment is the same as S101 in the previous embodiment. For details, please refer to the relevant description of S101 in the previous embodiment, and details are not repeated here.
[0074]In S202, the two-dimensional image is detected by using a pre-trained deep learning model, and the two-dimensional target area and geometric shape type corresponding to the target object in the two-dimensional image are identified.
[0075] S202 in this embodiment is the same as S102 in the previous embodiment. For details, please refer to the relevant description of S102 in the previous embodiment, and details are not repeated here.
[0076] In S203, the two-dimensional target ...
Embodiment 3
[0106] image 3 It shows a schematic structural diagram of an object recognition and positioning device provided by the embodiment of the present application. For the convenience of description, only the parts related to the embodiment of the present application are shown:
[0107] The object identification and positioning device includes: a first acquisition unit 31 , an identification unit 32 , a rough segmentation unit 33 , and a positioning unit 34 . in:
[0108] The first acquisition unit 31 is configured to acquire the two-dimensional image and point cloud data of the region to be measured.
[0109] Optionally, the first acquisition unit includes a first acquisition module and a point cloud data generation module:
[0110] The first acquisition module is used to acquire a color map and a depth map of the area to be tested, wherein the color map is a two-dimensional image of the area to be tested;
[0111] A point cloud data generating module, configured to generate po...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More