Indoor mobile robot glass detection and map updating method based on depth image restoration
A mobile robot and depth image technology, applied in surveying and navigation, instruments, measuring devices, etc., can solve the problems that the map cannot show glass obstacles and affect the positioning and navigation planning work, and achieve safe and stable navigation functions and low system perception costs. low effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0056] Embodiment 1: The present invention provides a method for glass detection and map updating of an indoor mobile robot based on depth image restoration, the process of which is as follows figure 1 shown. The specific steps are:
[0057] S1: Process lidar information, obtain intensity data, and screen areas suspected of having glass based on the intensity data;
[0058]S2: Select the RGBD camera image based on the information of the area where glass is suspected to exist, use the convolutional neural network to identify the RGBD camera image, and judge whether there is glass in the area, define the absence of glass as the first category, and define the presence of glass as the second category Class II situation;
[0059] S3: When the result is the first type of situation, the map is updated normally without repairing;
[0060] S4: When the result is the second type of situation, judge the defect point type in the depth data acquired by the RGBD camera, center on the def...
Embodiment 2
[0089] Embodiment 2: The present invention provides a method for glass detection and map update of an indoor mobile robot based on depth image restoration. Further, the specific steps are:
[0090] S1: Process lidar information, obtain intensity data, and screen areas suspected of having glass based on the intensity data;
[0091] Further, the suspected area of the glass is screened, and the received laser radar distance information is firstly screened.
[0092] According to the characteristics of the data returned when the lidar scans the glass, find the distance information with a large enough single distance change according to the time stamp, and use this as a condition to trigger the glass suspected area detection program. After the program is triggered, record the current time. Time stamp, and then continuously collect the distance information under N time stamps, and perform variance analysis on the N data. If the variance is large enough, it means that the area is su...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


