System and method for dimensioning target objects
A method comprising obtaining, from a sensor, depth data representing a target object; selecting a model to fit to the depth data; for each data point in the depth data: defining a ray from a location of the sensor to the data point; and determining an error based on a distance from the data point to the model along the ray; when the depth data does not meet a similarity threshold for the model based on the determined errors, selecting a new model and repeating the error determination for the depth data based on the new model; when the depth data meets the similarity threshold for the model, selecting the model as representing the target object; and outputting the selected model representing the target object.
1. A method comprising:
obtaining depth data representing a target object;
selecting an object model as representing the target object based at least in part on the depth data meeting a threshold associated with the object model;
selecting at least one data point from the depth data;
defining a ray based at least in part on the at least one data point and a first location;
determining an error based at least in part on a distance from the at least one data point to an intersection of the selected object model and the ray.
2. The method of claim 1 , wherein the first location is the location of a sensor.
3. The method of claim 1 , wherein the threshold is a matching or similarity threshold.
4. The method of claim 1 , further comprising:
determining an object dimension based at least in part on the selected object model.
5. The method of claim 1 , further comprising classifying each data point as an inlier or an outlier based on an error threshold and the error for the data point.
6. The method of claim 5 , further comprising selecting the error threshold for the data point based on a distance of the data point from the first location.
7. The method of claim 5 , wherein the depth data is determined to meet the error threshold when a threshold percentage of the depth data are classified as inliers.
8. The method of claim 5 , wherein a second object model is selected based at least in part on a subset of the depth data classified as inliers.
9. The method of claim 1 , further comprising:
obtaining further depth data associated with the target object;
selecting at least one further data point from the further depth data;
determining a source sensor for each further data point; and
wherein one or more further rays are defined from the location of an associated source sensor for each further data point.
10. The method of claim 1 , further comprising one or more of:
displaying the selected model; and
using the selected model for navigational purposes.
11. The method of claim 1 , further comprising, when the depth data does not meet the threshold for the object model based on an accumulated one or more determined errors, selecting a new object model and repeating the error determination for each data point in the depth data based on the new object model.