Basler RGB-D Solution Specifications

The RGB-D solution merges Basler blaze 3D and color camera data for colored point clouds. It enhances object detection, classification, and scene understanding by combining depth and color information. This combination aids accurate recognition, particularly for similar shapes, and supports tasks like depalletizing and mobile robot navigation. The RGB-D approach offers advanced perception and improved accuracy for industrial automation applications.

Advantages of RGB-D: When does the combined use make sense?

Robust object detection and classification with increased accuracy of correct matches, especially for similarly shaped objects

Example: Can you tell in the left part of the point cloud whether it is an apple or an orange? This is only possible in RGB color. Conversely, a 2D camera would not be able to tell the difference between the photo of an apple and the real apple.

Color information helps improve scene details where depth information is lacking

Example: During depalletizing, two cartons are so close together on the pallet that they are recognized as one by the 3D camera. In the higher-resolution RGB data, however, a gap can be detected.

Reliable scene segmentation, if necessary enhanced by the use of deep learning (here: integration of prior scene knowledge), for example for the use of mobile robots

Example: Finding the floor in 3D is supported by color: asphalt gray probably belongs to road (floor)