This module requires a robot with a 3D sensor.
What it does¶
ALCloseObjectDetection allows you to detect objects that are too close to the robot to be directly detected by the 3D sensor.
How it works¶
In order to be detected and appear in the depth image returned by the 3D sensor, objects must be at a minimum distance to the sensor. However, using the Infrared image (also returned by the 3D sensor) it is possible to detect when objects are too close and compute their positions, as these objects will correspond to saturated pixels in the Infrared image.
Each time an object is detected in the “close range” of the 3D sensor by the module ALCloseObjectDetection,
the ALMemory key
CloseObjectDetection/ObjectInfo is updated and the ALMemory event
CloseObjectDetection/ObjectDetected() is raised.
The memory key contains the information about the detection of biggest close object. It is organized as follows:
ObjectInfo = [ TimeStamp, CloseObjectInfo, CameraPose_InTorsoFrame, CameraPose_InRobotFrame, Camera_Id ]
TimeStamp: this field is the time stamp of the image that was used to perform the detection.
TimeStamp [ TimeStamp_Seconds, Timestamp_Microseconds ]
CloseObjectInfo: each of these fields contains the description of the detected close object. It has the following structure:
CloseObjectInfo = [ PositionOfCog, AngularRoi, PixelsProportion, ]
- PositionOfCog = [x,y] contains the angular coordinates (in radians) of the center of gravity of the object.
- AngularRoi = [x,y,width, height] contains information about the smallest rectangle (ROI) in which the object is included. [x,y] corresponds to the angular coordinates (in radians) of the top left corner of the ROI in the current depth image. [width, height] corresponds to the angular size (in radians) of the ROI.
- PixelsProportion = [In_Frame, In_Roi] corresponds to the proportion of pixels that belong to the close object. In_Frame is the proportion relative to the total number of pixels in the frame and In_Roi is the proportion relative to the number of pixels in the ROI of the object.
Camera_Id: gives the Id of the camera used for the detection, i.e the depth camera.