Method for training a person recognition model using images from a camera, and method for recognizing persons from a trained person recognition model by means of a second camera in a camera network

A method (700) for recognizing persons from a trained person recognition model, the method (700) comprising:

• reading in (605) a detection signal (135) representing a detected person (325) within a monitoring area (515) of a first camera (100) in a camera network (505);
• collecting (610) a plurality of image signals (140) from the first camera (100) using the detection signal (135) which has been read in, wherein the collected image signals (140) represent a recorded image section (305, 310, 315, 320) from each image (340) from the first camera (100);
• adapting (625) the person recognition model using the collected image signals (140) in order to recognize the detected person (325) in an image from the at least one camera (100) or in an image from a second camera (200) in the camera network (505);
• capturing (705) at least one second image signal (220), wherein the second image signal (220) represents a second image section from an image (540) from the first camera (100) or from the second camera (200);
• and
• recognizing (710) a detected person (325) in the second image signal (220) which has been read in by means of the first camera (100) or the second camera (200) in the camera network (505) using the person recognition model.

A non-transitory, computer-readable medium containing computer-executable instructions that when executed by the computer cause the computer to

• read in (605) a detection signal (135) representing a detected person (325) within a monitoring area (515) of a first camera (100) in a camera network (505);
• collect (610) a plurality of image signals (140) from the first camera (100) using the detection signal (135) which has been read in, wherein the collected image signals (140) represent a recorded image section (305, 310, 315, 320) from each image (340) from the first camera (100);
• adapt (625) the person recognition model using the collected image signals (140) in order to recognize the detected person (325) in an image from the at least one camera (100) or in an image from a second camera (200) in the camera network (505);
• capture (705) at least one second image signal (220), wherein the second image signal (220) represents a second image section from an image (540) from the first camera (100) or from the second camera (200);
• and
• recognize (710) a detected person (325) in the second image signal (220) which has been read in by means of the first camera (100) or the second camera (200) in the camera network (505) using the person recognition model.