Method and device for three-dimensional object scanning with invisible markers

A three-dimensional (3D) object scanner, comprising:

• a first camera device;
• a second camera device;
• an invisible light source configured to emit a light onto a target object, the target object being painted with invisible markers that are invisible to the first camera device when the invisible light source is off, and the invisible markers being visible to the second camera device upon absorbing the light emitted by the invisible light source;
• and
• a controller configured to:
• control an on/off status of the invisible light source;
• control, when the invisible light source is off in a first period of a capturing cycle, the first camera device to capture a first image of the target object from a first orientation;
• control, when the invisible light source is on in a second period of the same capturing cycle, the second camera device to capture a second image of the target object, wherein the second image is used to determine 3D information of the target object;
• and
• pair the 3D information of the target object corresponding to the second image of the capturing cycle and the first image of the same capturing cycle to form a training sample for training a gesture recognition model.

A non-transitory storage medium storing computer instructions that, when executed by at least one processor, causing the at least one processor to perform:

• controlling an on/off status of an invisible light source, the invisible light source being configured to emit a light onto a target object, the target object being painted with invisible markers that are invisible to a first camera device when the invisible light source is off, and the invisible markers being visible to a second camera device upon absorbing the light emitted by the invisible light source;
• controlling, when the invisible light source is off in a first period of a capturing cycle, the first camera device to capture a first image of the target object;
• controlling, when the invisible light source is on in a second period of the same capturing cycle, the second camera device to capture a second image of the target object, wherein the second image is are used to determine 3D information of the target object;
• and
• pairing the 3D information of the target object corresponding to the second image of the capturing cycle and the first image of the same capturing cycle to form a training sample for training a gesture recognition model.