Wireless transmitter identification in visual scenes

A network node, comprising:

• communication circuitry configured to establish communications with a wireless device in an environment;
• and
• a processing system configured to:
• receive image data of the environment;
• receive a signal from the wireless device;
• extract vision features from the image data;
• extract wireless features from the signal;
• perform an analysis, using cross-modal analysis, of the vision features and the wireless features to identify the wireless device and a type of the signal received from the transmitter;
• and
• adapt the communications with the wireless device in accordance with the analysis,
• wherein the cross-modal analysis learns a new set of cross-modality features, and uses the new set of cross-modality features to predict whether there are transmitters in the environment, and predict which objects represent the transmitters.

A neural network for wireless transmitter identification, the neural network comprising:

• a vision feature extractor;
• a wireless feature extractor;
• and
• a bounding box selection engine configured to provide transmitter identification and identification of a type of the signal received from the transmitter from a cross-modal analysis of vision features from the vision feature extractor and wireless features from the wireless feature extractor,
• wherein the cross-modal analysis learns a new set of cross-modality features, and uses the new set of cross-modality features to predict whether there are transmitters in the environment, and predict which objects represent the transmitters.