Systems and methods for printed circuit board netlist extraction from multimodal imagery

A method comprising:

• capturing image data of a circuit board from a plurality of sensors to generate a set of captured data for each of the plurality of sensors, wherein the image data is a multimodal image data of the circuit board the plurality of sensors include a plurality of electromagnetic wavelengths;
• extracting a plurality of features from the image data using machine learning, wherein the plurality of features includes at least one of traces, pins, components, and/or text;
• fusing the plurality of features from each of the plurality of sensors to create a plurality of segmentation masks, wherein:
• the plurality of features are combined using a feature pyramid network;
• and
• the feature pyramid network is an encoder-decoder neural network;
• and
• generating a design associated with the circuit board from the plurality of features.

A system comprising:

• a plurality of sensors configured to capture image data of a circuit board to generate a set of captured data for each of the plurality of sensors, wherein the image data of the circuit board is a multimodal image data of the circuit board the plurality of sensors include a plurality of electromagnetic wavelengths;
• a feature pyramid network configured to fuse a plurality of features from the set of captured data to create a plurality of segmentation masks;
• and
• a processor configured to:
• extract the plurality of features from the image data of the circuit board using a machine learning, wherein the plurality of features includes at least one of traces, pins, components, and/or text;
• fuse the plurality of features from each of the plurality of sensors to create the plurality of segmentation masks, wherein the plurality of features are combined using the feature pyramid network;
• and
• generate a design associated with the circuit board from the plurality of features.

A system comprising:

• a processor;
• a non-transitory computer-readable storage media;
• and
• program instructions stored on the non-transitory computer-readable storage media for execution by the processor, the stored program instructions including instructions to:
• capture image data of a circuit board from a plurality of sensors to generate a set of captured data for each of the plurality of sensors, wherein the image data is a multimodal image data of the circuit board the plurality of sensors include a plurality of electromagnetic wavelengths;
• extract a plurality of features from the multimodal image data of the circuit board using a machine learning, wherein the plurality of features includes at least one of traces, pins, components, and/or text;
• fuse the plurality of features from each of the plurality of sensors to create a plurality of segmentation masks, wherein the plurality of features are combined using a feature pyramid network, wherein the feature pyramid network is an encoder-decoder neural network;
• and
• generate a design associated with the circuit board from the plurality of features.