Thermal imaging for self-driving cars

A system, comprising:

• at least one environmental sensor configured to obtain environmental attributes indicative of the environment;
• a thermal machine learning model configured to generate prior thermal maps based on the environmental attributes;
• an infrared module configured to capture infrared images of an environment of a vehicle;
• a normalization module configured to generate a normalized thermal map based on the prior thermal maps and the infrared images;
• at least one lidar or camera configured to generate lidar/visible data;
• an emissivity machine learning model configured to generate an emissivity map based on the lidar/visible data;
• a projection module configured to generate a projected map based on the normalized thermal map and the emissivity map;
• and
• a classification machine learning model configured to classify objects in the projected map, wherein if the classification machine learning model classifies at least one living object in the environment of the vehicle, the system instructs a computing device on the vehicle to transmit a signal to enable control of the vehicle.

A vehicle, comprising:

• a computing device, the computing device comprising:
• one or more processors;
• and
• data storage, wherein the data storage has stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing device to carry out functions comprising:
• receiving one or more infrared images taken of an environment;
• receiving a current spatial point cloud of the environment;
• applying a trained machine learning system to the one or more infrared images to determine an identified object type in the environment by at least:
• identifying objects in the environment using the current spatial point cloud;
• and
• calculating emissivity values for the identified objects;
• determining one or more prior thermal maps associated with the environment;
• determining a current thermal map associated with the environment based on the one or more infrared images;
• determining the identified object type using the current thermal map and the calculated emissivity values, wherein the trained machine learning system normalizes thermal variations observed in the environment based on the one or more prior thermal maps before determining the identified object type using the current thermal map and the calculated emissivity values, and wherein the identified object type comprises at least one living object;
• and
• in response to determining the identified object type comprising the at least one living object, transmitting a signal to enable control of the vehicle.