Systems and methods for deriving an agent trajectory based on multiple image sources

A non-transitory computer-readable medium comprising program instructions stored thereon that, when executed by at least one processor of a computing system, cause the computing system to perform functions comprising:

• receiving (i) a first sequence of images captured by a monocular camera associated with a vehicle during a given period of operation and (ii) a second sequence of image pairs captured by a stereo camera associated with the vehicle during the given period of operation;
• deriving, from the first sequence of images captured by the monocular camera, a first track for a given agent that comprises a first sequence of position information for the given agent;
• deriving, from the second sequence of image pairs captured by the stereo camera, a second track for the given agent that comprises a second sequence of position information for the given agent, wherein (i) the position information in first track is more accurate than the position information in the second track at a first set of one or more times within the given period of operation when the given agent was more than a given distance away from the vehicle and (ii) the position information in the second track is more accurate than the position information in the first track at a second set of times within the given period of operation when the given agent was less than the given distance away from the vehicle;
• and
• determining a trajectory for the given agent based on the first and second tracks for the given agent.

A computing system comprising:

• at least one processor;
• a non-transitory computer-readable medium;
• and
• program instructions stored on the non-transitory computer-readable medium that are executable by the at least one processor such that the computing system is configured to:
• receive (i) a first sequence of images captured by a monocular camera associated with a vehicle during a given period of operation and (ii) a second sequence of image pairs captured by a stereo camera associated with the vehicle during the given period of operation;
• derive, from the first sequence of images captured by the monocular camera, a first track for a given agent that comprises a first sequence of position information for the given agent;
• derive, from the second sequence of image pairs captured by the stereo camera, a second track for the given agent that comprises a second sequence of position information for the given agent, wherein (i) the position information in first track is more accurate than the position information in the second track at a first set of one or more times within the given period of operation when the given agent was more than a given distance away from the vehicle and (ii) the position information in the second track is more accurate than the position information in the first track at a second set of times within the given period of operation when the given agent was less than the given distance away from the vehicle;
• and
• determine a trajectory for the given agent based on the first and second tracks for the given agent.