18334285. MULTI-SENSOR OBJECT FUSION AND TRACKING FOR AUTONOMOUS SYSTEMS AND APPLICATIONS (NVIDIA Corporation)
Contents
MULTI-SENSOR OBJECT FUSION AND TRACKING FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
Organization Name
Inventor(s)
Mehmet Kemal Kocamaz of San Jose CA (US)
Parthiv Parikh of San Jose CA (US)
Baris Evrim Demiroz of Campbell CA (US)
Sangmin Oh of San Jose CA (US)
MULTI-SENSOR OBJECT FUSION AND TRACKING FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
This abstract first appeared for US patent application 18334285 titled 'MULTI-SENSOR OBJECT FUSION AND TRACKING FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
Original Abstract Submitted
In various examples, a technique for low-latency fusion and tracking of objects from multiple cameras is disclosed that includes determining a plurality of input objects and corresponding object characteristics, individual input objects and respective object characteristics being determined based at least on an image generated using a respective camera. The technique also includes identifying at least one subset of the plurality of input objects, the at least one subset corresponding to a respective physical object and comprising at least one input object that satisfies a similarity criterion. The technique further includes generating an output object associated with one or more smoothed object characteristics, the output object being generated based at least on two or more input objects included in the at least one subset of the plurality of input objects. The at least one subset corresponds to a physical object that is visible to two or more cameras.
