Detector-tracker architecture

• Main Authors: Tariq, Sarah, Tan, Qijun
• Format: Patent
• Language: English
• Published: 03.11.2020
• Subjects: CALCULATING; COMPUTING; CONTROLLING; COUNTING; HANDLING RECORD CARRIERS; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; REGULATING; SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES

A machine-learning (ML) architecture may comprise a first ML model and/or an optical flow model that receive, as input, a first image and a second image. The first ML model may output a first feature map corresponding to the first image and a second feature map corresponding to the second image. The optical flow model may output an estimated optical flow. A deformation component may modify the second feature map, as a deformed feature map, based at least in part on the estimated optical flow. The deformed feature map and the first feature map may be concatenated together as a concatenated feature map, which may be provided to a second ML model. The second ML model may be trained to output an output ROI and/or a track in association with an object represented in the first image.