Abstract: Systems and method for predicting performance of pipelines for object detection, pose estimation, and object tracking are provided. In one embodiment, a plurality of regressors are stored where each regressor may be trained for a specific object detection (OD), pose estimation (PE), and/or tracking pipeline, so that each regressor outputs a score equal to or greater than that of another regressor in response to a first feature vector as input, the first feature vector corresponding to a first object that is more suitable for the specific pipeline than other pipelines. A second feature vector is stored corresponding to a second object. The regressors are run with the second feature vector as input to derive respective scores, and a recommendation of at least one pipeline is indicated based on the derived scores with respect to the second object. OD/PE/tracking may then be performed using the at least one indicated pipeline.

Abstract: Systems and method for predicting performance of pipelines for object detection, pose estimation, and object tracking are provided. In one embodiment, a plurality of regressors are stored where each regressor may be trained for a specific object detection (OD), pose estimation (PE), and/or tracking pipeline, so that each regressor outputs a score equal to or greater than that of another regressor in response to a first feature vector as input, the first feature vector corresponding to a first object that is more suitable for the specific pipeline than other pipelines. A second feature vector is stored corresponding to a second object. The regressors are run with the second feature vector as input to derive respective scores, and a recommendation of at least one pipeline is indicated based on the derived scores with respect to the second object. OD/PE/tracking may then be performed using the at least one indicated pipeline.