Intelligent learning system with noisy label data
2020-06-23 Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION
reassignment INTERNATIONAL BUSINESS MACHINES CORPORATION ASSIGNMENT OF …
reassignment INTERNATIONAL BUSINESS MACHINES CORPORATION ASSIGNMENT OF …
Method for determining anchor boxes for training neural network object detection models for autonomous driving
In one embodiment, a set of bounding box candidates are plotted onto a 2D space based on
their respective dimension (eg, widths and heights). The bounding box candidates are …
their respective dimension (eg, widths and heights). The bounding box candidates are …
Autonomous vehicle system for intelligent on-board selection of data for building a remote machine learning model
T Muehlenstaedt, J Frtunikj, Z Kurtz - US Patent 11,657,591, 2023 - Google Patents
US11657591B2 - Autonomous vehicle system for intelligent on-board selection of data for
building a remote machine learning model - Google Patents US11657591B2 - Autonomous …
building a remote machine learning model - Google Patents US11657591B2 - Autonomous …
Road obstacle detection device, road obstacle detection method, and recording medium storing a road obstacle detection program
T Ohgushi, K Horiguchi, M Yamanaka - US Patent 11,443,526, 2022 - Google Patents
A road obstacle detection device which uses a pre-learned first identifier to associate a
semantic label with each pixel of an image, uses a pre-learned second identifier to estimate …
semantic label with each pixel of an image, uses a pre-learned second identifier to estimate …
Pre-labeling data with cuboid annotations
CL Cheng, E Branson, LM Braswell, D Havíř… - US Patent …, 2023 - Google Patents
One embodiment provides techniques for automatically pre-labeling point cloud data with
cuboid annotations. Point cloud data is processed using ML models to detect, associate, and …
cuboid annotations. Point cloud data is processed using ML models to detect, associate, and …
Partial point cloud-based pedestrians' velocity estimation method
A method, apparatus, and system for estimating a moving speed of a detected pedestrian at
an autonomous driving vehicle (ADV) is disclosed. A pedestrian is detected in a plurality of …
an autonomous driving vehicle (ADV) is disclosed. A pedestrian is detected in a plurality of …
Neural network object detection
A first six degree-of-freedom (DoF) pose of an object from a perspective of a first image
sensor is determined with a neural network. A second six DoF pose of the object from a …
sensor is determined with a neural network. A second six DoF pose of the object from a …
Cross-modality active learning for object detection
KS Tan, H Caesar, OO Beijbom - US Patent 11,887,324, 2024 - Google Patents
Among other things, techniques are described for cross-modality active learning for object
detection. In an example, a first set of predicted bounding boxes and a second set of …
detection. In an example, a first set of predicted bounding boxes and a second set of …
Methods and systems for updating perception models based on geolocation features
A server includes a controller programmed to obtain information about a first perception
model installed in a vehicle. The controller is further programmed to determine a value of …
model installed in a vehicle. The controller is further programmed to determine a value of …
Scoring autonomous vehicle trajectories using reasonable crowd data
Enclosed are embodiments for scoring one or more trajectories of a vehicle through a given
traffic scenario using a machine learning model that predicts reasonableness scores for the …
traffic scenario using a machine learning model that predicts reasonableness scores for the …