Title:
不確実性を有するランドマーク位置推定のための画像処理システムおよび方法
Document Type and Number:
Japanese Patent JP7345664
Kind Code:
B2
Abstract:
A controller for executing a task based on probabilistic image-based landmark localization, uses a neural network, which is trained to process images of objects of a type having a structured set of landmarks to produce a parametric probability distribution defined by values of parameters for a location of each landmark in each processed image. The controller submits the set of input images to the neural network to produce the values of the parameters that define the parametric probability distribution over the location of each landmark in the structured set of landmarks of each input image. Further, the controller determines, for each input image, a global landmark uncertainty for the image based on the parametric probability distributions of landmarks in the input image and executes the task based on the parametric probability distributions of landmarks in each input image and the global landmark uncertainty of each input image.
More Like This:
Inventors:
Marks, Tim
Kumar, Abinab
Mou, Wenxuan
Feng, Chen
Liu, Xiaomi
Kumar, Abinab
Mou, Wenxuan
Feng, Chen
Liu, Xiaomi
Application Number:
JP2022538569A
Publication Date:
September 15, 2023
Filing Date:
September 30, 2020
Export Citation:
Assignee:
Mitsubishi Electric Corporation
International Classes:
G06T7/00; G06T7/70; G06V10/82
Domestic Patent References:
| JP2019125112A |
Other References:
Nitesh B.Gundavarapu,et al.,Structured Aleatoric Uncertainty in Human Pose Estimation,CVPR WORKSHOP ON UNCERTAINTY AND ROBUSTNESS IN DEEP VISUAL LEARNING,米国,2019年06月16日,pp.50-53
Attorney, Agent or Firm:
Patent Attorney Fukami Patent Office