Rotated object detection
AssigneeInternational Business Machines Corporation
InventorsKun Yan Yin, Yuan Yuan Ding, Zhi Xing Peng, Fei Wang, Yue Liu
Life of this patent
Estimating the term…
Abstract
At least one processor determines bounding boxes in an image using a neural network. At least one processor extracts an initial bounding box for an object in the image. At least one processor selects a cluster center of the bounding boxes and circumscribes a cluster box around the cluster center. At least one processor rotates the initial bounding box and contents of the initial bounding box according to a rotation angle determined based on the cluster box. At least one processor detects the object in the rotated initial bounding box using a trained machine learning model.
Claims20
A computer-implemented method comprising:
- determining bounding boxes in an image using a neural network;
- extracting an initial bounding box for an object in the image;
- selecting a cluster center of the bounding boxes and circumscribing a cluster box around the cluster center;
- rotating the initial bounding box and contents of the initial bounding box according to a rotation angle determined based on the cluster box;
- and
- detecting the object in the rotated initial bounding box using a trained machine learning model.
A computer program product comprising:
- a set of one or more computer readable storage media;
- and
- program instructions, collectively stored in the set of one or more storage media, for causing a processor set to perform the following computer operations:
- determine bounding boxes in an image using a neural network;
- extract an initial bounding box for an object in the image;
- select a cluster center of the bounding boxes and circumscribe a cluster box around the cluster center;
- rotate the initial bounding box and contents of the initial bounding box according to a rotation angle determined based on the cluster box;
- and
- detect the object in the rotated initial bounding box using a trained machine learning model.
A computer system comprising:
- a processor set;
- a set of one or more computer-readable storage media;
- and
- program instructions, collectively stored in the set of one or more storage media, for causing the processor set to perform the following computer operations:
- determine bounding boxes in an image using a neural network;
- extract an initial bounding box for an object in the image;
- select a cluster center of the bounding boxes and circumscribe a cluster box around the cluster center;
- rotate the initial bounding box and contents of the initial bounding box according to a rotation angle determined based on the cluster box;
- and
- detect the object in the rotated initial bounding box using a trained machine learning model.
Dependencies are inferred from the claim text.