公开(公告)号：US20170206431A1

公开(公告)日：2017-07-20

申请号：US15001417

申请日：2016-01-20

申请人： Microsoft Technology Licensing, LLC

发明人： Jian Sun ,  Ross Girshick ,  Shaoqing Ren ,  Kaiming He

IPC分类号： G06K9/46 ,  G06N3/08 ,  G06F17/30 ,  G06K9/62

CPC分类号： G06K9/4671 ,  G06F17/30256 ,  G06F17/30864 ,  G06K9/3233 ,  G06K9/4628 ,  G06K9/6267 ,  G06K9/685 ,  G06N3/0454 ,  G06N3/084

摘要： Systems, methods, and computer-readable media for providing fast and accurate object detection and classification in images are described herein. In some examples, a computing device can receive an input image. The computing device can process the image, and generate a convolutional feature map. In some configurations, the convolutional feature map can be processed through a Region Proposal Network (RPN) to generate proposals for candidate objects in the image. In various examples, the computing device can process the convolutional feature map with the proposals through a Fast Region-Based Convolutional Neural Network (FRCN) proposal classifier to determine a class of each object in the image and a confidence score associated therewith. The computing device can then provide a requestor with an output including the object classification and/or confidence score.

公开(公告)号：US09858496B2

公开(公告)日：2018-01-02

申请号：US15001417

申请日：2016-01-20

申请人： Microsoft Technology Licensing, LLC

发明人： Jian Sun ,  Ross Girshick ,  Shaoqing Ren ,  Kaiming He

IPC分类号： G06K9/62 ,  G06K9/46 ,  G06N3/08 ,  G06F17/30

CPC分类号： G06K9/4671 ,  G06F17/30256 ,  G06F17/30864 ,  G06K9/3233 ,  G06K9/4628 ,  G06K9/6267 ,  G06K9/685 ,  G06N3/0454 ,  G06N3/084

摘要： Systems, methods, and computer-readable media for providing fast and accurate object detection and classification in images are described herein. In some examples, a computing device can receive an input image. The computing device can process the image, and generate a convolutional feature map. In some configurations, the convolutional feature map can be processed through a Region Proposal Network (RPN) to generate proposals for candidate objects in the image. In various examples, the computing device can process the convolutional feature map with the proposals through a Fast Region-Based Convolutional Neural Network (FRCN) proposal classifier to determine a class of each object in the image and a confidence score associated therewith. The computing device can then provide a requestor with an output including the object classification and/or confidence score.