发明名称 |
Depth information generating device, depth information generating method, and stereo image converter |
摘要 |
A depth information generating device includes a region extracting unit that detects a human face in at least one two-dimensional image, and based on the detected face, extracts a human figure region indicating a human figure within a region of the at least one two-dimensional image; and a depth map generating unit that gives a depth value different from a depth value of a region other than the human figure region to the human figure region to generate a depth map that separates the human figure region from the region other than the human figure region. |
申请公布号 |
US9014462(B2) |
申请公布日期 |
2015.04.21 |
申请号 |
US201113520654 |
申请日期 |
2011.11.09 |
申请人 |
Panasonic Intellectual Property Management Co., Ltd. |
发明人 |
Yamada Hitoshi;Thummanuntawat Thanaphat;Lasang Pongsak;Shen Sheng Mei |
分类号 |
G06K9/00;G06T7/00 |
主分类号 |
G06K9/00 |
代理机构 |
Wenderoth, Lind & Ponack, L.L.P. |
代理人 |
Wenderoth, Lind & Ponack, L.L.P. |
主权项 |
1. A depth information generating device comprising:
a non-transitory memory device storing a program; and a hardware processor configured to execute the program and cause the depth information generating device to operate as: a region extracting unit configured to detect a human face region in at least one two-dimensional image, and extract a human figure region using a human figure premask selected based on a position of the detected human face region and that includes the detected human face region, the size of the human figure premask being changed according to a size of the detected human face region and being selected among a plurality of human figure premasks which are a plurality of pieces of data on a face feature pattern and a plurality of pieces of region data of a human model stored in a memory in advance, the human figure region indicating the human figure within a region in the at least one two-dimensional image; and a generating unit configured to generate a depth map for separating the human figure region from a region other than the human figure region by giving a depth value different from a depth value of the region other than the human figure region to the human figure region, wherein the human figure premask includes a face region that is the human face region, and a body region that is a region other than the face region. |
地址 |
Osaka JP |