发明名称 Apparatus and method for detecting body parts from user image
摘要 An apparatus for detecting a body part from a user image may include an image acquirer to acquire a depth image, an extractor to extract the user image from a foreground of the acquired depth image, and a body part detector to detect the body part from the user image, using a classifier trained based on at least one of a single-user image sample and a multi-user image sample. The single-user image may be an image representing non-overlapping users, and the multi-user image may be an image representing overlapping users.
申请公布号 US9443136(B2) 申请公布日期 2016.09.13
申请号 US201414249464 申请日期 2014.04.10
申请人 SAMSUNG ELECTRONICS CO., LTD. 发明人 Liu Rong;Chen Maolin;Zhang Fan;Kim Ji Yeun;Gong Lujin;Sun Xun;Hu Zhilan
分类号 G06K9/00;G06K9/46 主分类号 G06K9/00
代理机构 Harness, Dickey & Pierce, P.L.C. 代理人 Harness, Dickey & Pierce, P.L.C.
主权项 1. An apparatus configured to detect a body part from a user image, the apparatus comprising: an image acquirer configured to acquire a first depth image and a second depth image, the second depth image acquired after the first depth image; and at least one processor and a memory, the memory containing computer readable instructions stored thereon, which when executed by the at least one processor, configure the at least one processor to, extract the user image from a foreground of the first depth image,divide the user image into at least one of a single-user image representing non-overlapping users and a multi-user image representing overlapping users,flag the user image extracted from the first depth image,track the flagged user image in the second depth image,determine overlap of the flagged user image in the second depth image, anddetect the body part from the extracted user image using a first classifier and a second classifier,wherein the first classifier is configured to classify the body part from the single-user image, and the second classifier is configured to classify the body part from the multi-user image.
地址 Gyeonggi-do KR
您可能感兴趣的专利