发明名称 DATASET CREATION FOR TRACKING TARGETS WITH DYNAMICALLY CHANGING PORTIONS
摘要 A mobile platform visually detects and/or tracks a target that includes a dynamically changing portion, or otherwise undesirable portion, using a feature dataset for the target that excludes the undesirable portion. The feature dataset is created by providing an image of the target and identifying the undesirable portion of the target. The identification of the undesirable portion may be automatic or by user selection. An image mask is generated for the undesirable portion. The image mask is used to exclude the undesirable portion in the creation of the feature dataset for the target. For example, the image mask may be overlaid on the image and features are extracted only from unmasked areas of the image of the target. Alternatively, features may be extracted from all areas of the image and the image mask used to remove features extracted from the undesirable portion.
申请公布号 US2016098600(A1) 申请公布日期 2016.04.07
申请号 US201514967189 申请日期 2015.12.11
申请人 QUALCOMM Incorporated 发明人 Wagner Daniel;Szalavari Zsolt Szabolcs
分类号 G06K9/00;G06T7/40;G06K9/46;G06T7/00 主分类号 G06K9/00
代理机构 代理人
主权项 1. A method comprising: providing an image of a target, the target being an object to be tracked using image based detection and tracking; identifying an undesirable portion within the target, wherein the undesirable portion is one of a texture-less surface, repetitively textured surface, or a variable area on product packaging; generating an image mask for the undesirable portion within the target; extracting features from the target in the image of the target to create a feature dataset for the target and using the image mask to exclude features within the undesirable portion within the target from the feature dataset for the target, wherein extracting the features from the target in the image of the target to create the feature dataset for the target and using the image mask comprises overlaying the image mask on the undesirable portion within the target in the image of the target and extracting the features within unmasked areas of the target or extracting the features within all areas of the target in the image of the target and using the image mask to remove the features extracted within the undesirable portion within the target from the feature dataset; and storing the feature dataset for the image based detection and tracking of the target, wherein the undesirable portion of the target is excluded from the stored feature dataset and features from remaining portions of the target are included in the stored feature dataset.
地址 San Diego CA US