发明名称 Stereo camera calibration using proximity data
摘要 Approaches discussed herein enable a computing device, such as a phone or tablet computer, to automatically recalibrate cameras used to capture three-dimensional images. A proximity sensor can be used to determine the distance to an object at approximately the time that three-dimensional image data is captured that includes a representation of the object. The apparent distance to the object, from the disparity of the three-dimensional image data, can be compared against the detected distance as measured by the proximity sensor. The difference between the detected and apparent distance, or the corresponding disparity values, can be used to determine a relative misalignment among the cameras, when then can be used to update the appropriate calibration parameters.
申请公布号 US9602806(B1) 申请公布日期 2017.03.21
申请号 US201313914469 申请日期 2013.06.10
申请人 Amazon Technologies, Inc. 发明人 Stafford David W.;Silva Jennifer;Falk Edward Ackley;Myers Robert King
分类号 H04N13/02;H04N13/00;H04N19/597;G06T7/00;H04N13/04 主分类号 H04N13/02
代理机构 Polsinelli LLP 代理人 Polsinelli LLP
主权项 1. A computing device, comprising: a first camera; a second camera; a proximity sensor; at least one processor; and memory including instructions that, when executed by the at least one processor, cause the computing device to: concurrently capture a first image of an object using the first camera and a second image of the object using the second camera;determine an apparent disparity, in pixels, between at least a portion of the object represented in the first image and the portion of the object represented in the second image;determine an apparent distance between the computing device and the object based on the apparent disparity;measure, by the proximity sensor, a detected distance between the computing device and the object;determine an expected disparity, in pixels, between the portion of the object represented in the first image and the portion of the object represented in the second image based on the detected distance;determine a relative misalignment value for at least one of the first camera or the second camera that corresponds to a difference between the apparent disparity and the expected disparity; andobtain, based at least in part on the relative misalignment value, one or more calibration parameters for at least one of the first camera or the second camera when the difference is equal to, or greater than, a threshold disparity value, wherein the one or more calibration parameters are used to compute a second apparent distance between the computing device and a second object.
地址 Reno NV US