-
1.发明申请公开(公告)号：US20150023588A1
公开(公告)日：2015-01-22
申请号：US14336777
申请日：2014-07-21
Applicant: STMicroelectronics S.r.l.
Inventor： Massimiliano Barone
IPC: G06T7/00
CPC classification number: G06T7/0075 , G06T7/593 , G06T2207/10028
Abstract: A depth map is generated from at least a first and a second image. A plurality of reference pixels are selected in the first image. A cost function is used to associate each reference pixel with a respective pixel in the second image. A masking operation is used to identify a subset of pixels in a block of pixels surrounding a reference pixel and the cost function is based on the identified subset of pixels. A disparity between each reference pixel and the respective pixel in said second image is determined, and a depth value is determined for each reference pixel as a function of the respective disparity. A depth map is generated based on the determined depth values.
Abstract translation: 从至少第一和第二图像生成深度图。 在第一图像中选择多个参考像素。 成本函数用于将每个参考像素与第二图像中的相应像素相关联。 掩蔽操作用于识别参考像素周围的像素块中的像素的子集，并且成本函数基于所识别的像素子集。 确定所述第二图像中的每个参考像素和相应像素之间的差异，并且对于每个参考像素确定作为相应视差的函数的深度值。 基于确定的深度值生成深度图。
-
Patent Agency Ranking
2.发明授权公开(公告)号：US10288990B1
公开(公告)日：2019-05-14
申请号：US15850667
申请日：2017-12-21
Applicant: STMicroelectronics S.r.l. , STMicroelectronics Ltd
Inventor： Massimo Ratti , Eli Yaser , Naomi Petrushevsky , Massimiliano Barone
Abstract: Disclosed herein is a laser projection system including a laser projector emitting a laser beam, a movable mirror apparatus reflecting the laser beam toward a surface, and a graphics processing unit (GPU). The GPU is configured to receive video data, estimate a varying speed of movement of the movable mirror apparatus for different positions of the laser beam across the surface, and process the video data based upon the estimated varying speed of movement. An application specific integrated circuit (ASIC) receives the processed video data, and to generate a beam position control signal based upon required or desired movement of the movable mirror apparatus. A laser driver controls the laser projector as a function of the processed video data, and a mirror controller controls the movable mirror apparatus as a function of the beam position control signal.
-
3.发明授权公开(公告)号：US09317925B2
公开(公告)日：2016-04-19
申请号：US14336734
申请日：2014-07-21
Applicant: STMicroelectronics S.r.l.
Inventor： Massimiliano Barone
CPC classification number: G06T7/0075 , G06T7/593 , G06T2207/10028
Abstract: A depth map is generated from at least a first and a second image. A plurality of reference pixels in the first image are selected and associated with respective pixels in the second image. A disparity between each reference pixel and the respective pixel in said second image is determined, and a depth value is determined as a function of the respective disparity. The plurality of reference pixels is selected based on detected contours in the first image.
Abstract translation: 从至少第一和第二图像生成深度图。 选择第一图像中的多个参考像素并与第二图像中的相应像素相关联。 确定所述第二图像中每个参考像素与相应像素之间的差异，并且确定深度值作为相应视差的函数。 基于第一图像中检测到的轮廓来选择多个参考像素。
-
4.发明申请公开(公告)号：US20150023586A1
公开(公告)日：2015-01-22
申请号：US14336734
申请日：2014-07-21
Applicant: STMicroelectronics S.r.l.
Inventor： Massimiliano Barone
IPC: G06T7/00
CPC classification number: G06T7/0075 , G06T7/593 , G06T2207/10028
Abstract: A depth map is generated from at least a first and a second image. A plurality of reference pixels in the first image are selected and associated with respective pixels in the second image. A disparity between each reference pixel and the respective pixel in said second image is determined, and a depth value is determined as a function of the respective disparity. The plurality of reference pixels is selected based on detected contours in the first image.
Abstract translation: 从至少第一和第二图像生成深度图。 选择第一图像中的多个参考像素并与第二图像中的相应像素相关联。 确定所述第二图像中每个参考像素与相应像素之间的差异，并且确定深度值作为相应视差的函数。 基于第一图像中检测到的轮廓来选择多个参考像素。
-
5.发明授权Method for generating a depth map, related system and computer program product 有权生成深度图，相关系统和计算机程序产品的方法公开(公告)号：US09373171B2
公开(公告)日：2016-06-21
申请号：US14336763
申请日：2014-07-21
Applicant: STMicroelectronics S.r.l.
Inventor： Massimiliano Barone
CPC classification number: G06T7/0075 , G06T7/593 , G06T2207/10028
Abstract: A depth map is generated from at least a first and a second image. Generally, a plurality of reference pixels are selected in the first image and associated with respective pixels in the second image. Next, the disparity between each reference pixel and the respective pixel in said second image is determined, and for each reference pixel a depth value as a function of the respective disparity. In particular, each reference pixel is associated with a respective pixel in the second image via a matching and a filtering operation. The matching operation selects for each reference pixel a plurality of candidate pixels in the second image and associates with each candidate pixel a respective cost function value and a respective disparity value.
Abstract translation: 从至少第一和第二图像生成深度图。 通常，在第一图像中选择多个参考像素并与第二图像中的相应像素相关联。 接下来，确定所述第二图像中的每个参考像素和相应像素之间的差异，并且对于每个参考像素，确定作为相应视差的函数的深度值。 特别地，每个参考像素经由匹配和滤波操作与第二图像中的相应像素相关联。 匹配操作为每个参考像素选择第二图像中的多个候选像素，并且将每个候选像素与相应的成本函数值和相应的视差值相关联。
-
6.发明授权公开(公告)号：US09483830B2
公开(公告)日：2016-11-01
申请号：US14336777
申请日：2014-07-21
Applicant: STMicroelectronics S.r.l.
Inventor： Massimiliano Barone
IPC: G06T7/00
CPC classification number: G06T7/0075 , G06T7/593 , G06T2207/10028
Abstract: A depth map is generated from at least a first and a second image. A plurality of reference pixels are selected in the first image. A cost function is used to associate each reference pixel with a respective pixel in the second image. A masking operation is used to identify a subset of pixels in a block of pixels surrounding a reference pixel and the cost function is based on the identified subset of pixels. A disparity between each reference pixel and the respective pixel in said second image is determined, and a depth value is determined for each reference pixel as a function of the respective disparity. A depth map is generated based on the determined depth values.
Abstract translation: 从至少第一和第二图像生成深度图。 在第一图像中选择多个参考像素。 成本函数用于将每个参考像素与第二图像中的相应像素相关联。 掩蔽操作用于识别参考像素周围的像素块中的像素的子集，并且成本函数基于所识别的像素子集。 确定所述第二图像中的每个参考像素和相应像素之间的差异，并且对于每个参考像素确定作为相应视差的函数的深度值。 基于确定的深度值生成深度图。
-
-
-
-
-
Search Results
6
records
(took 0.017 seconds)
