Microsoft Technology Licensing, LLC

Konrad Karner

Martin Josef Ponticelli

Gur Kimchi

Blaise Aguera Y Arcas

Stephen L Lawler

Michael Kroepfl

Michael Gruber

John Charles Curlander

Markus Unger

Franz W Leberl

Zanin Cosic

Hannes Hegenbarth

Joachim Bauer

Gerald Schweighofer

Arnold Irschara

Richard Ladstädter

Andreas Klaus

Christian Neuner

Helfried Tschemmernegg

A system that facilitates collecting data is described herein. The system includes a digital camera that is configured to capture images in a visible light spectrum and a near-infrared camera that is configured to capture near infrared images, wherein a field of view of the digital camera and the field of view of the near-infrared camera are substantially similar. The system further includes a trigger component that is configured to cause the digital camera and the near-infrared camera to capture images at a substantially similar point in time, and also includes a mounting mechanism that facilitates mounting the digital camera and the near-infrared camera to an automobile.

Three dimensional image capture system for imaging building facades using a digital camera, a near-infrared camera, and laser range finder

Vehicle-mounted sensor system that includes cameras and laser measurement systems

Mobile platforms are used to capture an area using a variety of sensors (e.g., cameras and laser scanners) while traveling through the area, in order to create a representation (e.g., a navigable set of panoramic images, or a three-dimensional reconstruction). However, such sensors are often precisely calibrated in a controlled setting, and miscalibration during travel (e.g., due to a physical jolt) may result in a corruption of data and/or a recalibration that leaves the platform out of service for an extended duration. Presented herein are techniques for verifying sensor calibration during travel. Such techniques involve the identification of a sensor path for each sensor over time (e.g., a laser scanner path, a camera path, and a location sensor path) and a comparison of the paths, optionally after registration with a static coordinate system, to verify that the continued calibration of the sensors during the mobile operation of the platform.

Mobile imaging platform calibration

Among other things, one or more techniques and/or systems are provided for mitigating redundant pixel texture contribution for texturing a geometry. That is, the geometry may represent a multidimensional surface of a scene, such as a city. The geometry may be textured using one or more texture images (e.g., an image comprising color values and/or depth values) depicting the scene from various view directions (e.g., a top-down view, an oblique view, etc.). Because more than one texture image may contribute to texturing a pixel of the geometry (e.g., due to overlapping views of the scene), redundant pixel texture contribution may arise. Accordingly, a redundant textured pixel within a texture image may be knocked out (e.g., in-painted) from the texture image to generate a modified texture image that may be relatively efficient to store and/or stream to a client due to enhanced compression of the modified texture image.

Redundant pixel mitigation

Among other things, one or more techniques and/or systems are provided for defining a view direction for a texture image used to texture a geometry. That is, a geometry may represent a multi-dimensional surface of a scene, such as a city. The geometry may be textured using one or more texture images depicting the scene from various view directions. Because more than one texture image may contribute to texturing portions of the geometry, a view direction for a texture image may be selectively defined based upon a coverage metric associated with an amount of non-textured geometry pixels that are textured by the texture image along the view direction. In an example, a texture image may be defined according to a customized configuration, such as a spherical configuration, a cylindrical configuration, etc. In this way, redundant texturing of the geometry may be mitigated based upon the selectively identified view direction(s).

View direction determination

Many imaging scenarios involve an achromatic image (e.g., a panchromatic image or a near-infrared image) and one or more concurrently captured monochromatic images (e.g., RGB images captured through a Bayer filter array), and the compositing of these images through de-mosaicing and/or pan-sharpening to generate a high-resolution color image. However, in many such scenarios, the monochromatic images may exhibit distortion of edge geometry, resulting in artifacts and/or color distortions near visual edges of the composite image. However, such distortions may be absent from the achromatic image, and edge geometry may be represented as an intensity gradient among respective neighborhoods of achromatic pixels. Presented herein are techniques for reducing such distortions in monochromatic images through iterative adjustment of monochromatic pixel intensity to reflect the gradients of the neighborhoods of the corresponding achromatic pixels. Convergence of such adjustments produces composite images exhibiting accurately reconstructed edge geometry.

Monochromatic edge geometry reconstruction through achromatic guidance

Three dimensional image capture system for imaging building facades using a digital camera, near-infrared camera, and laser range finder

Growing community of inventors

Raaba, Austria

Konrad Karner