Ricoh Company, Ltd.

Skybox Imaging, Inc.

Planet Labs, Inc.

Planet Labs Pbc

M Dirk Robinson

David Geoffrey Stork

Julian M Mann

Guotong Feng

Daniel Berkenstock

Kathrin Berkner

Brendan Hermalyn

Mark Allen Robertson

Joshua D Levine

Junlan Yang

Oliver Guinan

Hadar Isaac

Matt William Messana

Thomas Joseph Melendez

Jonathan Dyer

Ronny Votel

Mohammed Shoaib

Edward L Schwartz

H Keith Nishihara

Noah Denis Bedard

Chwen-Yuan Ku

Ivana Tosic

Wanmin Wu

Patrick Llull

Jun Ke

Systems and methods of capturing imagery are provided. In particular, an imaging platform can be configured to capture imagery using a dual-axis steering mirror and one or more image capture devices. The line of sight angle of the imaging platform can be controlled by controlling the motion of the steering mirror in accordance with a motion profile. In example embodiments, the motion profile can correspond to a sawtooth wave. The imaging platform can further include one or more position sensors used to determine a position and/or orientation of the imaging platform along a path on which the imaging platform travels. The motion of the steering mirror can then be controlled to rotate about a first axis and a second axis to compensate for line of sight errors based at least in part on the determined position and/or orientation.

Controlling a line of sight angle of an imaging platform

Multiframe reconstruction combines a set of acquired images into a reconstructed image. Here, which images to acquire are selected based at least in part on the content of previously acquired images. In one approach, a set of at least three images of an object are acquired at different acquisition settings. For at least one of the images in the set, the acquisition setting for the image is determined based at least in part on the content of previously acquired images. Multiframe image reconstruction, preferably via a multi-focal display, is applied to the set of acquired images to synthesize a reconstructed image of the object.

Adaptive image acquisition and display using multi-focal display

Examples of an imaging sensor include a two-dimensional staring sensor with spectral filter strips for multispectral overhead imaging. The sensor may also include a panchromatic sensor with block or strip filters. The sensor may be used to collect multispectral color image data at a sampling resolution from overhead imaging platforms such as airplanes or satellites. The sensor can be used to provide video images. If a panchromatic sensor is included, the sensor may be used to collect panchromatic image data. Examples of methods for processing the image date include using the panchromatic image data to perform multi-frame enhancement or panchromatic sharpening on spectral images to improve their quality and resolution.

Systems and methods for overhead imaging and video

Multiframe reconstruction combines a set of acquired images into a reconstructed image. Here, which images to acquire are selected based at least in part on the content of previously acquired images. In one approach, a set of at least three images of an object are acquired at different acquisition settings. For at least one of the images in the set, the acquisition setting for the image is determined based at least in part on the content of previously acquired images. Multiframe image reconstruction is applied to the set of acquired images to synthesize a reconstructed image of the object.

Adaptive image acquisition for multiframe reconstruction

Examples of systems and methods to provide estimates of dark current for pixels of a photosensor as a function of the temperature of the sensor and the gain applied to the photosensor are described. In various implementations, the dark current estimated for each pixel can depend at least partly on a global scale factor and a global bias that depend on temperature and gain and a temperature-independent and gain-independent offset value for each pixel. The scale, bias, and offsets may be determined from multiple dark field images taken by the sensor over a range of operating temperatures. In some cases, the scale and bias can be determined using a subset of less than all the image pixels. Scale and bias derived for a particular sensor can be used in the calibration of different sensors.

Sensor dark pixel offset estimation

Examples of systems and methods for delivering overhead video to a computing device are provided. Delivering the overhead video can include generating multiple versions of the overhead video having respective resolutions, bitrates, or frame rates. The system can then generate georeferenced video data for each version by incorporating georeferencing coordinates and time synchronization information. The georeferenced video data can be stored in transcoded video files. In response to a request from a computing device for video data of a geographical region, the system can transmit a primary video stream comprising georeferenced video data of a relatively high quality and a secondary video stream comprising georeferenced video data of a relatively low quality, wherein the primary video stream includes the geographical region and the secondary video stream includes a proximal geographical region.

Multi-resolution pyramid for georeferenced video

Described are systems, methods, computer programs, and user interfaces for image location, acquisition, analysis, and data correlation that uses human-in-the-loop processing, Human Intelligence Tasks (HIT), and/or or automated image processing. Results obtained using image analysis are correlated to non-spatial information useful for commerce and trade. For example, images of regions of interest of the earth are used to count items (e.g., cars in a store parking lot to predict store revenues), detect events (e.g., unloading of a container ship, or evaluating the completion of a construction project), or quantify items (e.g., the water level in a reservoir, the area of a farming plot).

Adaptive image acquisition and processing with image analysis feedback

Using human intelligence tasks for precise image analysis

A method and apparatus for finite impulse response (FIR) filter bank architecture and method that involve low-complexity computation resources are described. In one embodiment, a digital image processing system includes an index mapping module to determine a rotation angle index to control rotation of an input patch of an image based on the (x,y) pixel coordinates of the image patch. The digital image processing system may also include a rotation module to rotate the input patch of the image based on the rotation angle index. In one embodiment, the digital image processing system may further include a filter engine module applied to a rotated version of the input patch of the image.

Method and apparatus for FIR filtering using space-varying rotation

A weighted sum of a set of component filters is used to effectively apply different 'composite' FIR filters to compensate for aberrations resulting from different opto-mechanical settings. The FIR filters are 'composite' in the sense that they are a weighted sum of the set of component filters. In one approach, the aberrations vary as a function of the opto-mechanical setting, and the opto-mechanical setting is used to determine the weights of the different component filters.

Imaging system with variable opto-mechanical system, aberrated optics and compensating filter bank

Growing community of inventors

Menlo Park, CA, United States of America

M Dirk Robinson