Digitalglobe, Incorporated

Microsoft Technology Licensing, LLC

Mark D Tabb

Krzysztof Koperski

Carsten Tusk

Giovanni B Marchisio

Jeffrey D Shafer

Gur Kimchi

Kartik Chandra Muktinutalapati

Pete Nagy

Zhaoqiang Bi

A system for analysis of remotely sensed image data of parking facilities, storage lots, or road regions, for determining patterns over time and determine time-based information such as facility capacities or vehicle movement.

Automated remote car counting

Land classification based on analysis of image data. Feature extraction techniques may be used to generate a feature stack corresponding to the image data to be classified. A user may identify training data from the image data from which a classification model may be generated using one or more machine learning techniques applied to one or more features of the image. In this regard, the classification module may in turn be used to classify pixels from the image data other than the training data. Additionally, quantifiable metrics regarding the accuracy and/or precision of the models may be provided for model evaluation and/or comparison. Additionally, the generation of models may be performed in a distributed system such that model creation and/or application may be distributed in a multi-user environment for collaborative and/or iterative approaches.

Classification of land based on analysis of remotely-sensed earth images

Feature extraction of image data using feature extraction modules. The feature extraction modules may be provided in an architecture that allows for modular, decoupled generation and/or operation of the feature extraction modules to generate feature data corresponding to image data. In this regard, the feature extraction modules may communicate with a file system storing image data and feature data by way of a common interface format. Accordingly, regardless of the nature of the execution of the feature extraction module, each feature extraction module may be communicative by way of the common interface format, thereby providing a modular approach that is highly scalable, flexible, and adaptive.

Automated and scalable object and feature extraction from imagery

Techniques for object detection include training a first classifier to detect an object based on textural features and a second classifier to detect the object based on textural features and spectral features. A classifier relationship between the two classifiers is learned and used with the first classifier to detect other objects. If desired, the performance of the object detector can be improved by comparing the results of detecting objects with the first classifier and the classifier relationship versus detecting objects with the first and second classifier together, and modifying the classifier relationship based upon the comparison.

Object detection with textural to spectral domain adaptation

Processing and analyzing at least one remotely-sensed image to automatically detect and identify parking lots within a region of the remotely-sensed image. This may include: (1) receiving a remotely-sensed image having zero or more parking lots; (2) identifying a set of pixels related to parking lot features within the remotely-sensed image; (3) identifying at least one parking row within the remotely-sensed image; and (3) identifying a parking lot based on the identified parking rows. Identifying at least one parking lot may further include using first, second, third, and fourth level modules, such as a concrete/asphalt detection module, a road marking detection module, a vehicle detection module, and a Hough aggregation for parking row detection module.

Techniques for identifying parking lots in remotely-sensed images by identifying parking rows

A system for oil storage tank monitoring, comprising an extraction module and an analysis module, wherein an extraction module is utilized to determine information from an oil storage tank image and an analysis module is utilized to perform operations on extracted information, such as for determining measurements or values of oil storage tanks.

Oil tank farm storage monitoring

A system for automated car counting comprises a satellite-based image collection subsystem; a data storage subsystem; and an analysis software module stored and operating on a computer coupled to the data storage subsystem. The satellite-based image collection subsystem collects images corresponding to a plurality of areas of interest and stores them in the data storage subsystem. The analysis module: (a) retrieves images corresponding to an area of interest from the data storage subsystem; (b) identifies a parking space in an image; (c) determines if there is a car located in the parking space; (d) determines a location, size, and angular direction of a car in a parking space; (e) determines an amount of overlap of a car with an adjacent parking space; (f) iterates steps (b)-(e) until no unprocessed parking spaces remain; and (g) iterates steps (a)-(f) until no unprocessed images corresponding to areas of interest remain.

Point of origin information for image data may be inaccurately registered against a geographic location absolute. A process for aligning image and highly accurate model data adjusts a point of origin of the image data by matching elements in the image with corresponding elements of the model. In a street-level image, building skylines can be extracted and corresponding skylines from the building model can be placed over the image-based skyline. By adjusting the point of origin of the image, the respective skylines can be aligned. Building edge and facade depth information can similarly be matched by adjusting the image point of origin of the image. The adjusted point of origin of the image can be used to then automatically place images on the models for a long run of images.

Growing community of inventors

Longmont, CO, United States of America

Mark D Tabb