Abstract: Methods for visual presentation of vehicle positioning relative to the surrounding objects using an electronic computer device are presented, the methods including: causing the electronic computing device to provide a display of the interested objects on a same interface according to their relative positions; enabling instant communications among the objects displayed on the same interface; enabling an instant screen sharing among the objects displayed on the same interface and among broader audiences.

Abstract: Methods for business operation based on vehicle-carrying image processing by using an electronic computer device are presented, the methods include: causing the electronic computing device to capture, transmit, model and interpret the images; causing the business to operate based on the assembled information conveyed through the images; causing the automatic establishment of bid processes for business transactions. In some embodiments, methods further include: mapping the Quick Response (QR) codes to the classified objects; building and applying deep learning models for pattern recognition; building and applying an embedded communication network. In some embodiments, methods further include: determining the vehicle operation status and operation irregularities. In some embodiments, methods further include: causing the searches on the embedded communication network to generate inquiries and to establish bid processes.

Abstract: Certain aspects of the present disclosure relate to methods and apparatus for implementing image locating relative to a global structure. The method generally includes mapping one or more close-up images of a structure to a 3D model of the structure, and indicating, on an overview image of the structure, the location of the one or more close-up images based on the mapping.

Abstract: The disclosure provides an approach for performing inspections. An image analysis application is configured to receive sensor data captured at least by one or more sensors mounted on a first unmanned aerial vehicle (UAV) flying along at least one programmed flight pattern. The image analysis application is further configured to normalize the sensor data, and determine anomalies based, at least in part, on differences between the normalized sensor data and sensor data previously captured at least by one or more sensors mounted on a second UAV flying along the at least one programmed flight pattern. In addition, the image analysis application is configured to generate a report indicating the determined anomalies.

Abstract: The disclosure provides an approach for performing inspections. An image analysis application is configured to receive sensor data captured at least by one or more sensors mounted on a first unmanned aerial vehicle (UAV) flying along at least one programmed flight pattern. The image analysis application is further configured to normalize the sensor data, and determine anomalies based, at least in part, on differences between the normalized sensor data and sensor data previously captured at least by one or more sensors mounted on a second UAV flying along the at least one programmed flight pattern. In addition, the image analysis application is configured to generate a report indicating the determined anomalies.

Abstract: Certain aspects of the present disclosure relate to methods and apparatus for implementing image locating relative to a global structure. The method generally includes mapping one or more close-up images of a structure to a 3D model of the structure, and indicating, on an overview image of the structure, the location of the one or more close-up images based on the mapping.

Abstract: Techniques are disclosed for identifying objects in images. In one embodiment, transfer learning is employed to build new classifiers on top of pre-trained machine learning models, such as pre-trained convolutional neural networks (CNNs), by re-training classification layers of the pre-trained machine learning models using new training data while keeping feature detection layers of the pre-trained machine learning models fixed. Subsequently, the re-trained machine learning models may take as input images depicting regions of interest extracted from larger images using a sliding window, a saliency map, an image disparity map, and/or a region of interest detection technique, and output classifications of objects in the input images. In addition, a meta model may be learned that aggregates outputs of the re-trained machine learning models for robustness.

Abstract: Techniques are disclosed for rental vehicle damage detection and automatic rental vehicle management. In one embodiment, a rental vehicle management application receives video and/or images of a rental vehicle's exterior and dashboard and processes the video and/or images to determine damage to the vehicle as well as the vehicle's mileage and fuel level. A machine learning model may be trained using image sets, extracted from larger images of vehicles, that depict distinct types of damage to vehicles, as well as image sets depicting undamaged vehicles, and the management application may apply such a machine learning model to identify and classify vehicle damage. The management application further determines sizes of vehicle damage by converting the damage sizes in pixels to real-world units, and the management application then generates a report and receipt indicating the damage to the vehicle if any, mileage, fuel level, and associated costs.

Abstract: Techniques are disclosed for detecting and reporting railroad track anomalies. In one embodiment, a track inspection application is configured to receive images (or other sensor data) depicting a railroad track captured by cameras mounted on a train, compare the captured images with corresponding reference images (or other sensor data) captured from substantially the same locations and vantage points, and detect anomalies in the railroad track represented by differences between the captured images and corresponding reference images. In another embodiment, the inspection application may generate a three-dimensional (3D) model of the railroad track based on depths determined through, e.g., triangulation, and determine the railroad track's geometry from the 3D model.

Abstract: Certain aspects of the present disclosure relate to methods and apparatus for applying image analysis and machine learning algorithms to a collection of 2-D aerial images into one or more of a claims report. For example, a method may include generating an insurance analytics project based on a user input, acquiring image data of the structure based on the insurance analytics project, generating a 3-D model of the structure based on the image data, calculating measurements of the structure based on the 3-D model and image data, detecting one or more features of the structure using one or more of the measurements, the 3-D model, and the image data, and generating a report based on one or more of the user input, the image data, the 3-D model, the measurements, and the one or more features.

Abstract: Methods for aerial image processing and object identification using an electronic computing device are presented, the methods including: causing the electronic computing device to build a deep learning model; receiving actual aerial image data; applying the deep learning model to the actual aerial image data to identify areas of interest; post-processing the areas of interest; and returning a number of classified objects corresponding with the areas of interest to a user. In some embodiments, methods further include: applying global positioning system (GPS) mapping to the number of classified objects with respect to the actual aerial image data.

Abstract: Methods for analyzing a chart using an electronic computing device are presented, the methods including: causing the electronic computing device to receive a chart image corresponding with the chart, the chart image having recorded chart data; analyzing the recorded chart data, where the analyzing returns at least measurement values corresponding with the recorded chart data; and returning volumetric results of the processing to a user. In some embodiments, the recorded chart data corresponds with data selected from the group consisting of: temperature data, differential pressure data, and static pressure data. In some embodiments, the chart corresponds with a chart integration device or a chart recorder. In some embodiments, methods further include: capturing the chart image with a mobile image capture device.

Abstract: Methods for aerial image processing and object identification using an electronic computing device are presented, the methods including: causing the electronic computing device to build a deep learning model; receiving actual aerial image data; applying the deep learning model to the actual aerial image data to identify areas of interest; post-processing the areas of interest; and returning a number of classified objects corresponding with the areas of interest to a user. In some embodiments, methods further include: applying global positioning system (GPS) mapping to the number of classified objects with respect to the actual aerial image data.

Abstract: Methods for analyzing a chart using an electronic computing device are presented, the methods including: causing the electronic computing device to receive a chart image corresponding with the chart, the chart image having recorded chart data; analyzing the recorded chart data, where the analyzing returns at least measurement values corresponding with the recorded chart data; and returning volumetric results of the processing to a user. In some embodiments, the recorded chart data corresponds with data selected from the group consisting of: temperature data, differential pressure data, and static pressure data. In some embodiments, the chart corresponds with a chart integration device or a chart recorder. In some embodiments, methods further include: capturing the chart image with a mobile image capture device.

Abstract: Methods for providing a multi-directional search using an electronic computing device are presented, the method including: causing the electronic computing device to provide a multi-directional search bar; displaying a number of audience selections to whom the multi-directional search is directed; selecting any of the number of audience selections; entering a multi-directional search query; and returning a response to the multi-directional search query based on both the selected audience and the search query. In some embodiments, methods further include: providing a number of privacy settings corresponding with the selected audience selection; and selecting one of the number of privacy settings, where the selected privacy setting is selected from the group consisting of: a private search and a public search.

Abstract: A computer program process and system for generating user interfaces incorporates a search-driven navigation method for invoking commands to an application program running on the computer. A user interface is generated for display by a user interface process running on a computer. The user interface receives from a user of the application program one or more keywords. The process uses those keywords to look up one or more commands or files available to the user to control the application program with names and/or descriptions that match or are otherwise associated with the one or more keywords. The user interface is updated to display the one or more commands and/or files. Upon selection by the user of one of the one or more commands the application responds to the command and updates the interface based on the selected command.