Abstract: A computer vision system configured for detection and recognition of objects in video and still imagery in a live or historical setting uses a teacher-student object detector training approach to yield a merged student model capable of detecting all of the classes of objects any of the teacher models is trained to detect. Further, training is simplified by providing an iterative training process wherein a relatively small number of images is labeled manually as initial training data, after which an iterated model cooperates with a machine-assisted labeling process and an active learning process where detector model accuracy improves with each iteration, yielding improved computational efficiency. Further, synthetic data is generated by which an object of interest can be placed in a variety of setting sufficient to permit training of models. A user interface guides the operator in the construction of a custom model capable of detecting a new object.

Abstract: Method and system for identifying vehicles or other objects of interest along a route comprises at least one mobile data capture device capturing at least one data stream such as video of a rearward view as the vehicle, person or other object associated with the data capture device moves along a route. Detection and identification of objects as being of interest is determined by dividing a route into a plurality of route segments and determining whether a given candidate object or vehicle follows the lead object through multiple turns along the route. Unique identifiers such as license plates or anomalous object characteristics are used to determine whether an object appears in multiple route segments, permitting rapid analysis of a large volume of unstructured data to determine relationships between a lead object and one or more trailing objects.

Abstract: A computer vision system configured for detection and recognition of objects in video and still imagery in a live or historical setting uses a teacher-student object detector training approach to yield a merged student model capable of detecting all of the classes of objects any of the teacher models is trained to detect. Further, training is simplified by providing an iterative training process wherein a relatively small number of images is labeled manually as initial training data, after which an iterated model cooperates with a machine-assisted labeling process and an active learning process where detector model accuracy improves with each iteration, yielding improved computational efficiency. Further, synthetic data is generated by which an object of interest can be placed in a variety of setting sufficient to permit training of models. A user interface guides the operator in the construction of a custom model capable of detecting a new object.

Abstract: Systems, methods and techniques for detecting, identifying and classifying objects, including multiple classes of objects, from satellite or terrestrial imagery where the objects of interest may be of low resolution. Includes techniques, systems and methods for alerting a user to changes in the detected objects, together with a user interface that permits a user to rapidly understand the data presented while providing the ability to easily and quickly obtain more granular supporting data.

Abstract: A multisensor processing platform includes, in at least some embodiments, a face detector and embedding network for analyzing unstructured data to detect, identify and track any combination of objects (including people) or activities through computer vision algorithms and machine learning. In some embodiments, the unstructured data is compressed by identifying the appearance of an object across a series of frames of the data, aggregating those appearances and effectively summarizing those appearances of the object by a single representative image displayed to a user for each set of aggregated appearances to enable the user to assess the summarized data substantially at a glance. The data can be filtered into tracklets, groups and clusters, based on system confidence in the identification of the object or activity, to provide multiple levels of granularity.

Abstract: A computer vision system configured for detection and recognition of objects in video and still imagery in a live or historical setting uses a teacher-student object detector training approach to yield a merged student model capable of detecting all of the classes of objects any of the teacher models is trained to detect. Further, training is simplified by providing an iterative training process wherein a relatively small number of images is labeled manually as initial training data, after which an iterated model cooperates with a machine-assisted labeling process and an active learning process where detector model accuracy improves with each iteration, yielding improved computational efficiency. Further, synthetic data is generated by which an object of interest can be placed in a variety of setting sufficient to permit training of models. A user interface guides the operator in the construction of a custom model capable of detecting a new object.

Abstract: A computer vision system configured for detection and recognition of objects in video and still imagery in a live or historical setting uses a teacher-student object detector training approach to yield a merged student model capable of detecting all of the classes of objects any of the teacher models is trained to detect. Further, training is simplified by providing an iterative training process wherein a relatively small number of images is labeled manually as initial training data, after which an iterated model cooperates with a machine-assisted labeling process and an active learning process where detector model accuracy improves with each iteration, yielding improved computational efficiency. Further, synthetic data is generated by which an object of interest can be placed in a variety of setting sufficient to permit training of models. A user interface guides the operator in the construction of a custom model capable of detecting a new object.

Abstract: A computer vision system configured for detection and recognition of objects in video and still imagery in a live or historical setting uses a teacher-student object detector training approach to yield a merged student model capable of detecting all of the classes of objects any of the teacher models is trained to detect. Further, training is simplified by providing an iterative training process wherein a relatively small number of images is labeled manually as initial training data, after which an iterated model cooperates with a machine-assisted labeling process and an active learning process where detector model accuracy improves with each iteration, yielding improved computational efficiency. Further, synthetic data is generated by which an object of interest can be placed in a variety of setting sufficient to permit training of models. A user interface guides the operator in the construction of a custom model capable of detecting a new object.

Abstract: A location detection system performs a process that uses data from a satellite navigation sensor in conjunction with data from a second sensor to determine the accuracy of location estimates provided by the satellite navigation sensor. The system uses the satellite navigation sensor to determine location estimates from at a first time and a second time. The system also uses data from the second sensor to determine a third location estimate, which represents another estimate of the system's location at the second time. The system uses the three location estimates to determine whether the second location estimate satisfies an accuracy condition. If the accuracy condition is satisfied, then the second location estimate may be provided as input to a process.

Abstract: Architecture that summarizes a large amount (e.g., thousands of miles) of street-level image/video data of different perspectives and types (e.g., continuous scan-type data and panorama-type data) into a single view that resembles aerial imagery. Polygons surfaces are generated from the scan patterns and the image data is projected onto the surfaces, and then rendered into the desired orthographic projection. The street-level data is processed using a distributed computing approach across cluster nodes. The collection is processed into image tiles on the separate cluster nodes representing an orthographic map projection that can be viewed at various levels of detail. Map features such as lower-level roads, that are at lower elevations than higher-level roads, and are hidden by higher-level overpassing roads, can be navigated in the map. With the summarized data, the maps can be navigated and zoomed efficiently.

Abstract: A location detection system performs a process that uses data from a satellite navigation sensor in conjunction with data from a second sensor to determine the accuracy of location estimates provided by the satellite navigation sensor. The system uses the satellite navigation sensor to determine location estimates from at a first time and a second time. The system also uses data from the second sensor to determine a third location estimate, which represents another estimate of the system's location at the second time. The system uses the three location estimates to determine whether the second location estimate satisfies an accuracy condition. If the accuracy condition is satisfied, then the second location estimate may be provided as input to a process.

Abstract: Architecture that summarizes a large amount (e.g., thousands of miles) of street-level image/video data of different perspectives and types (e.g., continuous scan-type data and panorama-type data) into a single view that resembles aerial imagery. Polygons surfaces are generated from the scan patterns and the image data is projected onto the surfaces, and then rendered into the desired orthographic projection. The street-level data is processed using a distributed computing approach across cluster nodes. The collection is processed into image tiles on the separate cluster nodes representing an orthographic map projection that can be viewed at various levels of detail. Map features such as lower-level roads, that are at lower elevations than higher-level roads, and are hidden by higher-level overpassing roads, can be navigated in the map. With the summarized data, the maps can be navigated and zoomed efficiently.

Abstract: Architecture that summarizes a large amount (e.g., thousands of miles) of street-level image/video data of different perspectives and types (e.g., continuous scan-type data and panorama-type data) into a single view that resembles aerial imagery. Polygons surfaces are generated from the scan patterns and the image data is projected onto the surfaces, and then rendered into the desired orthographic projection. The street-level data is processed using a distributed computing approach across cluster nodes. The collection is processed into image tiles on the separate cluster nodes representing an orthographic map projection that can be viewed at various levels of detail. Map features such as lower-level roads, that are at lower elevations than higher-level roads, and are hidden by higher-level overpassing roads, can be navigated in the map. With the summarized data, the maps can be navigated and zoomed efficiently.