Abstract: Systems, methods and computer-readable media for creating and using video analysis rules that are based on map data are disclosed. A sensor(s), such as a video camera, can track and monitor a geographic location, such as a road, pipeline, or other location or installation. A video analytics engine can receive video streams from the sensor, and identify a location of the imaged view in a geo-registered map space, such as a latitude-longitude defined map space. A user can operate a graphical user interface to draw, enter, select, and/or otherwise input on a map a set of rules for detection of events in the monitored scene, such as tripwires and areas of interest. When tripwires, areas of interest, and/or other features are approached or crossed, the engine can perform responsive actions, such as generating an alert and sending it to a user.

Abstract: A monitoring method and system are disclosed. In one embodiment, a method includes monitoring the health of a person in a home. The method includes capturing a video sequence from a first camera disposed within the home, including capturing two-dimensional image data for the video sequence; receiving depth data corresponding to the two-dimensional data, and associating the depth data with the video sequence as metadata; setting a plurality of events to monitor associated with the person, the events defined to include actions captured from the first camera, at least a first event including the person's body being in a particular bodily position and performing video content analysis on the video sequence to determine whether the events have occurred.

Abstract: A method for determining a likelihood that a first object captured in a first image and a second object captured in a second image are the same object includes capturing the first image from a first viewpoint and a second image from a second viewpoint, wherein the first object is in the first image, and the second object is in the second image. The method also includes determining a first likelihood that a first visual feature on the first object and a second visual feature on the second object are the same visual feature, and determining a second likelihood that a dimension of the first object and a corresponding dimension of the second object are the same. The method then includes determining a final likelihood that the first object and the second object are the same object based at least partially upon the first likelihood and the second likelihood.

Abstract: A video surveillance system, device and methods may accurately model the shape of a human object monitored by a video stream. 3D human models, such as a coarse 3D human model and a detailed 3D human model may be estimated by mapping individual body part components to a frame. For example, a coarse 3D human model may be obtained by mapping the cylindrical body parts to a plurality of skeleton pose estimates on a part by part basis. A detailed 3D human model may be estimated by mapping detailed human body parts to respective the cylindrical body parts of the coarse 3D human model on a part by part basis. The detailed 3D human model may be used to detect accessories of the human object being monitored, as well as overall dimensions, body part dimensions, age, and gender of the human object being monitored.

Abstract: A video surveillance system is set up, calibrated, tasked, and operated. The system extracts video primitives and extracts event occurrences from the video primitives using event discriminators. The system can undertake a response, such as an alarm, based on extracted event occurrences.

Abstract: A method is provided for augmenting video feed obtained by a camera of a aerial vehicle to a user interface. The method can include obtaining a sequence of video images with or without corresponding sensor metadata from the aerial vehicle; obtaining supplemental data based on the sequence of video images and the sensor metadata; correcting an error in the sensor metadata using a reconstruction error minimization technique; creating a geographically-referenced scene model based on a virtual sensor coordinate system that is registered to the sequence of video images; overlaying the supplemental information onto the geographically-referenced scene model by rendering geo-registered data from a 3D perspective that matches a corrected camera model; creating a video stream of a virtual representation from the scene from the perspective of the camera based on the overlaying; and providing the video stream to a UI to be render onto a display.

Abstract: The present disclosure provides for a method, device, and computer-readable storage medium for performing a method for discerning a vehicle at an access control point. The method including obtaining a video sequence of the access control point; detecting an object of interest from the video sequence; tracking the object from the video sequence to obtain tracked-object data; classifying the object to obtain classified-object data; determining that the object is a vehicle based on the classified-object data; and determining that the vehicle is present in a predetermined detection zone based on the tracked-object data.

Abstract: A content analysis engine receives video input and performs analysis of the video input to produce one or more gross change primitives. A view engine coupled to the content analysis engine receives the one or more gross change primitives from the content analysis engine and provides view identification information. A rules engine coupled to the view engine receives the view identification information from the view engine and provides one or more rules based on the view identification information. An inference engine performs video analysis based on the one or more rules provided by the rules engine and the one or more gross change primitives.

Abstract: A video surveillance system extracts video primitives and extracts event occurrences from the video primitives using event discriminators. The system can undertake a response, such as an alarm, based on extracted event occurrences.

Abstract: A method and system using face tracking and object tracking is disclosed. The method and system use face tracking, location, and/or recognition to enhance object tracking, and use object tracking and/or location to enhance face tracking.

Abstract: A video surveillance system may include at least one sensing unit capable of being operated in a scanning mode and a video processing unit coupled to the sensing unit, the video processing unit to receive and process image data from the sensing unit and to detect scene events and target activity.

Abstract: A method and system for performing video content analysis based on two-dimensional image data and depth data are disclosed. Video content analysis may be performed on the two-dimensional image data, and then the depth data may be used along with the results of the video content analysis of the two-dimensional data for tracking and event detection.

Abstract: Provided is a computer-implemented method for processing one or more video frames. The meth can include generating, by a processor, a change in value of one or more pixels obtained from the one or more video frames; classifying, by the processor, the change in value of the one or more pixels to produce one or more classes of the change in value of the one or more pixels, wherein the one or more classes include one or more of a stationary target, a moving target, a target insertion, a target removal, or a local change; and constructing, by the processor, a listing of detected targets based on the one or more classes.

Abstract: A method and system for monitoring a retail environment by performing video content analysis based on two-dimensional image data and depth data are disclosed. Accuracy in customer actions to provide assistance, change marketing behavior, safety and theft, for example, is increase by analyzing video containing two-dimensional image data and associated depth data. Height data may be obtained from depth data to assist in object detection, object classification (e.g., detection a customer or inventory) and/or event detection.

Abstract: The present disclosure provides for a method, device, and computer-readable storage medium for performing a method for discerning a vehicle at an access control point. The method including obtaining a video sequence of the access control point; detecting an object of interest from the video sequence; tracking the object from the video sequence to obtain tracked-object data; classifying the object to obtain classified-object data; determining that the object is a vehicle based on the classified-object data; and determining that the vehicle is present in a predetermined detection zone based on the tracked-object data.

Abstract: Methods, devices and systems for performing video content analysis to detect humans or other objects of interest a video image is disclosed. The detection of humans may be used to count a number of humans, to determine a location of each human and/or perform crowd analyses of monitored areas.

Abstract: Some embodiments remove an obstruction, e.g., a smudge, from a video. The video may be broken down into layers, and every pixel in space/time may be assigned a layer. Typically, the obstruction will be on one layer, and the background and foreground will be on other layers. Some embodiments detect which layer is generated by the smudge. Some embodiments use a motion model as a judging criteria for deciding the smudge layer.

Abstract: A system and method for video surveillance and searching are disclosed. Video is analyzed and events are automatically detected. Based on the automatically detected events, textual descriptions are generated. The textual descriptions may be used to supplement video viewing and event viewing, and to provide for textual searching for events.

Abstract: A sensing device includes: a video imager to obtain a video; a processing unit to receive and process the video from the video imager; and a communication channel to output non-imagery signals.

Abstract: A method and system for monitoring buildings (including houses and office buildings) by performing video content analysis based on two-dimensional image data and depth data are disclosed. Occupation and use of such buildings may be monitored with higher accuracy to provide higher energy efficiency usage, to control operation of components therein, and/or provide better security. Height data may be obtained from depth data to provide greater reliability in object detection, object classification and/or event detection.