Abstract: Methods and systems detect objects of interest in a spatio-temporal signal. According to one embodiment, a system processes a digital spatio-temporal input signal containing zero or more foreground objects of interest superimposed on a background. The system comprises a foreground/background separation module, a foreground object grouping module, an object classification module, and a feedback connection. The foreground/background separation module receives the spatio-temporal input signal and, according to one or more adaptable parameters, produces foreground/background labels designating elements of the spatio-temporal input signal as either foreground or background. The foreground object grouping module is connected to the foreground/background separation module and identifies groups of selected foreground-labeled elements as foreground objects. The object classification module is connected to the foreground object grouping module and generates object-level information related to the foreground object.

Abstract: Methods and systems detect objects of interest in a spatio-temporal signal. According to one embodiment, a system processes a digital spatio-temporal input signal containing zero or more foreground objects of interest superimposed on a background. The system comprises a foreground/background separation module, a foreground object grouping module, an object classification module, and a feedback connection. The foreground/background separation module receives the spatio-temporal input signal as an input and, according to one or more adaptable parameters, produces as outputs foreground/background labels designating elements of the spatio-temporal input signal as either foreground or background. The foreground object grouping module is connected to the foreground/background separation module and identifies groups of selected foreground-labeled elements as foreground objects.

Abstract: A camera system comprises an image capturing device and an object classification module connected to the image capturing device. The image capturing device has a field of view and produces image data representing an image of the field of view. The object classification module is operable to determine whether or not an object in an image is a member of an object class. The object classification module includes N decision steps configured in a cascade configuration, wherein at least one of the N decision steps is operable to (a) accept an object as a member of the object class, (b) reject an object as a member of the object class, and (c) call on a next step to determine whether or not an object is a member of the object class.

Abstract: A camera system comprises an image capturing device, object detection module, object tracking module, and match classifier. The object detection module receives image data and detects objects appearing in one or more of the images. The object tracking module temporally associates instances of a first object detected in a first group of the images. The first object has a first signature representing features of the first object. The match classifier matches object instances by analyzing data derived from the first signature of the first object and a second signature of a second object detected in a second image. The second signature represents features of the second object derived from the second image. The match classifier determine whether the second signature matches the first signature. A training process automatically configures the match classifier using a set of possible object features.

Abstract: Video analytics and a mass storage unit are contained in a camera housing of a video camera. The video analytics analyzes video data produced by the video camera and detects whether there is an occurrence of a defined event of interest. The video data representing the field of view of the scene observed by the video camera are stored in the mass storage unit. The stored video data include video data of first and second qualities. The first quality represents the occurrence in a field of view of the video camera of the defined event of interest detected by the video analytics. The second quality represents the nonoccurrence in the field of view of the defined event of interest detected by the video analytics. Storing video data of first and second qualities reduces system storage capacity demands.

Abstract: A storage buffer and a hard-disk drive are provided in a video data storage application. The hard-disk drive operates normally in a powered-down state, and video data are stored in the storage buffer during a first time interval. The hard-disk drive is operated in a powered-up state. A portion of the video data stored in the storage buffer is transferred to and stored in the hard-disk drive in the powered-up state during a second time interval that is substantially shorter than the first time interval. The hard-disk drive is returned to the powered-down state. A total hard-disk drive storage time, representing a sum of the second time intervals, spent transferring to and storing a portion of the video data in the hard-disk drive is substantially less than a total buffer storage time, representing a sum of the first time intervals, spent storing the video data in the storage buffer.

Abstract: An automated electronic video surveillance system enables a high-resolution mega-pixel camera to capture high quality, detailed, magnified images at multiple locations, simultaneously with an overview of the whole scene. A preferred embodiment requiring no moving parts provides full 360-degree continuous viewing with up to 5× all-digital zoom capability. The system performs continuous surveillance and active resolution allocation in the form of a feedback control subsystem that dynamically allocates resources so that important details within a scene receive appropriate scrutiny, while uninteresting areas are imaged at a lower resolution.

Abstract: A method senses electromagnetic energy associated with a source over an area in N frequency bands and generates color image data representing at least a portion of the area. The data are arranged as pixels, and the data for a given pixel comprise chroma, hue, and intensity values. The N frequency bands constitute a mathematical basis in N-dimensional space, and one band establishes a first reference vector in the space. Equal parts of all bands establish a second reference vector. A reference plane contains the first and second reference vectors. The data for the pixel correspond to a point in the space, and that point and the second reference vector define a plane of interest. Hue is an angle between the reference plane and the plane of interest. Chroma is an angle between the point and the second reference vector. Intensity is the point's Euclidean norm.

Abstract: A method augments an original discriminator in a classifier. The original discriminator has a set of input connections to receive feature data derived from an input pattern. The original discriminator generates in response to an input pattern a set of original discriminator outputs. The method connects an additional discriminator to the original discriminator. The additional discriminator has a set of parameters. The additional discriminator also has a first set of input connections configured to receive feature data derived from an input pattern and a second set of input connections to receive some or all of the set of original discriminator outputs. The additional discriminator generates a set of outputs in response to said some or all of the set of original discriminator outputs and in response to the feature data according to the set of parameters. The method applies a set of training input patterns to both the original and additional discriminator in parallel.

Abstract: Methods and systems detect objects of interest in a spatio-temporal signal. According to one embodiment, a system processes a digital spatio-temporal input signal containing zero or more foreground objects of interest superimposed on a background. The system comprises a foreground/background separation module, a foreground object grouping module, an object classification module, and a feedback connection. The foreground/background separation module receives the spatio-temporal input signal as an input and, according to one or more adaptable parameters, produces as outputs foreground/background labels designating elements of the spatio-temporal input signal as either foreground or background. The foreground object grouping module is connected to the foreground/background separation module and identifies groups of selected foreground-labeled elements as foreground objects.

Abstract: A method senses electromagnetic energy associated with a source over an area in N frequency bands and generates color image data representing at least a portion of the area. The data are arranged as pixels, and the data for a given pixel comprise chroma, hue, and intensity values. The N frequency bands constitute a mathematical basis in N-dimensional space, and one band establishes a first reference vector in the space. Equal parts of all bands establish a second reference vector. A reference plane contains the first and second reference vectors. The data for the pixel correspond to a point in the space, and that point and the second reference vector define a plane of interest. Hue is an angle between the reference plane and the plane of interest. Chroma is an angle between the point and the second reference vector. Intensity is the point's Euclidean norm.