Abstract: To address problems that video imaging systems and platforms face when analyzing image and video content for detection and feature extraction, a solution is provided in which accumulating significant amounts of data suitable for training and learning analytics is leveraged to improve over time, the classifiers used to perform the detection and feature extraction, by employing a larger search space and generate additional and more complex classifiers through distributed processing. A distributed learning platform is therefore provided, which is configured for operating on large scale data, in a true big data paradigm. The learning platform is operable to empirically estimate a set of optimal feature vectors and a set of discriminant functions using a parallelizable learning algorithm. A method of adding new data into a database utilized by such a learning platform is also provided.

Abstract: A system and method are provided for performing saliency detection on an image or video. The method includes training and creating deep features using deep neural networks, such that an input image is transformed into a plurality of regions, which minimizes intra-class variance, and maximizes inter-class variance, according to one or more active contour energy constraints. The method also includes providing and output associated with the deep features.

Abstract: A system and method are provided for compressing video data, the method comprising: obtaining video data; extracting at least one object of interest from the video data using at least one classifier associated with at least one feature detectable in the video data; and preparing compressed video data comprising at least one object of interest extracted from the video data.

Abstract: A system and method are provided for mapping spatial and temporal measurements of motion constrained objects in a scene, e.g., vehicles. The method comprises determining a location parameter, and/or other interesting properties, for each of a plurality of objects at a plurality of points over time; generating a vector field over location and time using the location parameters, to specify the motion of each object over time; deriving measurements for each object using velocities from the vector field for that object, as the object moves through the scene over time; and outputting both individual and aggregate object and object property flow for the plurality of objects. Combining the generated map with a network graph and/or network model can provide network flow insights useful for historic event analysis, network flow monitoring, and planning purposes.

Abstract: A system and method are provided for performing saliency detection on an image or video. The method includes training and creating deep features using deep neural networks, such that an input image is transformed into a plurality of regions, which minimizes intra-class variance, and maximizes inter-class variance, according to one or more active contour energy constraints. The method also includes providing and output associated with the deep features.

Abstract: To address problems that video imaging systems and platforms face when analyzing image and video content for detection and feature extraction, a solution is provided in which accumulating significant amounts of data suitable for training and learning analytics is leveraged to improve over time, the classifiers used to perform the detection and feature extraction, by employing a larger search space and generate additional and more complex classifiers through distributed processing. A distributed learning platform is therefore provided, which is configured for operating on large scale data, in a true big data paradigm. The learning platform is operable to empirically estimate a set of optimal feature vectors and a set of discriminant functions using a parallelizable learning algorithm. A method of adding new data into a database utilized by such a learning platform is also provided.

Abstract: A system and method are provided for mapping spatial and temporal measurements of motion constrained objects in a scene, e.g., vehicles. The method comprises determining a location parameter, and/or other interesting properties, for each of a plurality of objects at a plurality of points over time; generating a vector field over location and time using the location parameters, to specify the motion of each object over time; deriving measurements for each object using velocities from the vector field for that object, as the object moves through the scene over time; and outputting both individual and aggregate object and object property flow for the plurality of objects. Combining the generated map with a network graph and/or network model can provide network flow insights useful for historic event analysis, network flow monitoring, and planning purposes.

Abstract: A system and method are provided for compressing video data, the method comprising: obtaining video data; extracting at least one object of interest from the video data using at least one classifier associated with at least one feature detectable in the video data; and preparing compressed video data comprising at least one object of interest extracted from the video data.