摘要:
Described is a method and system for embedding unsupervised learning into three critical processing stages of the spatio-temporal visual stream. The system first receives input video comprising input video pixels representing at least one action and at least one object having a location. Microactions are generated from the input image using a set of motion sensitive filters. A relationship between the input video pixels and the microactions is then learned, and a set of spatio-temporal concepts is learned from the microactions. The system then learns to acquire new knowledge from the spatio-temporal concepts using mental imagery processes. Finally, a visual output is presented to a user based on the learned set of spatio-temporal concepts and the new knowledge to aid the user in visually comprehending the at least one action in the input video.
摘要:
Described is a system for object and behavior recognition which utilizes a collection of modules which, when integrated, can automatically recognize, learn, and adapt to simple and complex visual behaviors. An object recognition module utilizes a cooperative swarm algorithm to classify an object in a domain. A graph-based object representation module is configured to use a graphical model to represent a spatial organization of the object within the domain. Additionally, a reasoning and recognition engine module consists of two sub-modules: a knowledge sub-module and a behavior recognition sub-module. The knowledge sub-module utilizes a Bayesian network, while the behavior recognition sub-module consists of layers of adaptive resonance theory clustering networks and a layer of a sustained temporal order recurrent temporal order network. The described invention has applications in video forensics, data mining, and intelligent video archiving.
摘要:
The present invention relates to a classifier cascade object detection system. The system operates by inputting an image patch into parallel feature generation modules, each of the feature generation modules operable for extracting features from the image patch. The features are provided to an opportunistic classifier cascade, the opportunistic classifier cascade having a series of classifier stages. The opportunistic classifier cascade is executed by progressively evaluating, in each classifier in the classifier cascade, the features to produce a response, with each response progressively utilized by a decision function to generate a stage response for each classifier stage. If each stage response exceeds a stage threshold then the image patch is classified as a target object, and if the stage response from any of the decision functions does not exceed the stage threshold, then the image patch is classified as a non-target object.
摘要:
Described is a system for registering a viewpoint of an imaging sensor with respect to a geospatial model or map. An image of a scene of a geospatial region comprising an object is received as input. The image of the scene is captured by a sensor having a current sensor state. Observation data related to the object's state is received, wherein the observation data comprises an object behavior of the object given the geospatial region. An estimate of the current sensor state is generated using a probability of an observation from the observation data given the current sensor state x. Finally, the image of the scene is registered with a geospatial model or map based on the estimate of the current sensor state.
摘要:
Disclosed is a method and system for generic object detection using block-based feature computation and, more specifically, a method and system for massively parallel computation of object features sets according to an optimized clock-cycle matrix. The method uses an array of correlators to calculate block sums for each section of the image to be analyzed. A greedy heuristic scheduling algorithm is executed to produce an optimized clock cycle matrix such that overlapping features which use the same block sum do not attempt to access the block at the same time, thereby avoiding race memory conditions. The processing system can employ any of a variety of hardwired Very Large Scale Integration (VLSI) chips such as Field Programmable Gate Arrays (FPGAs), Digital Signal Processors (DSPs) and Application Specific Integrated Circuits (ASICs).
摘要:
Anomaly prediction of battery parasitic load includes processing input data related to a state of charge for a battery and a durational factor utilizing a machine learning algorithm and generating a predicted start-up state of charge. Warnings are issued if the predicted start-up state of charge drops below a threshold level within an operational time.
摘要:
A vision-based system for automatically detecting the type of object within a specified area, such as the type of occupant within a vehicle is presented. The type of occupant can then be used to determine whether an airbag deployment system should be enabled or not. The system extracts different features, including wavelet features and/or a disparity map from images captured by image sensors. These features are then processed by classification algorithms to produce class confidences for various occupant types. The occupant class confidences are fused and processed to determine occupant type. In a preferred embodiment, image features from image edges, wavelet features, and disparity are used. Various classification algorithms may be implemented to classify the object. Use of the disparity map and/or wavelet features provides greater computational efficiency.
摘要:
An object recognition system is described that incorporates swarming classifiers. The swarming classifiers comprise a plurality of software agents configured to operate as a cooperative swarm to classify an object group in a domain. Each node N represents an object in the group having K object attributes. Each agent is assigned an initial velocity vector to explore a KN-dimensional solution space for solutions matching the agent's graph. Further, each agent is configured to search the solution space for an optimum solution. The agents keep track of their coordinates in the KN-dimensional solution space that are associated with an observed best solution (pbest) and a global best solution (gbest). The gbest is used to store the best solution among all agents which corresponds to a best graph among all agents. Each velocity vector thereafter changes towards pbest and gbest, allowing the cooperative swarm to classify of the object group.
摘要:
Described is a method for image registration utilizing particle swarm optimization (PSO). In order to register two images, a set of image windows is first selected from a test image and transformed. A plurality of software agents is configured to operate as a cooperative swarm to optimize an objective function, and an objective function is then evaluated at the location of each agent. The objective function represents a measure of the difference or registration quality between at least one transformed image window and a reference image. The position vectors representing the current individual best solution found and the current global best solution found by all agents are then updated according to PSO dynamics. Finally, the current global best solution is compared with a maximum pixel value which signifies a match between an image window and the reference image. A system and a computer program product are also described.
摘要:
The present invention relates to a method for three-dimensional (3D) object recognition using region of interest geometric features. The method includes acts of receiving an implicit geometry representation regarding a three-dimensional (3D) object of interest. A region of interest (ROI) is centered on the implicit geometry representation such that there is at least one intersection area between the ROI and the implicit geometry representation. Object shape features are calculated that reflect a location of the ROI with respect to the implicit geometry representation. The object shape features are assembled into a feature vector. A classification confidence value is generated with respect to a particular object classification. Finally, the 3D object of interest is classified as a particular object upon the output of a statistical classifier reaching a predetermined threshold.