387 results about "Object matching" patented technology

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.

A method and device for executing an application include operations of displaying an interest object on a screen of the device, in response to selection of the interest object, obtaining metadata matched with the interest object, determining an associated application associated with the interest object, executing the associated application by using the metadata as an input value to the associated application, and displaying, on the screen, a window indicating an execution result of the associated application executed by using the metadata.

Embodiments of the invention allow a consumer to make an online purchase of an encountered item. In one embodiment the encountered item to be purchased is photographed by a camera in, e.g., a cell phone. The image is sent via the cellular phone network to the Internet where it is received by a commerce center. The commerce center includes automated and manual image-matching tools. If the image is matched (i.e., identified with a predetermined degree of confidence) a message is sent back to the consumer's cell phone to indicate the cost to purchase the image from the commerce center or from another source. The consumer indicates whether and how many of the item type to purchase. Assuming the consumer has registered with the commerce center to provide transaction information such as a name, credit card number, shipping address, etc., the commerce center completes the transaction. Transaction options are available, such as allowing the consumer to request more information to be sent to the consumer's personal computer email address, have hardcopy information mailed, allowing the consumer to specify the item delivered to another party, selecting the item as a gift, obtaining information on related items, etc.

A method and system of electronically inspecting baggage comprises generating scan data representative of a piece of baggage. At least one of a contour and a surface is extracted from the scan data, and the at least one of a contour and a surface is representative of an object within the baggage. An object database comprises data representative of shapes of known objects, and the at least one of a contour and surface is compared to the object database to identify an object match which is presented.

Modeling systems and methods for constructing one or more models of a computing system using collected data. Certain model-based systems build topology models and/or model instances by transforming collected performance data into a collection-location independent form. In certain examples, systems include at least one agent for collecting performance data from monitored resource(s), canonical data transform (CDT) configurations, and a data transformation module for performing data transform operation(s) on the performance data based on at least one CDT configuration. The data transform operation may include generating and/or updating a topology model, assigning metrics to model object(s), updating properties of model object(s), creating associations between existing model objects, or the like. Certain systems and methods also allow for a single piece of data to be processed by multiple models or for pieces of data collected from different locations to be matched and/or associated with the same model object.

A method of searching a collection of data that includes specifying a compound query having two or more search parameters; identifying data objects in the collection that match the search parameters; and providing results that include both an identification of matching data objects and an extent to which the objects match respective ones of the search parameters. The extent of match is shown by graphical bars having elongated segments of a unique color associated with each search parameter so that the user may visually appreciate the relevance of respective parameters in the compound query. A client device communicating with a server, receives an applet to effect the user interface. Each search parameter has an associated unique color and the user may specify a range of relevance desired in the results by altering the strength of any one of the search parameters. A computer-readable medium embodying program code and a corresponding apparatus are also disclosed.

The invention discloses a virtual object display device based on augmented reality. The device resides in a mobile terminal provided with a camera and a display screen and comprises an image capturing module for capturing images containing markers in the current real scene via the camera, a position acquiring module for acquiring the current geographical location information, a feature extraction module for performing feature detection on captured images and extracting feature points of the markers in the images, an object matching module for determining image templates which are associated with the acquired geographical location information and contain the markers in a database according to the extracted feature points and acquiring virtual objects corresponding to the image templates and an object display module suitable for superposing the images in the current real scene with the acquired virtual objects to obtain a corresponding virtual scene and displaying the virtual scene via the display screen. The invention further discloses a corresponding method and system.

A method includes receiving video data and identifying a second object in at least one video frame of the video data. The method also includes determining whether to replace the second object in the at least one video frame with a first object based on at least one object matching rule. In response to determining that the second object is to be replaced with the first object, the method includes manipulating the three-dimensional model of the first object to generate a representation of the first object that matches at least one visual property of the second object and replacing the second object with the representation of the first object in the at least one video frame.

Data indicative of physical characteristics of an object of interest is received at a recognition system having an associated database in which is stored physical characteristic data for a plurality of reference objects each of which is cross-referenced to configuration information for a universal controlling device. The reference system uses the received data and the physical characteristic data for the plurality of reference objects to discern one or more reference objects as being a match for the object of interest. At least a subset of the configuration information that has been cross-referenced to the one or more reference objects discerned by the recognition system as being a match for the object of interest is then used to configure the universal controlling device to enable the universal controlling device to communicate commands to one or more target appliances.

Techniques for automatically comparing one or more objects determined from digital media content (e.g., an image, audio information, video information) to one or more objects specified by a machine readable identifier to determine if an object determined from the media content matches an object specified by the machine readable identifier. One or more actions may be initiated upon determining that an object determined from the media content matches an object specified by the machine readable identifier. Information identifying the action to be initiated may also be encapsulated by the machine readable identifier.

A method and apparatus for providing speech control to a graphical user interface (GUI) divide a GUI into a plurality of screen areas; assign the screen areas priorities; receive a first audio input relating to the selection of one of the objects in the interface; determine the one of the screen areas having the highest priority and including a first object matching the first audio input; and select the first object in the determined screen area if the determined screen area only contains one object matching the first audio input. The method and apparatus also select one of the objects that matches the first audio input in the determined screen area if the determined screen area contains more than one object that matches the first audio input.

An object recognition ingestion system is presented. The object ingestion system captures image data of objects, possibly in an uncontrolled setting. The image data is analyzed to determine if one or more a priori know canonical shape objects match the object represented in the image data. The canonical shape object also includes one or more reference PoVs indicating perspectives from which to analyze objects having the corresponding shape. An object ingestion engine combines the canonical shape object along with the image data to create a model of the object. The engine generates a desirable set of model PoVs from the reference PoVs, and then generates recognition descriptors from each of the model PoVs. The descriptors, image data, model PoVs, or other contextually relevant information are combined into key frame bundles having sufficient information to allow other computing devices to recognize the object at a later time.

The invention discloses a monocular camera and millimeter wave radar fused object identification and positioning method and system, and belongs to the technical field of multi-sensor fusion. The method comprises the following steps: step 1, sensor data acquisition and frame synchronization; 1a, millimeter wave radar and monocular camera data acquisition; 1b, data sequence matching based on frame synchronization; 2, recognition of an object and a boundary based on the neural network processing image; 2a, training in advance an instance partition neural network based on Mask-RCNN; 2b, completingobject recognition and image instance segmentation by using a neural network; 3, coordinate system conversion and data fusion; 3a, under the condition of known external parameters between sensors, converting radar point cloud to an image coordinate system; 3b, completing object matching information fusion based on an instance segmentation result; and 3c, displaying the object category and the object spatial position under the three-dimensional coordinate system. The method is more stable, and the influence of severe weather on data acquisition can be overcome.

Aspects of the disclosure provide a method for processing point cloud data. A plurality of frames of the point cloud data collected from an environment surrounding a pathway are classified into categories based on distances between three-dimensional points of respective frames of the point cloud data and a reference plane of the respective frame of the point cloud data. The distances indicate heights of the three-dimensional points of the plurality of frames of the point cloud data. The frames of the point cloud data of a same one of the categories that matches a pathway object are merged. Candidate point cloud data of three-dimensional points having distances from the pathway that satisfy a predetermined condition is extracted from the merged frames of the point cloud data. Point cloud data conforming to a feature of the pathway object is extracted from the candidate point cloud data.

A method of tracking an object includes obtaining an image captured by a camera, setting a plurality of patterns having various sizes, according to a distance from a horizon in the image to a plurality of pixels in the image, extracting an object matching one of the plurality of patterns having various sizes, while scanning the image using the plurality of patterns having various sizes, and displaying information about a position of the extracted object in the image.

Methods and systems provide a computational assistance for interactive classification that compensates for the small size of computer screens and accelerates classification tasks. Similarity indicators reduce manual search by enabling information objects to "call out" automatically to encourage a sensemaker to place related items nearby. Similarity terms signal which groups or objects match and why they match. Using these techniques, an interactive classification tool can focus a sensemaker's attention, move things into view automatically, and provide shortcuts for automatic classification. These techniques speed up classification for rule-based classification, example-based classification, and mixed strategies and have the potential for application in a wide variety of sensemaking tools.

The invention discloses a safety cap wearing condition detection method based on video stream data; the method comprises the following steps: obtaining video stream data; extracting moving objects; matching body objects; locating heads; matching safety cap colors; matching safety cap contours; matching safety cap wearing features. The method can provide multi-detection means, can combine the moving object detection, body object matching, head locating, safety cap color and contour matching and safety cap wearing feature matching technologies, thus greatly improving the safety cap and safety cap correct wearing recognition rate; the method can automatically identify and detect the safety cap wearing conditions of workers in the construction field, thus preventing workers wearing no safety cap or carrying safety caps by hands from entering the construction area, assisting construction area safety monitoring units of all levels to realize construction area intelligent monitoring, and improving the construction area safety monitoring informatization level.

The embodiment of the invention discloses a positioning shooting method and a mobile terminal. The method includes the following steps: collecting a preview image of a current scene through a rotary camera when a shooting instruction of the current scene is received; identifying whether a target shooting object matching a reference object exists in the preview image; and controlling the rotary camera to rotate when identifying that the target shooting object exists in the preview image so that the target shooting object in a to-be-shot image is in a preset positioning frame. On the basis of the shooting instruction, the rotary camera is controlled to focus the target shooting object and shoot a to-be-shot image. Through the method, the shooting efficiency is improved while a good shooting effect is guaranteed.

A high-speed automatic multi-object tracking method with kernelized correlation filters is provided. The method includes obtaining an image frame from a plurality of image frames in a video, extracting a foreground object sequence from the obtained image frame, and determining similarity between each foreground object of the extracted foreground object sequence and a tracked object. The method also includes calculating HOG features of the foreground objects with a lower similarity, obtaining training samples for each of the foreground objects with the lower similarity using a circular matrix, obtaining a classifier via a kernel method accelerated by FFTW, and obtaining tracking points using a sparse optical flow. Further, the method includes detecting object matching responses using a detection response function, performing multi-scale analysis for the object based on an optical flow method, and processing a next image frame of the plurality of image frames in the video until the video ends.

The present invention relates to a pseudonode used for deployment on a peer to peer network which pseudonode comprises an IP address and client ID that is changeable upon the occurrence of a preselected event and includes a list containing at least one searchable data object. The pseudonode is programmed for monitoring the network to receive search requests therefrom and to compare each said received search with said list of data objects and to respond to such request. The invention also provides a method for monitoring search requests for selected objects by nodes on a peer to peer network. The method includes interposing the pseudonodes on the network in which it is configured to provide at least one IP address and optionally at least one client ID. The pseudonode has at least one stored object corresponding to a request object stored at said pseudonode; and monitors the network to detect requests matching at least one of the stored objects and acquires a unique ID generated by any network node requesting the object matching that stored object on the pseudonode and responding to substantially each node representing an acquired ID

An object matching method, system and apparatus. The system can include a multiplicity of RFID tags storing corresponding tag data coupled individually to respective objects. Selected ones of the RFID tags can be programmed with tag data associating the selected ones of the RFID tags with one another. At least one RFID reader/interrogator can be configured to interrogate the RFID tags and responsive to the interrogation to read the corresponding tag data. Finally, matching logic can be programmed to determine whether interrogated ones of the RFID tags contain tag data indicating an association between coupled ones of the objects. Notably, the matching logic can be disposed in the RFID reader/interrogator.