399 results about "Object search" patented technology

Presenting a subset is disclosed. Information associated with a set of one or more objects is obtained, where the set of one or more objects have been detected from a collection of one or more images. Object search criteria is obtained. A subset of the collection is determined based at least in part on the object search criteria. The subset is presented.

The invention discloses a real-time tracking method and system for a ground moving object based on an UAV. An objection detection and identification module of a ground control station is started to process an image sequence returned from a camera, and the size and central coordinate of a target rectangular frame in a display screen of the ground station are obtained; an object tracking module is started, an algorithm fusion strategy is used to track an object, and if tracking is effective, an object positioning result is output to a tracking instruction generation module; if the object is not positioned, an object searching module is started, and the object is searched and an object positioning result is output to the tracking instruction generation module; and according to the requirement that an object image needs to be positioned in the center of the display screen of the ground station, the tracking instruction generation module generates a UAV position and posture adjusting instruction, and uploads the instruction to a UAV flight control system via a wireless transmission device to adjust the posture in real time. According to the system and method, the matching efficiency is high, realization is easy, the object can be identified effectively, and influence of background noises is avoided.

The application relates to a personalized data searching method and device. The device comprises the following steps: searching a data object according to a query word in a search request of a current user; determining a first behavior characteristic of a historic user in the search access process utilizing the query word according to a historic behavior log, and generating an intention vector of the query word; counting a second behavior characteristic of each user group to the data object according to a user attribute, and generating a preference vector of the user group; computing the similarity of the intention vector of the query word and the preference vector of each user group; using the user group corresponding to the condition that the similarity is greater than a set threshold value as a reference group for determining the intention preference of the current user; adjusting the sorting of the data objects searched by the current user through the query word through adoption of the historic behavior characteristics of the reference group. Thus the performance of a search platform is improved and promoted, the accuracy of a search result output to the user is improved, and the result, which is the most reasonable and the best for the search intention, is output for the user.

Disclosed herein are an apparatus and method for generating evidence video. The apparatus includes a video object indexing unit, a video object search unit, and an evidence video generation unit. The video object indexing unit recognizes an object by storing and analyzing videos received from multiple surveillance cameras, extracts the features of the recognized object, and then generates object metadata. The video object search unit compares received search conditions with the object metadata, and then outputs search results, including the feature information of at least one object, which corresponds to the search conditions. The evidence video generation unit generates an evidence video by aggregating only videos including a specific object selected from the search results.

A computer implemented method of presenting visual content items, comprising: grouping the visual content items according to predefined similarity rules relating to visual characteristics of the visual content items such that each group has a range for the number of its members; selecting a representative visual content item for each group; presenting the representative visual content item of each group that has a minimal number of members above a predefined threshold; and optionally presenting the visual content items alongside the representative visual content items. The grouping may be carried out by using predefined color groups; by using predefined shape groups; or using Keypoints of the visual content items, and relate to groups of human faces, product images and landscape images.

A method and apparatus for tracking a color-based object in video sequences are provided. According to the method, an initial object area in one frame of video sequences desired to be tracked is assigned, and an initial object effective window containing the initial object area is assigned. A frame following the frame containing the assigned initial object area is received as a newly input image, and an object search window containing the initial object area for tracking and the initial object effective window in the newly input image is assigned. Then, the model histogram of the initial object area corresponding to a predetermined bin resolution value and the input histogram of the image in the object search window are calculated. From the calculated object probability image, using a predetermined method, a new object area to which the initial object area moved is obtained in the next frame in which the initial object area of the frame desired to be tracked is given as a previous (tracked) object area. By doing so, the object in video sequences is tracked. Accordingly, using the continuously extracted video object region information, an object-based interactive-type additional information service function in movies, TV programs, and CFs can be implemented effectively.

In a search method and system for reducing the number of memory page-in/page-out operations to display, three dimensional objects are extracted through space search. The system comprises a parameter accepting module (22) which accepts parameters from a user to set up a view volume, a space searching module 24 which searches for an object which is included in the view volume, a tree holding module (28) which holds a multi-dimensional tree describing the three-dimensional coordinates of the object, and a file reading module (29) which loads the object data into memory in file units.

The invention discloses a healthy smart household system and a management method thereof. According to the system, environmental parameters, human body physiological parameters, household electrical appliance working parameters and other data are acquired by parameter detection equipment to perform classified storage, diagram drawing and comprehensive analysis, a part of data and the analysis result are respectively submitted to an environmental protection center, community doctors, household electrical appliance manufacturers and power supply stations to obtain feedback, and household electrical appliances are controlled according to the preset strategies, advice on health and advice on energy conservation are pushed to users and fault prediction is performed on the household electrical appliances according to the analysis result and feedback. Real-time monitoring of the state of health of people and the household electrical appliances, household electrical appliance smart control of the self-adaptive environment and human body state, household energy conservation management based on energy conservation evaluation coefficient, and a wireless object-searching system based on RFID can be realized; a no-disturbing high-efficiency communication mode of household members, equipment and environmental protection mechanisms, community hospitals, power grid companies and the household electrical appliance manufacturers is constructed; and a healthy smart household framework system with the comprehensive characteristics is formulated.

The invention relates to wireless communication technologies for target position measurement in the moving process, and provides a wireless communication system and method for determining the position of a target object. The problems that the target object is low in accuracy of the missing prevention function, low in speed, poor in safety, high in cost and the like are solved. The wireless communication system comprises a main machine and a secondary machine, wherein the main machine comprises a Bluetooth module, a processor module, a mobile sensor, an alarm apparatus and a positioning display, and the secondary machine comprises a Bluetooth module. The wireless communication method comprises the steps that the coordinates of three track points of the main machine are obtained through sensor signal calculation; the distance between each track point and the secondary machine is obtained through a Bluetooth RSSI technology, a security alarm prompt is given out when the distance between each track point and the secondary machine exceeds the security distance, target tracking is started, and the coordinates of the secondary machine are calculated. If the secondary machine moves, the sampling rate of the track points of the main machine is increased, and KALMAN filtering is used for correcting the sampling result so as to improve positioning accuracy. The wireless communication system and method for determining the position of the target object are high in security, short in positioning time, high in object searching speed and positioning accuracy, easy to implement and large in market size.

A method of locating and retrieving data objects on an ad hoc data communication system includes discovering devices comprising the system, identification of discovered devices supporting location and transfer of objects from remote devices, locating a desired data object on the devices of the system, and transferring of the desired object to a destination device.

The invention relates to a clothes advertisement putting method and system based on video leading role identification. The method comprises the following steps: A, face identification, i.e., obtaining such information as face pictures, coordinate positions and the like in video pictures; B, face tracking, i.e., gathering face pictures of the same person in continuous video frames so as to realize preliminary clustering of faces; C, face verification, i.e., calculating a distance between every two face pictures; D, face clustering, i.e., gathering the face pictures of the same person, and finding major roles in a video; E, human body detection, i.e., obtaining correlation information of a human body in the video for each frame of the video pictures by use of an area convolution feature; F, clothes marking, i.e., classifying and marking clothes in human body pictures; G, background removal and human body segmentation and clustering, i.e., cutting human bodies from the pictures, removing backgrounds unnecessary to the human bodies, and segmenting the human body clothes into multiple areas; and H, clothes picture retrieval, i.e., retrieving advertisement objects searching for matched clothes in a database by use of the clothes.

The invention discloses a real-time compression tracking method of multi-characteristic transfer learning. The method comprises the following steps: generating a training sample, and respectively extracting a positive sample and a negative sample for training a classifier from a current frame and a video frame which previously tracks an object; extracting the characteristics of an object and a background in the training sample, projecting an extracted high-dimension characteristic to a low-dimension characteristic of a compression domain by use of two complementary sparse mapping matrixes, and generating two balanced characteristics for indicating the object and the background; constructing and updating the classifier, and training a naive Bayes classifier for classifying samples to be detected by use of the characteristic of the compression domain; and employing a secondary object search strategy. According to the invention, by use of the coarse-to-fine secondary search strategy, the quantity of generated scanning windows is reduced, the quantity of the samples to be detected is reduced, the object search process is accelerated, the scanning window with the maximum response value is taken as a tracked object, and the training sample and the classifier are updated based on this.

Embodiments of the present invention provide an AR-based information processing method, apparatus, AR device, and storage medium. According to the invention, during a process that a user uses an AR device, when a user's eyeball looks at the target object, the image information of the target object being watched by the user's eyeball can be obtained, according to the image information of the targetobject, and superimposing the relevant information of the target object on the AR scene image within the range of the user's field of vision, so that any relevant information of the object searched by the user can be superimposed on the AR scene image according to the user's fixation point in real time, thereby greatly enriching the virtual information superimposed on the AR scene; and accordingto the different concerns of users, users can display the relevant information of the objects of interest to users, without binding the corresponding virtual information for AR scene or part of the objects in AR scene, which can realize the personalized superposition of virtual information in AR scene.

Systems and methods for addressing the problem of specific planar object search from a large-scale image database. Given a query image with a particular object and a planar surface, the systems and methods attempt to find, from a large image corpus, a set of representative images in which that object appears. According to the complexity of geometric transformations between a query image and its target images, the whole problem can be categorized into two classes: Rotation-Scale-Translation (RST)-transformed image search, and affine/homography-transformed image search.

Systems and methods search video data for objects that satisfy a general object description. A database is populated with identified objects and object characteristics detected in video data with at least one identifier that specifies video image data. At least one search parameter is received that presents a general object description. The database is queried based upon the received at least one search parameter. At least one identifier is returned from the database based upon the at least one search parameter.

The invention aims to provide a spatial index structure tree based method and device for providing results of searching spatial objects. The method includes: acquiring a candidate spatial index structure tree; according to a predetermined unit area threshold, subjecting leaf nodes of the candidate spatial index structure tree to node decomposition until a spatial index structure tree is obtained; acquiring a spatial object query request from a user; according to a query area, performing area matching querying on the spatial index structure tree to obtain matching nodes; according to the query request, performing object matching querying on the spatial objects of the matching nodes to obtain spatial object searching results; providing the user with the spatial object searching results. Compared to the prior art, the method and device has the advantages that area matching querying is performed on the spatial index structure tree to obtain the matching nodes according to the spatial object query object from the user, object matching querying is performed on the spatial objects of the matching nodes to obtain the spatial object searching results according to the query request, and the spatial objects can be searched more efficiently.

An object search method, computer program product, and a terminal having an object search function are disclosed. The object search method includes: displaying a list of a plurality of objects including a first object and a second object in a first screen area, and displaying a touch input window for touch input in a second screen area; touching a first position on the touch input window with a pointer and then dragging the pointer to a second position on the touch input window; and moving an object indicator from the first object to the second object on the list as the pointer is dragged from the first position to the second position. Therefore, it is possible to efficiently search for an object.

The invention provides a method for tracking moving objects on a highway. The method comprises the following steps: labeling an interested area and a vehicle driving direction; obtaining a moving object in a current frame; and obtaining an object queue, which is being tracked by the previous frame, obtaining an object queue to be tracked by the previous frame, obtaining an object queue, tracking of which is lost by the previous frame, putting remained moving objects in a queue to be tracked; and initializing for next-frame tracking. According to the invention, according to the vehicle driving characteristics on the highway, only one-way driving direction of a vehicle is arranged in one interested area; the forward driving direction of the vehicle is artificially arranged in combination with the relationship of the erection angle of a camera and a lane; therefore, the characteristic change tendency in the vehicle driving process can be effectively obtained; the number of object searching areas and templates required for searching can be reduced in an object searching and matching stage; and thus, the tracking accuracy and efficiency can be increased to a much greater extent.

The invention relates to a device and method for controlling a cloud service-oriented multiple concurrent service flow based on an HTTP (hyper text transport protocol) service flow management and maintenance system under the condition of a multiple concurrent service flow. The device comprises a server which is in double linkage with a TCP (transmission control protocol) and a client which is used for receiving and caching a HTTP request from the server and caching and maintaining the domain of an HTTP request data object, a URL (uniform resource locator) and destination host information, wherein the server comprises a TCP session number for receiving, caching and confirming a TCP connection request, an HTTP analysis part and an HTTP capsulation part; the client comprises a session management par; the HTTP analysis part and the capsulation part are connected to the session management part; and the session management part is connected to a request object searching part, a far-end data center and a local disk array, which can not only update the data in the local disk array in time but also can avoid the repeatedly supplied data object from the far-end data center, so as to quicken the response to the HTTP request and save the finite bandwidth resource.

A system and method for directing consumer traffic over the Internet properties of affiliated content providers and vendors increases traffic over affiliated sites by embedding a foreign object within those properties, and encouraging consumers to search for that object. Consumers register with the marketing solutions provider in order to become eligible to participate in the object search game. Content providers and vendors also register in order to become part of the said system that directs consumers to various Internet properties. Such an affiliate has their account credited once a consumer has been successfully directed to that affiliated property. The consumer has his or her account credited after successfully finding the object resident on that affiliate's property. Furthermore, in the case of vendors, should a consumer led to that affiliate's Internet property seek to make a purchase while there, relevant information concerning that consumer can be sent directly from the marketing solutions provider to the vendor, making the sales process more convenient for both the vendor and the consumer.

The invention discloses a searching method for an object in a terminal. The searching method for the object in the terminal comprises the following steps of obtaining a character string input by a user when an object searching instruction is detected, obtaining label information matched with the character string, and obtaining and displaying the object which is searched for and corresponds to the label information matched with the character string in the mapping relation table between the prestored label information and the searched object. The invention further discloses a searching device for the object in the terminal. By the adoption of the searching method and device for the object in the terminal, a user can rapidly and conveniently find the object to be searched for on the basis of the character string matched with the label information.

There is provided a method and an apparatus for searching rights objects stored in a portable storage device by using an object location data. The method includes: accessing the portable storage device; transmitting an object identifier to the portable storage device; receiving a location data of a first object searched based on the object identifier from the portable storage device; storing the location data of the first object with the object identifier; and transmitting the location data of the first object and an operation data representing operations to be performed with the first object to the portable storage device by using the location data of the first object.

An object search method, a search verification method, and apparatuses thereof, pertain to the field of video surveillance technologies. The object search method includes: acquiring an object image for search and a designated region of the object image for search, and calculating local feature points in the designated region of the object image for search; searching in a pre-constructed index set for indexes matching the local feature points in the designated region; and acquiring object images corresponding to the detected indexes, and using the acquired object images as detected object images in a video. In this way, object search is implemented by using local regions of an image, the application range of the object search is extended, and accuracy of the search result is improved.

The invention provides a human body multi-joint feature tracking method based on Mean Shift and artificial school intelligent optimization, including the following steps: firstly, based on the color distribution feature of an object model, the optimization position of a tracked human body multi-joint feature at the current frame is obtained according to the image information of a previous frame by means of artificial school intelligent optimization algorithm; then, according to the color distribution feature of the object model, object search is carried out within the domain of the optimization position by means of Mean Shift iteration algorithm, wherein, the candidate object most similar to the color distribution of the object model is the tracked object. The invention which improves the prior Mean Shift and introduces the candidate object area for artificial school intelligent optimization realizes accurate tracking of human body multi-joint feature object.

The invention relates to a wireless telemetering telecontrol system and method with ultra-low power consumption, aiming at achieving an ultra-low power consumption state that a controlled end is in a periodically dormant state and is used for flashly monitoring signals after wake-up. When work commands need to be sent to the controlled end, command signals are continuously sent to the controlled end by a control end in a short time; at the moment of wake-up, the controlled end only receives one-bit or plural limited-bit data signals and checks the RF characteristics thereof, particularly spread spectrum code characteristics; and only when the RF characteristics are verified, an entire data signal packet is received in a time-delay manner and then is analyzed. When the power consumption ofthe controlled end is greatly reduced, a fast wireless channel is maintained between the control end and controlled equipment, thereby opening a door for the wide application of wireless acquisition and transmission of sensor data as well as the wireless telemetering telecontrol of equipment in the IOT (Internet Of things) market. The invention also provides a long-range GPS (Global Positioning System) which is independent of a wireless mobile public network, as well as a simple and effective short-range object searching method.

An anti-lost object search method based on TOF wireless distance measurement comprises the steps that one or more anti-lost subunits bound with an anti-lost object are arranged, all the anti-lost subunits are connected with an anti-lost master unit in a wireless mode, the anti-lost master unit is in wireless connection with a mobile phone or a tablet personal computer carried with a user in a Bluetooth mode, and the anti-lost master unit is used for calculating the distance between the anti-lost master unit and the anti-lost subunits and transmitting the distance information to the mobile phone or the tablet personal computer in a Bluetooth mode so as to display or further process the distance information. The defects that as communication distance is short in the prior art, estimated distance information is prone to being affected by external factors and becomes invalid can be overcome.