38 results about "Automatic localization" patented technology

This disclosure provides a method and system for automatically recognizing facial expressions at variable resolutions of video. According to one exemplary method, facial expressions are detected, extracted and classified from a video sequence based on an automatic localization of the periocular region associated with a detected and extracted face.

A localization tool is arranged to automatically localize a raw package for a target language, country or geographic region. The raw package is an executable binary stored in a specific location identified in a file system. The raw package includes data that identifies localization information. The localization tool uses the localization information to create a list of files to be localized in the target language, identify any strings to replace within each file, locate the files to be localized in the file system where the raw package is stored, and create any other parameters and functions required to localize the raw package. The raw package is localized by applying the target language, country or geographic region specific information to the files to be localized. The localized package is then stored in a target directory within the file system.

Embodiments include apparatus and methods for generating a localization geometry or occupancy grid for a geographic location. Point cloud that describes a vicinity of a pathway is collected by a distance sensor and describing a vicinity of the pathway. The point cloud data is reduced or filtered to a predetermined volume with respect to the roadway. The remaining point cloud data is projected onto a two-dimensional plane including at least one pixel formation. A volumetric grid is defined according to the at least one pixel formation, and a voxel occupancy for each of a voxels forming the volumetric grid is determined. The arrangement of the voxel occupancies or a sequence of data describing the voxel occupancies is a localization geometry that describes the geographic location of the pathway.

Apparatus and methods are described for generating geometries for stripe-shaped objects. An image is identified that includes a roadway having one or more stripe-shaped objects. The stripe-shaped objects may include lane lines for road edges or lanes of the roadway. The stripe-shaped objects may include a barrier. At least one targeted region within the image is determined. The at least one targeted region is shaped to intersect the one or more stripe-shaped objects and includes a plurality of pixels. An image analysis is performed on the image to determine when the at least one target region includes a pixel in common with the one or more stripe-shaped objects. A geometry is constructed using the pixel in common. The geometry may be used to update a map or subsequently perform localization.

A system and method is provided for determining the geographic location of a three-dimensional metrology instrument. The three-dimensional metrology instrument includes a geographic location determination circuit, such as a GPS. The geographic location determination circuit allows the metrology instrument to synchronize the instruments internal clock to allow cooperative measurements with multiple metrology instruments. The geographic location determination circuit further allows for automatic localization of configuration parameters of the metrology instrument. The geographic location determination circuit still further allows for the recording of location when predetermined environmental events occur.

Embodiments include apparatus and methods for automatic generation of local window-based 2D occupancy grids that represent roadside objects at a region of a roadway and automatic localization based on the 2D occupancy grids. 2D occupancy grids are generated based on an altitude threshold for point cloud data and grid cell occupancy for grid cells of local windows associated with the region of the roadway. The 2D occupancy grids are stored in a database and associated with the region of the roadway. Sensor data from a user located at the region of the roadway is received. The accessed 2D occupancy grids and the received sensor data are compared. Based on the comparison, localization of the user located at the region of the roadway is performed.

The invention relates to an autonomous underwater vehicle (AUV) automatic localization method. The autonomous underwater vehicle (AUV) automatic localization method includes the following steps that firstly, a target position of each AUV which automatically moves to work at the target position is set; secondly, localization accuracy decreases gradually due to affection caused by contrast error of a tracking instrument and water flow after the AUV is submerged; thirdly, each AUV periodically broadcasts coordinate information and coordinate accuracy lambda to the surroundings; and fourthly, each AUV computes localization accuracy in real time and can update coordinates whenever the coordinate accuracy lambda of the AUV is lower than limit value, or coordinate accuracy of at least three adjacent nodes is higher than the AUV. Without adopting conventional water surface or underwater localization anchor buoy, underwater staying work time of the AUVs can be prolonged, and further, the AUVs are distributed without central control and are free of limit of numbers, and no limit is set on the network topological structure, coordinates and accuracy information can be carried on normal communication information, communication quantity is favorably reduced, the technology is mature and operation load is low.

The invention discloses a CT scanning visual localization method, which comprises the following steps: (1) setting a scanned site, scanning parameters and human body parameters of a patient; (2) acquiring one or more localization reference human body characteristics related to the scanned site; (3) in a process of moving a scanning bed, continuously acquiring human body images passing a scanning region and implementing human body characteristic recognition in real time, and acquiring positions, corresponding the localization reference human body characteristics, of the scanning bed; and (4) inaccordance with the acquired scanning bed positions, in combination with anthropometry knowledge, calculating an initial scanning position and an ending scanning position, corresponding to the scanned site, of the scanning bed. According to the CT scanning visual localization method, automatic localization can be implemented in a moving process of the scanning bed in accordance with the selectedscanned site, so that a relatively high processing speed and accurate localization are guaranteed, and the method is friendly to the patient. Meanwhile, the invention also discloses a CT system for implementing the CT scanning visual localization method.

Provided is an in-field apparatus and method for automatic localization of a fault having occurred at power transmission lines of a power supply system, the in-field apparatus includes a preprocessing unit configured to process measured voltage and/or current raw time series data of the power transmission lines to provide a normalized raw data and/or feature representation of the measured raw time series data, and an artificial intelligence module configured to predict an optimal evaluation time used for evaluation of the measured voltage and/or current raw time series data to localize the fault based on the normalized raw data and/or feature representation.

Embodiments include apparatus and methods for automatic detection of pole-like objects for a location at a region of a roadway and automatic localization based on the detected pole-like objects. Pole-like objects are modeled as cylinders and the models are generated based on detected vertical clusters of point cloud data associated to corresponding regions along the region of the roadway. The modeled pole-like objects are stored in a database and associated with the region of the roadway. Sensor data from a user located at the region of the roadway is received. The pole-like object model is accessed and compared to the received sensor data. Based on the comparison, localization of the user located at the region of the roadway is performed.

A computer-implemented system automatically analyzes an electronic document that is a representation of an essay, and it automatically generates localized feedback for specific text spans within the essay. The localized feedback relates to the text span's impact on the overall quality of the essay. The system does this by generating scores for the essay both with and without the text span, and determining an impact value representing the difference between the probable scores. The system then uses the impact value to identify a comment that is appropriate for the text span's impact value.

A 24 color card video key frame automatic localization and color difference time sequence change analysis method is disclosed.The photographing stable period data of the equipment to be tested obtained by prior knowledge is combined with the inter-frame difference method, A 24 color card color difference analysis result is associated with a point in time corresponding to a key frame, The timing sequence change rule of the color difference of 24 color cards in the whole shooting process can be obtained, and the purpose of color difference analysis of 24 color cards in batch can be achieved byautomatically dividing the map card area, which greatly improves the computational efficiency and reduces the computational amount.

The invention relates to a welding machine based on visual localization. The welding machine comprises a base, a movement mechanism mounted on the base, a welding gun module connected with the movement mechanism and a visual localization module, wherein the visual localization module comprises an image acquisition module which is fixedly connected with the welding gun module and is used for acquiring image information of a workpiece to be welded, an illumination module which is matched with the image acquisition module and is used for illuminating the workpiece to be welded, a reference objectwhich has a determined coordinate value, is arranged between the workpiece to be welded and the image acquisition module and is located in a photographing range of the image acquisition module, and an image processing device which is connected with the image acquisition module and is configured to identify and acquire a characteristic pattern in an image, compare the characteristic pattern with the coordinate value of the reference object, calculate an effective coordinate value of the characteristic pattern and transmit the effective coordinate value to the movement mechanism. The inventionfurther relates to an automatic welding method by utilizing the welding machine based on the visual localization, and automatic localization and welding can be realized.

The present disclosure relates to a method and system for identifying and reading a barcode on a circular label. Such method and system, in the embodiment discussed, is concretely addressed to a specific example in the engineering of a barcode reader in an electromechanical system for biological analyses which uses cone-shaped tubes and corresponding strips of fluid containers. It is a requirement of the system that the right cone matches with the right strip. In order to avoid any human error, barcode reading system is implemented, by placing a barcode (e.g. a 2D barcode) on the cone-shaped tube and a barcode on the strip: however the particular shape of the cone poses some problems in the automatic localization and reading of the barcode on the circular label on top of the cone. An additional difficulty of the present system is that of the inclination of barcode reader with respect to the circular label carrying the code, due to the relative positioning of the various components of the machine which does not allow a straight alignment between the reader and the target. With the method according to a preferred embodiment of the present disclosure the circular label is scanned to detect the 2D barcode and it is then read, with a simplified algorithm requiring limited power and hardware resources.

A method for directly generating double-code network diagrams with detailed work lists is demonstrated as the attached drawing 1 in the abstract. The method adopts cross lists as the data structure of a network diagram and arrays, structures and single linked lists as the solution to generate directly the data structure of a double-code network diagram with a detailed work list. A user is first asked to compile a detailed work list which then is read into the memory of a computer by a program; next, the program carries out automatic denomination for a tail node and a heat node of each process and automatic localization for the position of each node and finally transforms a complete detailed work list into a double-code network diagram document. The invention can not only avoid the frequent transformation of the network diagram and reduce the error probability, but also eliminate the trouble of the user for inputting the names of the tail node and head node of each process, thereby significantly improving the design efficiency of the network diagram and providing great convenience for the user in design of new network diagrams.