390 results about "Image flow" patented technology

A method of tracking a face in a reference image stream using a digital image acquisition device includes acquiring a full resolution main image and an image stream of relatively low resolution reference images each including one or more face regions. One or more face regions are identified within two or more of the reference images. A relative movement is determined between the two or more reference images. A size and location are determined of the one or more face regions within each of the two or more reference images. Concentrated face detection is applied to at least a portion of the full resolution main image in a predicted location for candidate face regions having a predicted size as a function of the determined relative movement and the size and location of the one or more face regions within the reference images, to provide a set of candidate face regions for the main image.

A method of tracking faces in an image stream with a digital image acquisition device includes receiving images from an image stream including faces, calculating corresponding integral images, and applying different subsets of face detection rectangles to the integral images to provide sets of candidate regions. The different subsets include candidate face regions of different sizes and / or locations within the images. The different candidate face regions from different images of the image stream are each tracked.

An object-enabled navigation system assists a vision-impaired user in navigating an environment. The system captures 3D movement of a moving object within the environment, wherein the three-dimensional movement is determined using at least one image capture device aimed at the moving object. The system predicts a mobile path of the visually-impaired user. The system determines whether the movement of the moving object will intersect with the mobile path of the vision-impaired user and informs the vision-impaired user whether the movement of the moving object will intersect the mobile path of the vision-impaired user.

A method for following hand movements in an image flow, includes receiving an image flow in real time, locating in each image in the received image flow a hand contour delimiting an image zone of the hand, extracting the postural characteristics from the image zone of the hand located in each image, and determining the hand movements in the image flow from the postural characteristics extracted from each image. The extraction of the postural characteristics of the hand in each image includes locating in the image zone of the hand the center of the palm of the hand by searching for a pixel of the image zone of the hand the furthest from the hand contour.

Methods, systems and computer program products (“software”) enable a virtual three-dimensional visual experience (referred to herein as “V3D”) videoconferencing and other applications, and capturing, processing and displaying of images and image streams.

An image processing apparatus for tracking faces in an image stream iteratively receives a new acquired image from the image stream, the image potentially including one or more face regions. The acquired image is sub-sampled (112) at a specified resolution to provide a sub-sampled image. An integral image is then calculated for a least a portion of the sub-sampled image. Fixed size face detection (20) is applied to at least a portion of the integral image to provide a set of candidate face regions. Responsive to the set of candidate face regions produced and any previously detected candidate face regions, the resolution at which a next acquired image is sub-sampled is adjusted.

Embodiments of the present disclosure provide a method comprising providing 2-D or 3-D graphics content to a graphics processing module; processing the graphics content to generate a stream of images (e.g., three dimensional images and / or two dimensional images) for display, the stream having a frame rate; and governing a rate of processing the graphics content to limit the frame rate of the generated stream of images to be less than or equal to a frame rate threshold. Other embodiments may also be described and claimed.

The invention discloses a method and a system for managing a remote concentrated image, wherein the method is applied to a system comprising a centralized management center and one or a plurality of data centers, and the method comprises the following steps of: receiving a image flow rate which is from the data center and is sent through a GRE ( Generic Routing Encapsulation) tunnel by a router of the centralized management center, searching a next-hop route in a VPN (Virtual Private Network) instance corresponding to the GRE tunnel and sending the image flow rate to a corresponding VLAN (Virtual Local Area Network) interface on an exchanger of the centralized management center; and after the exchanger of the centralized management center receives the image flow rate through the VLAN interface, sending the image flow rate to monitoring equipment through the VLAN interface connected with the monitoring equipment. The invention realizes the three-layer network realization of the monitoring and the management of the remote concentrated image.

A method of distinguishing between regions of an image, separating and masking the original image into multiple image planes, and compressing each separated image plane with a compression method that is optimal for its characteristics. From a video stream, separate image streams can be compressed with different methods, and the separae image streams can be stored or transmitted at different rates. Alternatively, frame differencing can be applied to the separated streams. One method of distinguishing the region of interest is use of an input device to allow the viewer or broadcaster to dynamically select the shape, size, or position of the region. An alternate method of distinguishing the regions of interest is automated analysis of the characteristics of various regions of an image.

An anti-spoofing system operative for repulsing spoofing attacks in which an impostor presents a spoofed image of a registered end user, the system comprising a plurality of spoof artifact identifiers including a processor configured for identifying a respective plurality of spoofed image artifacts in each of a stream of incoming images and a decision maker including a processor configured to determine an individual image in the stream is authentic only if a function of artifacts identified therein is less than a threshold criterion.

A calibration device is presented for use in a surveillance system for event detection. The calibration device comprises an input utility for receiving data indicative of an image stream of a scene in a region of interest acquired by at least one imager and generating image data indicative thereof, and a data processor utility configured and operable for processing and analyzing said image data, and determining at least one calibration parameter including at least one of the imager related parameter and the scene related parameter.

A system and method for classification of images of an image stream includes receiving an image stream of unclassified images, for example produced by an in-vivo imaging device, and adapting an initial classification algorithm to classify images to groups based on at least a subset of the received image stream of unclassified images.

The invention belongs to the technical field of remote sensing image processing and in particular relates to a manifold dimension reduction method of hyperspectral images based on image block distance. According to the method, a novel distance measure, namely an image block distance measure is provided and is applied to neighborhood selection and lower dimension coordinate embedding in manifold learning, and a nonlinear dimension reduction method of novel hyperspectral remote sensing images is obtained. The physical properties of the hyperspectral images are utilized, the spectral information and space information of the images are combined, the local characteristics between data points can be better kept, and the characteristics of an original data set are well kept on the basis of reducing the image information redundancy to the greatest degree. The method has high applicability on various different hyperspectral data, and has important application values in detection and identification aspects of high-precision terrain classification and ground targets based on the hyperspectral remote sensing images.

A method for estimating image-to-image motion of a pixel block in a stream of images which includes a current image which includes the pixel block and a reference image, the method including performing a hierarchical search in a search area of the reference image, including producing a decimated reference image and a decimated pixel block, searching for a location in the search area of the decimated reference image which best fits the decimated pixel block, repeating the producing and the searching for more than one level of hierarchy, determining a first candidate location in the reference image which corresponds to the best fitting location, determining a second candidate location in the reference image by a method other than the hierarchical search, performing a search in the reference image for refined locations of the first and the second candidate locations, selecting one final location from the refined candidate locations, and using the final location for estimating the motion. Related apparatus and methods are also described.

A closed-loop control system for stereoscopic video capture is provided. At least two motorized lenses are positioned in accordance with specified parameters to capture spatially-disparate images of a scene. The motorized lenses focus light on a corresponding one of the at least two sensors, which generate image streams. One or more processors execute instructions to provide a stream analyzer and a control module. The stream analyzer receives the image streams from the sensors and analyzes the image streams and the specified parameters in real time; the stream analyzer then modifies the image streams and generates metadata. The control module then receives and analyzes the image streams and metadata and transmits updated parameters to a control mechanism that is coupled to the at least two motorized lenses. The control mechanism then modifies operation of the at least two motorized lenses in real time in accordance with the updated parameters.

The invention relates to a real three-dimensional display system and a display method; an image projection device in a case is connected with a motion display screen arranged above the case; a display area of the motion display screen is arranged on the top of the case; the motion display screen intercepts two-dimensional image flow projected by the image projection device at different positions of a Z axis; the two-dimensional image flow forms 1-N two-dimensional images at different positions of the Z axis; the motion display screen rotates at the rotating speed of 480 to 600r / min, so that the two-dimensional images which are continuously intercepted at different positions of the Z axis are synthesized into a real three-dimensional image; the real three-dimensional image is displayed in an X,Y,Z three-dimensional space; and the invention randomly observes an scene to be observed in 360 degrees and is used to produce the real three-dimensional image with true physical depth in the three-dimensional space. The invention breaks through the bottleneck of three-dimensional display definition, so as to realize tens of millions of three-dimensional image body elements; the three-dimensional image is directly observed without any auxiliary equipment; and a rear projection type is adopted, the whole system is integrated, so as to facilitate transportation and maintenance.

The invention provides a low-power consumption portable real-time image target detecting and tracking system and a method thereof, which can realize automatic cell cultivation process control and online observation in space and equivalent harsh environments. The system comprises a PL (Programmable Logic) subsystem and a PS (Processing System) subsystem; an image acquisition unit comprises a camera interface module, an image pre-processing module and an AXI-DMA module; the camera interface module is used for reading camera data and controlling parameters of an image resolution, an acquisition frame rat and a data format; the image pre-processing module is used for carrying out pre-processing operation such as color correction, histogram equalization and space transformation on an acquired image flow; the AXI-DMA module is used for realizing self return from image data to DDR3 RAM via an AXI-HP interface; an image acceleration unit comprises a reconfigurable image accelerator and the AXI-DMA module; the reconfigurable image accelerator is used for dynamically loading an image target detecting or image target tracking accelerator according to a system working stage; and the AXI-DMA module is used for realizing self return from image data to DDR3 RAM via an AXI-ACP interface.

The invention discloses a method and device for processing an image. The method comprises the steps of conducting synthetic operation based on two or more branches of frame image flows, and obtaining a panorama frame image flow which corresponds to the environment; analyzing first operation specific to the panorama frame image flow, and obtaining a target area indicated by the first operation in the panorama frame image flow; selecting a target object from objects carried by the target area of the panorama frame image flow, and detecting the position of the target object in each panorama frame image of the panorama frame image flow; based on the position of the target object in each panorama frame image of the panorama frame image flow, segmenting the target object from each panorama frame image, and generating a panorama frame image flow corresponding to the target object. By means of the method and device, multiple target objects can be monitored and tracked accurately.

The invention discloses a fine-grained image classification method and system, computer equipment and a storage medium. The fine-grained image classification method comprises the steps of: establishing a fine-grained image classification network which is a double-branch network for attention inhibition and attention enhancement and comprises a residual network and an attention layer; acquiring a training set, wherein the training set is composed of a plurality of training images; training the fine-grained image classification network by using the training set, and acquiring a fine-grained image classification model by using a gradient-propelled maximum value and minimum value cross entropy loss function; acquiring a to-be-classifiedimage; and inputting the to-be-classified image into the fine-grained image classification model, so that the to-be-classified image flows in the residual network and does not pass through the attention layer, and a category prediction result is obtained. The fine-grained image classification method and the system is implemented based on weak supervised learning and an attention mechanism, and the fine-grained image classification model obtained throughtraining can realize a good fine-grained image classification effect.

The invention discloses a method and a device for realizing the batch processing of images; the method comprises the following steps of: reading an image source folder path and a processed image storage path input by the user; reading processing parameters input by the user, wherein the processing parameters comprise the coordinates of a left upper top point, cutting width and height, and zooming proportion; traversing all images; reading an image file according to the image source folder path, and acquiring an image flow; capturing the read image file according to the coordinates of the left upper top point and the cutting width and height; generating a buffer image object after being cut; constructing a buffer image by using new width and height according to the zooming proportion, and constructing an Input / Output (IO) flow to output to an appointed file; and ending. In the invention, the batch processing is realized for single function point (cutting, zooming or copying) no longer, but the batch processing of multiple function points is realized in a compatible manner; therefore, the working amount of user operation can be greatly reduced, and the convenience brought by programs is realized.

The invention discloses a GPS-fused robot vision inertial navigation integrated positioning method. The method comprises the following steps: extracting and matching feature points of left and right images and front and back images of a binocular camera, and calculating three-dimensional coordinates of the feature points and relative poses of image frames; selecting a key frame in an image stream,creating a sliding window, and adding the key frame into the sliding window; calculating a visual reprojection error, an IMU pre-integration residual error and a zero offset residual error and combining the errors into a joint pose estimation residual error; carrying out nonlinear optimization on the joint pose estimation residual error by using an L-M method to obtain an optimized visual inertial navigation (VIO) robot pose; if the GPS data exist at the current moment, performing adaptive robust Kalman filtering on the GPS position data and the VIO pose estimation data to obtain a final robot pose; and if no GPS data exist, replacing the final pose data with the VIO pose data. According to the method, the positioning precision of the robot is improved, the calculation consumption is reduced, and the demands of large-range and long-time inspection are satisfied.

A method operable in a digital image acquisition system having no photographic film is provided. The method comprises receiving a relatively low resolution image of a scene from an image stream, wherein the scene potentially includes one or more faces. At least one high quality face classifier is applied to the image to identify relatively large and medium sized face regions and at least one relaxed face classifier is applied to the image to identify relatively small sized face regions. A relatively high resolution image of nominally the same scene is received and at least one high quality face classifier is applied to the identified small sized face regions in the higher resolution version of said image.

Embodiments for displaying first and second images to a pilot of an aircraft are presented. The embodiments include, but are not limited to, obtaining a first image signal and a second image signal, commanding a display unit to display a first image on a display screen corresponding to the first signal, and computing an image moving velocity of the first image. The method further comprises estimating an image flow velocity for the second image based on the second image signal and comparing the image moving velocity of the first image to the image flow velocity of the second image. After the comparison, the display unit is commanded to display the second image overlaid on the first image, and commanding the display unit to establish an intensity of the second image within a predefined range based upon the comparison.

Channel switching system and method of an IPTV service in a passive optical network (PON) are disclosed. To reduce a channel switching time of an IPTV system in the passive optical network, the system and the method use a channel switching control module and a channel list module in the passive optical network. In a case where a passive optical network system receives an IPTV channel switching request transmitted from a terminal user, the channel switching control module checks a recording of a channel list module and a recording of an authentication list module, and then updates a filter recording of an optical network unit to thereby directly transmit an image flow of a new channel in the passive optical network. When such system and method are applied to the passive optical network, high-speed switching of the IPTV service channel by the terminal user can be realized.

The invention provides a high content image flow biological microscopic analysis system. The system comprises a liquid flow system and an optical system, wherein the liquid flow system enables cells in sample cell suspension to be focused in the center of a liquid flow under the constraint of the system sheath liquid flow and to flow through a detection window of a flow chamber one by one; the optical system comprises optical sources, an optical path system and an optical filter stack; the optical sources include a halogen lamp and a laser; through the optical path system and the optical filter stack formed by a plurality of dichroscopes, the optical system generates a bright field cell image, a six-channel fluorescent cell image and six PMT (photomultiplier tube) optical intensity signals with different wave bands. The high content image flow biological microscopic analysis system integrates flow cytometry and fluorescence microscopic imaging, has a plurality of detection channels, can collect the cell images of the cells passing through the flow chamber one by one and can carry out quantitative analysis on each cell image by utilizing analysis software, thus providing the statistical data of a cell group and the information of the cell morphology, cell structures and subcellular signal distribution.

The invention discloses an interaction and instant feedback system and method in teaching. The system comprises: student ends which are used for converting current screenshots into flows when questions are raised, uploading the flows to a server end, receiving resource IDs returned by the server end, forming corresponding messages by combining instruction numbers with the resource IDs according to an appointed format and sending the messages to the server end; a teacher end which is used for receiving the messages forwarded by the server end, carrying out unpacking according to the an appointed format, obtaining the resource IDs after unpacking, requesting the corresponding image flows from the server end according to the resource IDs, converting the image flows into image files and displaying the image files on the teacher end; and the server end which is used for receiving the flows converted by the screenshots, generating the resources IDs, returning the resources IDs to the student end, writing questioning records of the student ends into a background database, receiving the image obtaining request of the teacher end, sending the corresponding image flows and forwarding the interaction messages between the student ends and the teacher end. By adopting the interaction and instant feedback system and method, instant interaction in class between the teacher end and the student ends is facilitated.

A system for processing a medical image for personalized brain disease diagnosis and status determination, includes: an image processing unit, which obtains a 3D T1 weighted image, a 2D T2 fluid attenuated inversion recovery (FLAIR) image, a magnetic resonance angiogram (MRA) image, which images only a vessel for checking abnormality of a brain vessel, and a 4D phase-contrast flow image for recognizing a state of a blood flow in a vessel; a complex image analyzing unit, which selects a disease-to-be-diagnosed, sets a brain area according to the selected disease, and analyzes brain tissue and a brain vessel; and a personalized diagnosis and result output unit, which outputs a brain state, a disease-specific risk degree, a risk of disease, and a disease prediction result through a machine learning algorithm by utilizing an age-specific data DB.

Systems and method are provided for a towing vehicle towing a trailer having at least one imaging device. A method includes: receiving, from a first imaging device coupled to the trailer, a first image stream having a plurality of first images; receiving, from a second imaging device coupled to the vehicle, a second image stream having a plurality of second images; determining, at least one common feature between a first image of the first images and a second image of the second images; determining a first distance from the first imaging device to the at least one common feature and a second distance from the second imaging device to the at least one common feature; and determining, a position of the first imaging device relative to the vehicle based on the first distance, the second distance and a known position and pose of the second imaging device.

An example of an electronic device with a first camera and a second camera is described. The first camera receives a first image stream, and the second camera receives a second image stream that includes a face of a user of the electronic device. The electronic device also includes a camera control module that identifies gesture based on a change in the second image stream, identifies a camera control feature of the first camera based on the gesture, and activates the camera control feature for the first camera.