Abstract: An image processing method and a device configured to implement the same are disclosed. The method comprises: from an imaging device, obtaining image data that comprises temporally consecutive image frames; performing feature extraction on each of the obtained image frames; dynamically retaining extracted feature data of the obtained image frames in a feature accumulation database by regulating data retention in the feature accumulation database to a selective subset of the extracted feature data from the obtained image frames; performing Random Sample Consensus (RANSAC) operation on the selective subset of the extracted feature data from the feature accumulation database; and generating an estimation model from output of the RANSAC operation based on at least one of an extracted feature data of a current image frame or extracted feature data of one or more temporally preceding image frames of the obtained image frames.

Abstract: The present application discloses an imaging system for detecting human-object interaction and a method for detecting human-object interaction thereof. The imaging system includes an event sensor, an image sensor, and a controller. The event sensor is configured obtain an event data set of the targeted scene according to variations of light intensity sensed by pixels of the event sensor when an event occurs in the targeted scene. The image sensor is configured capture a visual image of the targeted scene. The controller is configured to detect human according to the event data set, trigger the image sensor to capture the visual image when the human is detected, and detect the human-object interaction in the targeted scene according to the visual image and a series of event data sets obtained by the event sensor during the event.

Abstract: An image processing method and a device configured to implement the same are disclosed. The device comprises: a hybrid imaging device configured to obtain optical input; and a processing device in signal communication with the hybrid imaging device. The processing device comprises: a motion detection circuit that performs feature tracking based on a first component of an obtained optical input; a motion estimation circuit that performs motion compensation based on output of the motion detection unit; a frame reconstruction circuit that reconstructs image frame based on both the output of the motion estimation unit and a second component of the optical input; and an output unit that outputs image frame at a predetermined global frame rate.

Abstract: The present application discloses an imaging system for detecting human-object interaction and a method for detecting human-object interaction thereof. The imaging system includes an event sensor, an image sensor, and a controller. The event sensor is configured obtain an event data set of the targeted scene according to variations of light intensity sensed by pixels of the event sensor when an event occurs in the targeted scene. The image sensor is configured capture a visual image of the targeted scene. The controller is configured to detect human according to the event data set, trigger the image sensor to capture the visual image when the human is detected, and detect the human-object interaction in the targeted scene according to the visual image and a series of event data sets obtained by the event sensor during the event.

Abstract: An image processing device combines a plurality of contents (e.g. videos) with a story line retained as much as possible, while reducing view's discomfort. The image processing device compares one of the contents, which contains a first partial content and a second partial content subsequent to the first partial content, with another one of the contents, which contains a plurality of consecutive partial contents; detects, as a third partial content, a partial content with the highest similarity value from among the plurality of partial contents; and generates relational information by using the highest similarity value obtained by the first processing unit. The relational information is then used for merging the first partial content, the second partial content and the third partial content.

Abstract: An image recognition device that improves the accuracy of generic object recognition compared with conventional technologies by reducing the influence of the position, size, background clutter and the like of an object that is targeted to be recognized in the input image by the generic object recognition. The image recognition device performs a generic object recognition and includes: a segmenting unit configured to segment an input image into a plurality of regions in accordance with meanings extracted from content of the input image; a generating unit configured to compute feature data for each of the plurality of regions and generate feature data of the input image reflecting the computed feature data; and a checking unit configured to check whether or not a recognition-target object is present in the input image in accordance with the feature data of the input image.

Abstract: An image recognition device that improves the accuracy of generic object recognition compared with conventional technologies by reducing the influence of the position, size, background clutter and the like of an object that is targeted to be recognized in the input image by the generic object recognition. The image recognition device performs a generic object recognition and includes: a segmenting unit configured to segment an input image into a plurality of regions in accordance with meanings extracted from content of the input image; a generating unit configured to compute feature data for each of the plurality of regions and generate feature data of the input image reflecting the computed feature data; and a checking unit configured to check whether or not a recognition-target object is present in the input image in accordance with the feature data of the input image.

Abstract: The present invention provides an image recognition apparatus with enhanced performance and robustness. In an image recognition apparatus 1, an image classification information accumulating unit 20 stores therein feature information defining visual features of various objects obtained through a learning process. For classification of input images, an image feature obtaining unit 18 extracts descriptors indicating features from each input image, image vocabularies corresponding to the descriptors are voted, and a classifying unit 19 calculates existence probabilities of one or more candidate objects, based on the result of the voting. According to the existence probabilities, objects contained in the image is identified. Through the calculation, the existence probabilities are adjusted by an exclusive classifier, based on exclusive relationship information defining exclusive object sets each containing different objects (object labels) predicted not to coexist in a same image.

Abstract: The present invention provides an image processing device capable of combining a plurality of contents (e.g. videos) with a story line retained as much as possible, while reducing view's discomfort. The image processing device compares one of the contents, which contains a first partial content and a second partial content subsequent to the first partial content, with another one of the contents, which contains a plurality of consecutive partial contents, so as to detect, as a third partial content, a partial content with the highest similarity value from among the plurality of partial contents, and generates relational information by using the highest similarity value obtained by the first processing unit, the relational information being used for merging the first partial content, the second partial content and the third partial content.

Abstract: The present invention provides an image recognition apparatus with enhanced performance and robustness. In an image recognition apparatus 1, an image classification information accumulating unit 20 stores therein feature information defining visual features of various objects obtained through a learning process. For classification of input images, an image feature obtaining unit 18 extracts descriptors indicating features from each input image, image vocabularies corresponding to the descriptors are voted, and a classifying unit 19 calculates existence probabilities of one or more candidate objects, based on the result of the voting. According to the existence probabilities, objects contained in the image is identified. Through the calculation, the existence probabilities are adjusted by an exclusive classifier, based on exclusive relationship information defining exclusive object sets each containing different objects (object labels) predicted not to coexist in a same image.

Abstract: A transmitting apparatus includes a generation unit configured to generate a notification message and a transmission unit configured to transmit the notification message. The notification message includes a broadcast identifier identifying a broadcast and timing control information indicating when media information related to and distinct from the broadcast is to be displayed. A receiving apparatus includes a broadcast reception unit configured to receive broadcast and a notification message reception unit configured to extract broadcast identifiers and timing control information from the notification messages.

Abstract: Provided is a probe capable of effectively performing NIR imaging by optimally arranging input channels and detection channels, and an image reconstruction method using the probe. The probe (10) according to the present invention performs NIR imaging on a region of interest (16) that is an imaging target, and includes a probe body (11) in which the input channels and the detection channels are arranged, and the probe body includes: first input channels (131) arranged in the upper area (19); first detection channels (141) arranged in the lower area (20); second input channels (132) arranged in the left area (17); and second detection channels (141) arranged in the right area (18).

Abstract: An optical-combined imaging method which improves image quality and shortens the time for imaging includes: a structure identification step (S21) of identifying the position and size of an observation target object which is located within body tissue; a region determining step (S22) of determining an imaging subject region which includes the observation target object, based on the location and size identified in the structure identification step (S21); a measurement step (S23) of measuring diffused light propagated through the imaging subject region determined in the region determining step (S22); an imaging step (S24) of estimating an optical characteristic within the imaging subject region based on the measuring result in the measurement step (S23) and imaging the optical characteristic; and a displaying step (S25) of displaying the optical characteristic imaged in the imaging step (S24).

Abstract: The present invention is a system and method for broadcast content related notification. In embodiments, a Notification Generation unit (NTG) generates a notification message, the notification message including notification event description and related broadcast content identifiers. A broadcast content identifier references to a broadcast service, content or program which the notification event is related with. A Notification Channel Selection unit (NTCS) selects a notification channel to be used for delivery of the notification message. A Notification Distribution unit (NTD) uses the selected notification channel for the delivery of notification messages to one or multiple terminals. A Notification Reception unit (NTR) in a terminal receives the notification message from the notification channel.

Abstract: A method of embedding copyright management information in AV (audio visual) content that is distributed in a downloadable file format. In a MP4 file format, which is a format for distributing downloadable files, content data is separated by code into a general stream and an IPMP (intellectual property management and protection) controlled media stream. A box for embedding data required for IPMP initialization and a box for embedding data required to interpret IPMP and related parameters are rendered in a first box that is rendered in a control data box.

Abstract: A method of transferring information specifying an IPMP tool utilized for processing a content protected by IPMP to an IPMP terminal specifies and uses XML schema for terminal platform specification, parametric description, and parametric aggregation which is to be used in MPEG-n IPMP system. For example, according to the method, based on a predetermined terminal platform XML schema and language to describe a terminal platform, terminal platform specification is created based on the terminal platform schema and language to specify on what platform or terminal the IPMP tool can run. The terminal platform specification is attached to metadata associated with the tool. The terminal platform specification and the IPMP tool are transferred to an IPMP terminal which is implemented with a terminal platform parser based on the terminal platform schema and language.

Abstract: An apparatus of a flexible and common MPEG-2 IPMP system (Intellectual Property Management and Protection) is invented to provide flexibility and interoperability by introducing a IPMP Control Information which includes IPMP Tool List and an optional Tool Container. The IPMP Control Information is put in PSI in MPEG-2 transport stream, and a special PES packet in MPEG-2 program stream. IPMP Stream is defined to carry IPMP information that is to be sent to each individual IPMP tool instance. The concept of Tool Manager, Message Router from MPEG-4 IPMP extension is mapped into MPEG-2 terminal to form MPEG-2 IPMP framework together with introduced IPMP Control Information and IPMP Stream. As a result of this invention, the same protected MPEG-2 content is able to play back by different types of MPEG-2 IPMP terminals, and the same MPEG-2 content can be protected by using different vendors' IPMP system.

Abstract: The present invention relates to content and IPMP tool transfer among distributed IPMP devices. A set of messages is defined for distributed IPMP devices. These messages include content transfer message, IPMP tool transfer messages, as well device ID broadcasting messages. Using these messages, distributed devices can use a standard set of messages to establish a network, and exchange content protected by IPMP in an inter-operable way. It is also related to carriage of rights in MPEG system, especially in MPEG-4 system. Rights ES (Elementary Stream) is defined in MPEG-4 system, to carry rights information. The Rights ES is also attached with information including whether the rights carried in the ES is proprietary or not, and/or what should be the rights management tool to handle this Rights ES. With that, terminal can be built in an inter-operable way, and retrieve rights from a standardized position.

Abstract: Digital Rights Management (DRM) or Intellectual Property Management and Protection (IPMP) for generic digital content wherein a IPMP Control Graph and a REL-IPMP Control Graph carries protection signalling and rights expression data. Both content packaging and terminal processing relating to the above control graph are clearly defined and elaborated.

Abstract: A Baseline DVB-CPCM is presented in this proposal to provide a secure and interoperable content delivery and transferring apparatus. The proposed Baseline DVB-CPCM is a unit to be implemented in a compliant CPCM device, and it consists of five major modules to be used for end-to end solution and content transferring between devices. These modules are CPCM Manager, Tools Box, Rights Management Module, Message Router, and CAS-CPCM Converter.