Future Wei Technologies, Inc.

Matsushita Electric Industrial Co., Ltd.

Xerox Corporation

Panasonic Corporation

Huawei Technologies Co., Limited

Hong Heather Yu

Jun Tian

Hongbing Li

Yu Huang

Dong-Qing Zhang

Dapeng Oliver Wu

Mingquan Wu

Zhenyu Wu

Yue Chen

Han Zou

Miao Zhao

Ye-Kui Wang

Kui Lin

Dongqing Zhang

Steven Jay Harrington

Taoran Lu

Lei Yang

Zixiang Xiong

Gozde Bozdagi

John Wus

Robert Bryll

Bo Wang

Szeming Cheng

Peter Kiesel

Wei Jiang

Zheng Yuan

Zhenhua Liu

Ajay Raghavan

Nirwan Ansari

Michael Robert Campanelli

Zhu Li

Qiushu Chen

Alexander D Gelman

Kyle Arakaki

Min Wu

Peng Yin

Jin Yan

Yunchao Gao

Bing Han

Qian Chen

Jianbin Dai

Xin Li

Wei Liu

Yong Wang

Chao Zhang

Peng Zhang

Lei Zhang

Yang Xu

Nasir D Memon

Lina Dong

Tsuhan Chen

Wenjun Zeng

Jianyu Zhang

Tao Han

Sanqi Li

Robert Fish

Yan Zhang

Yifu Zhang

Prabir Bhattacharya

Jie Hu

Xiangyang Kong

Alex Gelman

Dongjing Shan

Kuan-chuan Peng

Colin Campbell

Qi Wang

Shu Wang

Bin Jia

Jizhou Gao

Jingteng Xue

Dong Cao

Zhifeng Chen

Yingnan Zhu

Gleb Naumovich

Ezgi Yalcin

Mikhail Sosonkin

Chang Wen Chen

Nirwan Ansari Ansari

A system includes a sensor network comprising at least two optical fibers coupled to a pavement. Each optical fiber includes one or more optical sensors installed a predetermined distance from one or more adjacent optical fibers. The one or more optical sensors are configured to produce a wavelength shift signal. A processor is configured to determine one or both of one or more attributes of one or more objects travelling on the pavement and a traffic condition of the pavement based on the wavelength shift signal. A transmitter is configured to transmit the one or more attributes to a predetermined location.

Traffic monitoring using optical sensors

One or more spacers for installing an optical cable are disposed in a trench that extends along an axis. The optical cable includes one or more optical sensors. Each spacer includes a base configured to rest in a bottom of the trench. A first arm extends from the base. The first arm is adjacent to a first wall of the trench. An opposing second arm extends from the base. The second arm is adjacent to an opposing second wall of the trench. The optical cable is configured to extend along the axis.

Installation of optical sensors for use in traffic monitoring

A method of stabilizing a video in real time using a single pass including receiving consecutive video frames, where the consecutive video frames include a current video frame and previous video frames, storing the consecutive video frames in a buffer, estimating a global motion for the current video frame by describing a camera's relative motion between the current video frame and one of the previous video frames adjacent to the current video frame, estimating a long-term camera motion for the current video frame by determining a geometric mean of an accumulation of the estimate of the global motion for the current video frame and an estimate of global motion for each of the previous video frames, and displaying the current video frame on a display of an electronic device, the current video frame stabilized based on the estimate of the long-term camera motion.

One-pass video stabilization

In one embodiment, a method including receiving, by a server, an input video and extracting features of the input video to produce extracted features. The method also includes comparing the extracted features of the input video with metadata stored in a metadata database storage and incorporating the input video into a matched video corresponding to metadata that matches the extracted features of the input video upon determining that the extracted features of the input video match metadata in the metadata database storage.

System and method for organizing multimedia content

In an image processing method, an object is located within an image. An area around the object is determined and divided into at least first and second portions based upon image information within the area. The object can then be classified based upon both image information in the first portion of the area and image information in the second portion of the area.

Method and system for image processing to classify an object in an image

A computer program product comprising computer executable instructions stored on a non-transitory computer readable medium such that when executed by a processor, causes the processor to identify an object of interest in a visual media element, analyze the object of interest according to a defined set of rules to form a recommendation for improvement of the visual media element, and recommend the improvement to the visual media element to a user. A method comprising receiving a visual media element as an input, determining a relevant object of interest within the visual media element, analyzing an aesthetic appearance of the relevant object of interest according to a guideline, and recommending a change to the visual media element for conforming to the guideline.

Photographic picture quality improvement recommendation system using objects

A device is disclosed comprising a memory configured for holding video and a processor coupled to the memory. The memory contains computer-executable instructions that, when executed by the processor, cause the device to perform operations to stabilize the video, the operations comprising buffering consecutive original video frames, determining transformation matrices from subsets of the original video frames, wherein the transformation matrices represent estimates of stable camera motion, using the transformation matrices to warp the original video frames and generate video that is stabilized relative to the original video frames, and adjusting a size of a subset of original video frames in response to detecting a condition.

A video server comprises memory to store video content obtained from multiple camera views; one or more streaming components configured to stream video content to a client application; and one or more frame feeder components. A frame feeder component is configured to access first video content corresponding to a first camera view and provide the first video content to a streaming component; access, in response to a request received at the video server to stream second video content corresponding to a second camera view, intermediate video content corresponding to one or more camera views intermediate to the first and second camera views; and access the second video content, and provide the intermediate video content and the second intermediate video to the streaming component.

Multi-view video streaming with fast and smooth view switch

A method and system is proposed to create a generative model to interpolate any view of a planar scene given a sequence of reference views and a synthesis view that is optimized by the marginalization of photometric regulation, and geometric registration parameters. According to one aspect of the claimed subject matter, a technique is proposed to combine information from varying input camera poses. Planar homography based image super resolution in free view interpolation for planar structure is applied to the combined information. Non-redundant information is combined in such a manner that the high resolution and free view problems in traditional 2D based image-based rendering techniques are overcome.

High resolution free-view interpolation of planar structure

In accordance with an embodiment of the present invention, a method for inserting secondary content into a media stream includes dividing the media stream having a plurality of frames into a plurality of shots at a processor. The method further includes grouping consecutive shots from the plurality of shots into a plurality of scenes. A first list of insertion points is generated for introducing the secondary content. The insertion points of the first list are boundaries between consecutive scenes in the plurality of scenes. An average insertion point saliency of the media stream is generated at the insertion points in the first list. A second list of insertion points is then generated. The insertion points in the second list are arranged to maximize a function of the average insertion point saliency and a distance between each insertion point in the second list with other insertion points in the second list.

Media processing devices for detecting and ranking insertion points in media, and methods thereof

In one embodiment, a method of organizing multimedia content includes obtaining, by a server, a first video program. Also, the method includes selecting a first video, where the first video is a first subset of the first video program, and where the first video forms a first branch of the first video program and selecting a second video, where the second video is a second subset of the first video program. Additionally, the method includes selecting a first partial video, where the first partial video is a first subset of the first video and selecting a second partial video, where the second partial video is a second subset of the first video. The method also includes establishing a multi-dimensional index tree including a first video program level, a first video level, a first partial video level.

Apparatus and method for modification of emotion conveyed by an image. In one aspect, a metric corresponding to the emotion conveyed by an image is generated, and a command for modifying the emotion of the image causes the emotion conveyed by the image to be changed according to the specified change to emotion. The command to modify the image emotion can be made via an emotion keyword, and can include an indicated magnitude of emotion change. Emotion conveyed by an image can be specified via an emotion vector, where elements of the vector correspond with emotions arranged along orthogonal dimensions in an emotion space. In one aspect, an emotion predictor is trained to predict the emotion conveyed by an image via determining characteristic values for a set of image feature categories, based on a set of images associated with emotion keywords of the emotion space.

Emotion modification for image and video content

Embodiments are provided herein to achieve video or image sequence encoding with an improved denoising algorithm that is both efficient computationally and has acceptable overhead cost in comparison to other denoising schemes for video encoding. The embodiments include using recursive bilateral filtering as part of the denoising algorithm, which is integrated into a video encoder to overcome limitations of other encoder-integrated denoising algorithms. An embodiment method includes receiving, at a filtering and residual computation function at the encoder, a macro block comprising a plurality of pixels. The filtering and residual computation function also receives, from a motion estimation function at the encoder, a reference block. The reference block comprises a plurality of reference pixels corresponding to the macro block. The filtering and residual computation function further applies a recursive bilateral filter function to each of the pixels of the macro block using the reference pixels of the reference block.

System and method for encoder-integrated media denoising

In accordance with an embodiment of the present invention, a method of streaming a media preview includes delivering a preview data having preview information from a media file to be streamed. The preview data has a multi-dimensional hierarchical data structure has a plurality of layers with increasing content of the preview information in each layer of the plurality of layers. The preview data is configured to provide an adaptive and scalable preview service.

Method and apparatus for scrub preview services

An apparatus comprising a plurality of ports, and a processor coupled to the ports and configured to receive a plurality of video frames from any of the ports, wherein the video frames comprise an object and a background, and wherein the video frames comprise a plurality of color pixels for the object and the background, receive a plurality of depth frames from any of the ports, wherein the depth frames comprise the object and the background, and wherein the depth frames comprise an indication of an object depth relative to a background depth, and encode the video frames using the indication of the object depth relative to the background depth.

Using depth information to assist motion compensation-based video coding

Growing community of inventors

West Windsor, NJ, United States of America

Hong Heather Yu