Intel Corporation

Yimin Zhang

Wenlong Li

Yangzhou Du

Tao Wang

Wei Hu

Xiaofeng Tong

Jianguo Li

Haibing Ren

Qiang Li

Ping Guo

Yurong Chen

Fei Duan

Joe F Zhou

Anbang Yao

Aamer Jaleel

Dayong Ding

Lidan Zhang

Ang Liu

Xiaobo Hu

Sirui Yang

Lin Xu

Hu Tiger Chen

Ya-Ti Peng

Qiang Eric Li

Eric Li

Jiankun Hu

Thomas Sachson

Changcheng Li

Zhongxuan Liu

Jianbo Ye

Du Yangzhou

Patricia P Wang

Jiulong Shan

Zengjian Hu

Renjing Pei

Lianrui Fu

Xioafeng Tong

John G Tennant

Hui A Li

A long-term object tracker employs a continuous learning framework to overcome drift in the tracking position of a tracked object. The continuous learning framework consists of a continuous learning module that accumulates samples of the tracked object to improve the accuracy of object tracking over extended periods of time. The continuous learning module can include a sample pre-processor to refine a location of a candidate object found during object tracking, and a cropper to crop a portion of a frame containing a tracked object as a sample and to insert the sample into a continuous learning database to support future tracking.

Continuous learning for object tracking

An example apparatus for generating synthesized images includes a receiver to receive a frame, a mask and external images. The apparatus also includes a foreground augmenter to generate augmented foregrounds in the frame based on the mask. The apparatus includes a background augmenter to generate augmented backgrounds based on the frame, the mask, and the external images. The apparatus also further includes an image synthesizer to generate a synthesized image based on the generated augmented foregrounds and the augmented backgrounds.

Training one-shot instance segmenters using synthesized images

Generally this disclosure describes a video communication system that replaces actual live images of the participating users with animated avatars. A method may include selecting an avatar; initiating communication; detecting a user input; identifying the user input; identifying an animation command based on the user input; generating avatar parameters; and transmitting at least one of the animation command and the avatar parameters.

Communication using interactive avatars

A system, article, and method of neural network object recognition for image processing includes customizing a training database and adapting an instance segmentation neural network used to perform the customization.

Method and system of neural network object recognition for image processing

A system and method of teaching a neural network through reinforcement learning methodology. The system includes a machine-readable medium having one or more processors that perform a motion task to produce a first result corresponding to navigating a device during a first episode and performing an interaction task during that same episode. After completion of the first episode a processor calculates a Q value change based on the first task result and the second task result. The processor then modifies parameters based on the Q value change such that during subsequent episode iterations the motion task and interactive task are improved and a smooth and continuous transition occurs between these two tasks.

Reinforcement learning for human robot interaction

A system, article, and method of point cloud registration using overlap regions for image processing.

Method and system of point cloud registration for image processing

Methods and apparatus to match images using semantic features are disclosed. An example apparatus includes a semantic labeler to determine a semantic label for each of a first set of points of a first image and each of a second set of points of a second image; a binary robust independent element features (BRIEF) determiner to determine semantic BRIEF descriptors for a first subset of the first set of points and a second subset of the second set of points based on the semantic labels; and a point matcher to match first points of the first subset of points to second points of the second subset of points based on the semantic BRIEF descriptors.

Methods and apparatus to match images using semantic features

Techniques are provided for estimation of human orientation and facial pose, in images that include depth information. A methodology embodying the techniques includes detecting a human in an image generated by a depth camera and estimating an orientation category associated with the detected human. The estimation is based on application of a random forest classifier, with leaf node template matching, to the image. The orientation category defines a range of angular offsets relative to an angle corresponding to the human facing the depth camera. The method also includes performing a three dimensional (3D) facial pose estimation of the detected human, based on detected facial landmarks, in response to a determination that the estimated orientation category includes the angle corresponding to the human facing the depth camera.

Estimation of human orientation in images using depth information from a depth camera

A device, method and system of video and audio sharing among communication devices, may comprise a communication device for generating and sending a packet containing information related to the video and audio, and another communication device for receiving the packet and rendering the information related to the audio and video. In some embodiments, the communication device may comprise: an audio encoding module to encode a piece of audio into an audio bit stream; an avatar data extraction module to extract avatar data from a piece of video and generate an avatar data bit stream; and a synchronization module to generate synchronization information for synchronizing the audio bit stream with the avatar parameter stream.

Method, apparatus and system of video and audio sharing among communication devices

Techniques are provided for detection of humans in images that include depth information. A methodology embodying the techniques includes segmenting an image into multiple windows and estimating the distance to a subject in each window based on depth pixel values in that window, and filtering to reject windows with sizes that are outside of a desired window size range. The desired window size range is based on the estimated subject distance and the focal length of the depth camera that produced the image. The method further includes generating classifier features for each remaining windows (post-filtering) for use by a cascade classifier. The cascade classifier creates candidate windows for further consideration based on a preliminary detection of a human in any of the remaining windows. The method further includes merging neighboring candidate windows and executing a linear classifier on the merged candidate windows to verify the detection of a human.

Detection of humans in images using depth information

The present disclosure is directed to face detection window refinement using depth. Existing face detection systems may perform face detection by analyzing portions of visual data such as an image, video, etc. identified by sub-windows. These sub-windows are now determined only based on pixels, and thus may number in the millions. Consistent with the present disclosure, at least depth data may be utilized to refine the size and appropriateness of sub-windows that identify portions of the visual data to analyze during face detection, which may substantially reduce the number of sub-windows to be analyzed, the total data processing burden, etc. For example, at least one device may comprise user interface circuitry including capture circuitry to capture both visual data and depth data. Face detection circuitry in the at least one device may refine face detection by determining criteria for configuring the sub-windows that will be used in face detection.

Face detection window refinement using depth

Systems, apparatuses and methods may generate a map of a search environment based on a probability of a target human being present within the search environment, capture a red, green, blue, depth (RGBD) image of one or more potential target humans in the search environment based on the map, and cause a robot apparatus to obtain a frontal view position with respect to at least one of the one or more potential target humans based on the RGBD images.

Human search and identification in complex scenarios

Movement of a user in a user space is mapped to a first portion of a command action stream sent to a telerobot in a telerobot space. An immersive feedback stream is provided by the telerobot to the user. Upon movement of user into or proximate to a margin of user space, the first portion of the command action stream may be suspended. The user may re-orient in the user space, and may then continue to move, with movement mapping re-engaged and resumption of transmission of a second portion of command action stream. In this way, user may control a telerobot via movement mapping, even though user space and telerobot space may not be the same size.

Movement mapping based control of telerobot

Apparatuses, methods and storage medium associated with processing an image are disclosed herein. In embodiments, a method for processing one or more images may include generating a plurality of pairs of keypoint features for a pair of images. Each pair of keypoint features may include a keypoint feature from each image. Further, for each pair of keypoint features, corresponding adjoin features may be generated. Additionally, for each pair of keypoint features, whether the adjoin features are similar may be determined. Whether the pair of images have at least one similar object may also be determined, based at least in part on a result of the determination of similarity between the corresponding adjoin features. Other embodiments may be described and claimed.

Growing community of inventors

Beijing, China

Yimin Zhang