Lifesize Communications, Inc.

Logitech Europe S.a.

Ge Precision Healthcare LLC

Lifesize, Inc.

Sandeep Lakshmipathy

Raghuram Belur

Hrishikesh G Kulkarni

Prithvi Ranganath

Binu Kaiparambil Shanmukhadas

Gautam Khot

Hitesh Chouhan

Vikas

Sudeep U Nayak

Raghu Prasad

Govindappa Simhadri

Jayanth Ganapathiraju

Ashish Goyal

Jignesh Dholakia

Kavitha Manickam

Vignesh Singh

Kalluru Vijayananda Reddy

Hrishikesh G Kulkami

Systems and techniques that facilitate real-time and/or offline de-identification of facial regions from regular and/or occluded color video streams obtained during diagnostic medical procedures are provided. A detection component can generate a bounding box substantially around a person in a frame of a video stream, can generate a heatmap showing key points or anatomical masks of the person based on the bounding box, and can localize a face or facial region of the person based on the key points or anatomical masks. An anonymization component can anonymize pixels in the frame that correspond to the face or facial region. A tracking component can track the face or facial region in a subsequent frame based on a structural similarity index between the frame and the subsequent frame being above a threshold. If the structural similarity index between the frame and the subsequent frame is above the threshold, the tracking component can track the face or facial region in the subsequent frame without having the detection component generate a bounding box or a heatmap in the subsequent frame, and the anonymization component can anonymize pixels in the subsequent frame corresponding to the tracked face or facial region.

Method and system for real-time and offline de-identification of facial regions from regular and occluded color video streams obtained during diagnostic medical procedures

A method and system for automatically labeling a spine image is disclosed. The method includes receiving an input spine image and analyzing image features of the input spine image by a deep neural network. The method further includes generating a mask image corresponding to the input spine image by the deep neural network based on image characteristics of a training image dataset. A region of interest in the mask image comprises vertebral candidates of the spine. The training image dataset comprises a plurality of spine images and a plurality of corresponding mask images. The method further includes associating labels with a plurality of image components of the mask image and labeling the input spine image based on labels associated with the mask image.

Methods and systems for labeling whole spine image using deep neural network

A videoconference may be initiated between a plurality of endpoints. At least one of the endpoints may be coupled to a recording server, which may be configured to record the videoconference. A configuration may be selected (e.g., automatically or manually) for performing the recording. The endpoint (e.g., acting as an MCU) may transmit information to endpoints and may transmit recording information to the recording server. The recording information may be different from the videoconference information. For example, it may be in a 'streaming friendly' format, at a different bit rate, encoded differently, have different inputs, etc. The manner in which the videoconference is stored and/or recorded may be based on the selected configuration. Clients may be configured to receive and display the videoconference from the recording server and may be configured to change the provided layout to different layouts, e.g., based on user input.

Distributed recording or streaming of a videoconference in multiple formats

A federated media server system. The federated media server system may include a plurality of media servers. A first media server may be coupled to a second media server over a network. The first media server may also be coupled to a third media server over the network. Additionally, the second and third media servers may be coupled to a plurality of respective clients. The first media server may be configured to record video, e.g., videoconferences, and stream recordings to clients and/or the second and third media servers. The second and third media servers may assist in performing video recording, transcoding, storage of recordings, multicasting, etc.

Distributed transcoding of a video based on insufficient computing resources

Multicasting a videoconference recording to a plurality of clients

Distributed recording of a video based on available disk space

Multicasting a video to a plurality of clients based on a single stream

Streaming a videoconference using distributed transcoding

Customizing a conferencing system based on proximity of a participant. A first participant may be detected as being proximate to a first conferencing system. For example, the first participant may provide user input to check in to the first conferencing system. Alternatively, the conferencing system may automatically detect the first participant (e.g., by automatically detecting a personal device of the first participant). In response to detecting the proximate participant, the first conferencing system may be automatically customized for the participant.

Automatically customizing a conferencing system based on proximity of a participant

Distributed recording of a videoconference in multiple formats

Collaborative recording of a videoconference using a recording server

Automatically moving a conferencing based on proximity of a participant

Conducting a private videoconference within a videoconference. A videoconference may be established between a plurality of endpoints. Input may be received requesting the private videoconference for a plural subset of the plurality of endpoints. The private videoconference may be established between the plural subset of the plurality of endpoints. The initial videoconference may continue during the private videoconference. Private videoconference data may be transmitted only to the plural subset of endpoints of the private videoconference. The private videoconference may be sent directly between the plural subset of endpoints or may be sent via a multipoint control unit, e.g., of the initial videoconference. The private videoconference data may not be sent to the remaining endpoints of the initial videoconference.

Conducting a direct private videoconference within a videoconference

Growing community of inventors

Bengaluru, India

Sandeep Lakshmipathy