Ambarella International LP

International Business Machines Corporation

Intel Corporation

Siemens Aktiengesellschaft

Huiling Jinxin (shanghai) Pharmaceutical Technology Co., Ltd

Jian Tang

Tao Liu

Jingyang Qiu

Ruian Xu

Yufu Li

Rahul Khanna

Mengze Liao

Jiang Yu

Yufei Li

Teresa Chung Kan

Zhijun Liu

Luyi Sun

Qi Feng

Murugasamy K Nachimuthu

Brian Keith Martin

William Thomas Newport

Jingdong Sun

Ping Wu

Yan Yang

Qian Zhang

Pernell James Dykes

Xiaohua Cai

Xiaoming Yu

Jingli Zhang

Cheng-chieh Cheng

Ma Hao Chen

Qian Sun

An apparatus comprising an interface and a processor. The interface may be configured to receive pixel data. The processor may be configured to process the pixel data arranged as video frames, generate statistics and a timestamp for the video frames, perform computer vision operations on the video frames to determine one or more regions of interest within the video frames at the timestamp, track a movement of the regions of interest over a sequence of the video frames, evaluate a current luma value of the regions of interest, calculate auto-exposure parameters in response to the current luma value and a target luma value and generate an output signal comprising the auto-exposure parameters. The auto-exposure parameters may be calculated to prioritize an exposure of the regions of interest in the video frames and dynamically change the auto-exposure parameters based on the movement of the regions of interest.

Automatic exposure metering for regions of interest that tracks moving subjects using artificial intelligence

The present invention relates to the technical field of medicine, and to derivatives represented by formula 1 and formula 2 in which a carboxylic acid group is introduced into the structure of Ginkgolide B by means of a hydroxyl group at the 10-position and ester derivatives of carboxylic acid groups, and pharmaceutically acceptable organic or inorganic salts. Ginkgolide B is used as a parent body and is prepared by means of chemical structure modification so as to achieve the goals of improving solubility, increasing bioavailability and enhancing healing efficacy. The prepared compound and carboxylate salts thereof have significant platelet activating factor antagonism, an anticoagulant effect and an anti-acute cerebral ischemia effect, and can be used for preparing a drug for preventing and treating ischemic stroke, thrombosis, angina pectoris, cardiopulmonary infarction, as well as inflammation, asthma and other diseases related to a platelet activating factor.

Ginkgolide B derivative and salt thereof, preparation method therefor and use thereof

An apparatus comprising an interface, a light projector and a processor. The interface may be configured to receive pixel data. The light projector may be configured to generate a structured light pattern. The processor may be configured to process the pixel data arranged as video frames comprising the structured light pattern, perform computer vision operations to detect a size of a face area of the video frames, determine a scale ratio in response to the size of the face area, extract the structured light pattern from the video frames, generate a downscaled structured light image and generate a depth map in response to the downscaled structured light image and a downscaled reference image. A downscale operation may be performed in response to the scale ratio to generate the downscaled structured light image. The scale ratio may enable the generation of the downscaled structured light image with sufficient depth pixels.

Adaptive face depth image generation

A system comprising a plurality of capture devices and a calibration device. The capture devices may each comprise a warp table. The calibration device may be configured to store a plurality of configured warp tables in a warp table pool, perform a full calibration for one of the capture devices to generate the configured warp tables, initiate a quick calibration for the capture devices and apply one of the configured warp tables to the capture devices as the warp table. The calibration device may apply one of the configured warp tables to the capture devices by selecting one of the configured warp tables from the warp table pool in response to the quick calibration. If the quick calibration fails, the calibration device may generate a new configured warp table for the warp table pool in response to the full calibration and select the new configured warp table.

Quick RGB-IR calibration verification for a mass production process

An apparatus including an interface and a processor. The interface may be configured to receive pixel data generated by a capture device. The processor may be configured perform computer vision operations on the video frames to detect objects, perform a classification of the objects detected based on characteristics of the objects, determine whether the classification of the objects corresponds to an event, generate a full video stream in response to all of the video frames and generate encoded video frames. The full video stream may be recorded to a storage medium local to the apparatus. The encoded video frames may be communicated to a cloud service. The encoded video frames may comprise a first sample of the video frames selected at a first rate when the event is not detected and a second sample of the video frames selected at a second rate while the event is detected.

Smart timelapse video to conserve bandwidth by reducing bit rate of video on a camera device with the assistance of neural network input

An apparatus comprising a light projector, a sensor and a processor. The light projector may be configured to toggle a light pattern. The sensor may be configured to generate pixel data. The processor may be configured to process the pixel data arranged as video frames, extract IR images with the light pattern, IR images without the light pattern and RGB images from the video frames, generate a control signal in response to the IR images with the light pattern and the RGB images, calculate an IR interference measurement in response to the IR images without the light pattern and the RGB images and select a mode of operation for an IR channel control and an RGB channel control in response to the IR interference measurement. The control signal may be configured to adjust an exposure for the sensor.

Intelligent auto-exposure control for RGB-IR sensor

An apparatus including an interface and a processor. The interface may be configured to receive pixel data generated by a capture device. The processor may be configured to generate video frames in response to the pixel data, perform computer vision operations on the video frames to detect objects, perform a classification of the objects detected based on characteristics of the objects, determine whether the classification of the objects corresponds to a user-defined event and a user-defined identity and generate encoded video frames from the video frames. The encoded video frames may comprise a first sample of the video frames selected at a first rate when the user-defined event is not detected and a second sample of the video frames selected at a second rate while the user-defined event is detected. The video frames comprising the user-defined identity without a second person may be excluded from the encoded video frames.

Person-of-interest centric timelapse video with AI input on home security camera to protect privacy

The present disclosure is directed to efficient memory activation at runtime. A memory module (e.g., a memory riser) being added to a device would typically cause the device to enter system management mode (SMM) to activate the memory module. However, activation (e.g., memory module initialization, hardware training and system reconfiguration) in SMM may substantially delay the resumption of normal operations. Consistent with the present disclosure, at least the memory module initialization and hardware training portions of the activation may be performed by an operating system (OS) in the device, allowing normal device operation to continue during the activation. The OS portion of the activation may generate configuration data. In at least one embodiment, the configuration data may be applied for use in SMM. For example, a system management interrupt (SMI) handler may apply the configuration data during a quiescent period (e.g., a period of inactivity) that occurs during SMM.

Efficient memory activation at runtime

An apparatus including an interface and a processor. The interface may be configured to receive pixel data generated by a capture device. The processor may be configured to generate video frames in response to the pixel data, perform computer vision operations on the video frames to detect objects, perform a classification of the objects detected based on characteristics of the objects, determine whether the classification of the objects corresponds to a user-defined event and generate encoded video frames from the video frames. The encoded video frames may be communicated to a cloud storage service. The encoded video frames may comprise a first sample of the video frames selected at a first rate when the user-defined event is not detected and a second sample of the video frames selected at a second rate while the user-defined event is detected. The second rate may be greater than the first rate.

Event/object-of-interest centric timelapse video generation on camera device with the assistance of neural network input

An apparatus includes an interface and a processor. The interface may be configured to receive pixel data representing respective fields of view of two or more cameras arranged to obtain a predetermined field of view, where the respective fields of view of each adjacent pair of the two or more cameras overlap. The processor may be configured to process the pixel data arranged as video frames and perform a fixed pattern calibration for facilitating multi-view stitching. The fixed pattern calibration may comprise applying a pose calibration process to the video frames. The pose calibration process generally uses (i) intrinsic parameters, a respective translate vector, a respective rotation matrix, and distortion parameters for each lens of the two or more cameras and (ii) a calibration board to obtain configuration parameters for the respective fields of view of the two or more cameras. The pose calibration process may comprise changing a z value of the respective translate vector for each lens of the two or more cameras to at least one of a middle distance value and a long distance value while maintaining the respective rotation matrix for each lens of the two or more cameras unchanged.

Fixed pattern calibration for multi-view stitching

An apparatus includes an interface and a processor. The interface may be configured to receive video signals from two or more cameras arranged to obtain a predetermined field of view, wherein respective fields of view of each pair of said two or more cameras overlap. The processor may be configured to perform a fixed pattern calibration for facilitating multi-view stitching. The fixed pattern calibration may comprise (a) performing a geometry calibration process to obtain intrinsic parameters and distortion parameters for each lens of the two or more cameras, and (b) applying a pose calibration process to the video signals using (i) the intrinsic parameters and the distortion parameters for each lens of the two or more cameras, and (ii) a calibration board to obtain configuration parameters for the respective fields of view of the two or more cameras.

Growing community of inventors

Shanghai, China

Jian Tang