Abstract: An event camera system for pupil detection may include a camera assembly and a controller, and may also include one or more off-axis light sources. The camera assembly may include one or more infrared (IR) light sources and an event camera. The one or more IR light sources are configured to emit pulses of IR light along an optical path toward an eyebox. The IR light is reflected from an eye in the eyebox, and the reflected light propagates back along the optical path toward the event camera for detection. The controller is configured to determine an orientation of the eye using data output from the event camera.

Abstract: An example fused convolutional layer, comprising, a comparator capable of reception of a first zero point and a multiply-accumulation result, a first multiplexer coupled to the comparator, wherein the first multiplexer receives a plurality of power-of-two exponent values, a shift normalizer, coupled to the first multiplexer, wherein the shift normalizer is capable of receiving the multiply-accumulation result and the plurality of power-of-two exponent values, wherein the shift normalizer limits a quantization of the multiply-accumulation result to a power-of-two scale and a second multiplexer coupled to an output of the shift normalizer, the first multiplexer and receives a second zero point and outputs an activation.

Abstract: A hot standby fault processing system is provided. The system includes a first detection layer configured to detect and record faults of vehicle configurations with low safety levels, a second detection layer configured to detect a fault of a vehicle configuration with critical safety level and send fault information, a fault collection layer configured to classify and record the received fault information, freeze the vehicle configuration corresponding to the fault information, and send the fault information to a higher processing layer, a first processing layer configured to receive fault information sent by the fault collection layer, process faults corresponding to the fault information according to a preset policy, and send fault information of faults that cannot be processed to system safety components, a redundancy part configured as a backup with the first processing layer and take over the operation of the first processing layer when the first processing layer fails.

Abstract: This application includes a power supply circuit, a PCB circuit board, a power supply device. The power supply circuit includes a processing circuit, a load circuit and a feedback circuit which are sequentially connected. The feedback circuit is connected to an output terminal of the load circuit and an input terminal of the processing circuit, and is configured to obtain a voltage of the output terminal of the load circuit and generate a sampling value. The processing circuit is configured to control a voltage of the output terminal of the load circuit according to the sampling value. The power supply circuit includes a differential circuit which connects the load circuit and the feedback circuit by using a differential trace manner. By means of differential trace manner, accuracy of an obtained sampling value is improved and a stability of a voltage of the output terminal of the load circuit is ensured.

Abstract: The present invention discloses a multi-frame image super resolution system that utilizes both deep learning models and traditional models of enhancing the resolution of an image so that minimal computational resources are used. A frame alignment module of the invention aligns the frames of the image after which a processing module configured within the system process the Y and the UV channels of the image by using multiple deep and traditional resolution enhancement models. A merging unit merges the output of the processors to produce a super resolution image incorporating the advantages of both of the image enhancement methods.

Abstract: The present invention provides an intelligent and a flexible video enhancement system with improved visual quality of the video for better user experience. The video enhancement system enhances various types of videos and provides a user with better visual experience based on video corresponding features and personal preferences. The video enhancement system includes a dynamic analysis and adaptive processing techniques for enhancing video quality for seamless user experience.

Abstract: A method, an apparatus, an electronic apparatus, and a storage medium for image distortion calibration are provided. In the method, an original image is obtained. The original image includes a background region and a foreground object region. A background distortion calibration is performed on the original image for obtaining a first calibrated image. The foreground object distortion calibration is performed to the original image for obtaining the second calibrated image. The background region in the first calibrated image and the foreground object region in the second calibrated image are fused for obtaining a calibrated image. The method can not only calibrate the distortion of the background of the original image but also preserve the shape of the foreground object, thus improving the presenting effect of the calibrated image.

Abstract: The present invention discloses a system and a method for providing multi-channel high-quality depth estimation from a monocular camera for providing augmented reality (AR) and virtual reality (VR) features to an image. The invention further includes the method to enhance generalization on deployment-friendly monocular depth inference pipeline with semantic information. Furthermore, a vivid and intact reconstruction is guaranteed by inpainting the missing depth and context within the single image input.

Abstract: An apparatus has an audio receiver to receive audio input from client devices. An audio transmitter transmits audio output to the client devices. A synchronicity service evaluates the audio input with respect to a set of network metrics and dynamically adjusts audio communication parameters to insure that the audio output to the client devices has a latency at or below 66 ms.

Abstract: Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for generating a prediction of at least a text and a particular type associated with an object are described in this specification. A first model output is generated by using a first machine learning model to process input data including one or more objects. The first model output identifies an existence of a particular object in the input data and specifies characteristics of the particular object. A type of the particular object is determined based on the specified characteristics. The type comprises a single-row type and a multi-row type. A single-row representation of the particular object is generated. A second model output is generated by processing the single-row representation. The second model output comprises a prediction of characters corresponding to the particular vehicle license plate.

Abstract: The disclosure provides a method for improving brightness of mosaiced images, which comprises the following steps: determining a first common area shared by a first image to be mosaiced and a second image to be mosaiced, calculating color average values of the first image to be mosaiced and the second image to be mosaiced in the first common area respectively, determining a target average value of the first common area based on the two color average values, and determining an adjustment parameter of the first common area according to the target average value and the color average values; determining a second common area shared by the second image to be mosaiced and a third image to be mosaiced, calculating color average values of the second image to be mosaiced and the third image to be mosaiced in the second common area, determining a target average value of the second common area based on the two color average values, and determining an adjustment parameter of the second common area according to the target

Abstract: An external parameter calibration method for an image acquisition apparatus is disclosed. The method includes acquiring images from images acquired by the image acquisition apparatus. The images contain reference objects acquired by the image acquisition apparatus during the driving of the vehicle. The reference objects in the images are divided into a number of sections along a road direction in which the vehicle is located, and reference objects in each of the sections are fitted into straight lines. Pitch angles and yaw angles of the image acquisition apparatus are determined based on vanishing points of a straight line in each of the sections. The sequences of the determined pitch and yaw angles are filtered. Straight portions in the road from the filtered sequences of pitch and yaw angles are obtained. Data of the pitch angles and yaw angles corresponding to the straight portions are stored to a data stack.

Abstract: In one aspect, a system that can minimize quantization accuracy losses when implementing a neural network node on an edge device is disclosed. During operation, the system identifies a set of adjustable parameters in the edge device. The set of adjustable parameters include a set of registers of the edge device. The system then models the quantization of parameters and output of the neural network node on the edge device as an optimization problem by formulating at least an objective function, wherein the objective function is a function of the set of adjustable parameters. Next, the system solves the optimization problem by identifying a set of values for the set of adjustable parameters that satisfies the objective function. The system subsequently programs the edge device by configuring the set of adjustable parameters with the set of identified values. The programmed edge device implements the neural network node with improved precision.

Abstract: A method of face anti-spoofing, comprising, receiving a near infra-red facial image, having a near infrared channel, receiving a red-green-blue facial image, having a red channel, a green channel and a blue channel, generating a synthetic three channel image based on the near infrared channel, the red channel, the green channel and the blue channel and training a deep neural network based on the synthetic three channel image.

Abstract: Using various embodiments, methods and systems for implementing secure transaction transfers are described. In one embodiment, a system performing the techniques described herein maintains a multi key index associated with a plurality of financial transactions using a self-balanced sorted tree data structure. Thereafter, the system reads/stores the self-balanced sorted tree data structure into memory and applies a filtering algorithm on the self-balanced sorted tree data structure to determine at least one qualifying financial transaction out of the plurality of financial transactions. The system selects the at least one qualifying financial transaction if it does not exceed a predetermined value. In one embodiment, the predetermined value is determined based on an available maximum utilization amount available to a user. Thereafter, the system transfers the selected at least one qualifying financial transaction to a secured credit card.

Abstract: A method of age and gender estimation, comprising receiving an input image, detecting a facial image within the input image, estimating a head pose based on a set of facial image intensities of the facial image, wherein the head pose is expressed as a yaw, a pitch and a roll, determining whether the yaw, the pitch and the roll of the head pose is less than a predetermined threshold, aligning the facial image if the yaw, the pitch and the roll of the head pose are less than the predetermined threshold and predicting an age and a gender of the aligned facial image.

Abstract: A joint training network including a multi-heard module comprising a network input, a feature network coupled to the network input and including a feature detector decoder outputting interest points and a descriptor generator decoder outputting descriptors, the feature detector decoder and the descriptor generator decoder coupled in parallel, a depth network including a monocular depth prediction decoder and outputting a depth map, a flow network including an image segmentation decoder and outputting a segmented image, a segmentation network including a warping module outputting a rotation and translation and an input warp signal to a segmentation decoder outputting a residual flow and a pose network including a fully connected pose estimator coupled to an adder that receives input from the pose estimator and the residual flow from the segmentation decoder, the adder outputting an optical flow.

Abstract: A method of determining a vehicle position and a vehicle velocity, including receiving a camera image sequence based on a camera borne by a vehicle and determining a camera pose based on the camera image sequence. The method includes determining a global position system location based on a global position system receiver borne by the vehicle, determining an inertial movement signal based on an inertial movement unit borne by the vehicle and receiving a wheel encoder signal from a wheel of the vehicle. The method additionally includes determining at least one of the vehicle positions and the vehicle velocity based on at least two of the camera pose, the global position system location, the inertial movement signal and the wheel encoder signal in temporal synchronization.

Abstract: A method of hybrid lane modeling, including, receiving a roadway image, extracting a set of lane points from the roadway image, fitting a polynomial line to the set of lane points, determining a fitted error of the fitted polynomial line, outputting the polynomial line if the fitted error is less than a predetermined threshold, selecting a set of clean lane points from the set of lane points if the fitted error is greater than the predetermined threshold and interpolating a cubic spline line to the set of clean lane points.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a depth image, comprising obtaining data representing a first image generated by a first sensor and a second image generated by a second sensor, wherein each of the first and second images includes a plurality of pixels; determining, for each pixel of the plurality of pixels included in the first image, whether the pixel is a boundary pixel associated with a boundary of an object that is represented in the first image; determining, from a plurality of candidate penalty values and for each pixel in the first image, an optimized penalty value for the pixel; generating an optimized cost function for the first image based on the optimized penalty values for the plurality of pixels; and generating a depth image for the first image based on the optimized cost function.