Abstract: Systems, methods, and non-transitory computer readable media may be configured to characterize optical characteristics of optical elements. An optical element mount may be configured to carry an optical element. A calibration display may be configured to display a calibration object. The calibration object may include a known visual pattern. Multiple images of the calibration object may be obtained. The multiple images may be acquired using the optical element carried by the optical element mount. The multiple images may include different perspectives of the calibration object. Optical characteristics of the optical element may be characterized based on the known visual pattern and the different perspectives of the calibration object.

Abstract: Systems, methods, and non-transitory computer-readable media are provided for implementing a tracking camera system onboard an autonomous vehicle. Coordinate data of an object can be received. The tracking camera system actuates, based on the coordinate data, to a position such that the object is in view of the tracking camera system. Vehicle operation data of the autonomous vehicle can be received. The position of the tracking camera system can be adjusted, based on the vehicle operation data, such that the object remains in view of the tracking camera system while the autonomous vehicle is in motion. A focus of the tracking camera system can be adjusted to bring the object in focus. The tracking camera system captures image data corresponding to the object.

Abstract: Systems and methods for vehicle surveillance include a camera for capturing target images of vehicles. An object recognition system is in communication with the camera, the object recognition system including a processor for executing a synthesizer module for generating a plurality of viewpoints of a vehicle depicted in a source image, and a domain adaptation module for performing domain adaptation between the viewpoints of the vehicle and the target images to classifying vehicles of the target images regardless of the viewpoint represented in the target images. A display is in communication with the object recognition system for displaying each of the target images with labels corresponding to the vehicles of the target images.

Abstract: The present invention provides a roof-mounted solar module integration device, a solar power vehicle and a encapsulation method for modules. The integration device comprises: a substrate in which a through-hole is formed, wherein a front side of the substrate is provided with a first trench, and a reverse side of the substrate is provided with a second trench; a solar module fixed on the front side of the substrate; a plurality of conductive bands arranged in the first trench, wherein a first end of each of the conductive bands is connected with the solar module, and a second end is led out of the through-hole to the reverse side of the substrate; and a bypass diode and an anti-reversion diode which are arranged in the second trench and connected with the second ends of the conductive bands.

Abstract: In one embodiment, when an ADV is driving on a road segment, a driving parameter is recorded in response to a first control command. A difference between the first driving parameter and a target driving parameter corresponding to the first control command is determined. In response to determining that the difference exceeds a predetermined threshold, a second control command is issued to compensate the difference and cause the ADV to drive with a second driving parameter closer to the target driving parameter. A slope status of the road segment is derived based on at least the second control command. Map data of a map corresponding to the road segment of the road is updated based on the derived slope status. The updated map can be utilized to generate and issue proper control commands in view of the slope status of the road when the ADV drives on the same road subsequently.

Abstract: A method for implementing an unsupervised cross-domain distance metric adaptation framework with a feature transfer network for enhancing facial recognition includes recursively training a feature transfer network and automatic labeling of target domain data using a clustering method, and implementing the feature transfer network and the automatic labeling to perform a facial recognition task.

Abstract: Systems, methods, and non-transitory computer-readable media are provided for acquiring driving records from an autonomous vehicle. One or more patterns can be determined from the driving records. One or more criteria can be generated based on the one or more patterns. One or more suspicious points can be identified in the driving records by applying the one or more criteria to the driving records.

Abstract: A computer-implemented method, system, and computer program product is provided for pose-invariant facial recognition. The method includes generating, by a processor using a recognition neural network, a rich feature embedding for identity information and non-identity information for each of one or more images. The method also includes generating, by the processor using a Siamese reconstruction network, one or more pose-invariant features by employing the rich feature embedding for identity information and non-identity information. The method additionally includes identifying, by the processor, a user by employing the one or more pose-invariant features. The method further includes controlling an operation of a processor-based machine to change a state of the processor-based machine, responsive to the identified user in the one or more images.

Abstract: A video retrieval system is provided that includes a server for retrieving video sequences from a remote database responsive to a text specifying a face recognition result as an identity of a subject of an input image. The face recognition result is determined by a processor of the server, which estimates, using a 3DMM conditioned Generative Adversarial Network, 3DMM coefficients for the subject of the input image. The subject varies from an ideal front pose. The processor produces a synthetic frontal face image of the subject of the input image based on the input image and coefficients. An area spanning the frontal face of the subject is made larger in the synthetic than in the input image. The processor provides a decision of whether the synthetic image subject is an actual person and provides the identity of the subject in the input image based on the synthetic and input images.

Abstract: A video surveillance system is provided. The system includes a device configured to capture an input image of a subject located in an area. The system further includes a processor. The processor estimates, using a three-dimensional Morphable Model (3DMM) conditioned Generative Adversarial Network, 3DMM coefficients for the subject of the input image. The subject varies from an ideal front pose. The processor produces, using an image generator, a synthetic frontal face image of the subject of the input image based on the input image and coefficients. An area spanning the frontal face of the subject is made larger in the synthetic than in the input image. The processor provides, using a discriminator, a decision of whether the subject of the synthetic image is an actual person. The processor provides, using a face recognition engine, an identity of the subject in the input image based on the synthetic and input images.

Abstract: A face recognition system is provided. The system includes a device configured to capture an input image of a subject. The system further includes a processor. The processor estimates, using a 3D Morphable Model (3DMM) conditioned Generative Adversarial Network, 3DMM coefficients for the subject of the input image. The subject varies from an ideal front pose. The processor produces, using an image generator, a synthetic frontal face image of the subject of the input image based on the input image and the 3DMM coefficients. An area spanning the frontal face of the subject is made larger in the synthetic image than in the input image. The processor provides, using a discriminator, a decision indicative of whether the subject of the synthetic image is an actual person. The processor provides, using a face recognition engine, an identity of the subject in the input image based on the synthetic and input images.

Abstract: State of an autonomous driving vehicle (ADV) is measured and stored for a location and speed of the ADV. Later, the state of the ADV is measured for the location and speed corresponding to a previously stored state of the ADV at the same location and speed. Fields of the measured stored states of the ADV are compared. If one or more differences between the measured and stored ADV states exceeds a threshold, then one or more control input parameters of the ADV is adjusted, such as steering, braking, or throttle. Differences may be attributable to road conditions or to state of servicing of the ADV. Differences between measured and stored states of the ADV can be passed to a service module. Service module can access crowd sourced data to determine whether one or more control input parameters for a driving state of one or more ADVs should be updated.

Abstract: A system included and a computer-implemented method performed in one of a plurality of self-driving vehicles that are connected through a network are described. The system performs: processing image data of one or more scene images received by said one of the plurality of self-driving vehicles, to detect one or more objects included in the one or more scene images; determining a target object from the one or more detected objects at least based on the processed image data; predicting movement of the target object at least based on a current position and a current movement state of the target object; and performing a self-driving operation to drive said one of the plurality of self-driving vehicles based on the predicted movement of the target object.

Abstract: A touch screen and a touch device are provided. The touch screen includes a substrate and a plurality of touch electrodes on the substrate arranged at a same layer and in a matrix. Each of the plurality of touch electrode includes at least two sub-electrode wires, and the at least two sub-electrode wires are connected in sequence to form a polyline-shape. The substrate includes a plurality of sub-regions, each of the plurality of sub-region includes at least one touch electrode, and the at least one touch electrodes at a same sub-region are of an identical pattern. The plurality of sub-regions includes at least two sub-regions, and respective touch electrodes of the at least two sub-regions are of different patterns.

Abstract: A system included and a computer-implemented method performed in an autonomous-driving vehicle are described. The system performs: detecting one or more movable objects; determining a target movable object from the one or more detected objects; determining a manner of generating a directed alert notification selectively toward the target movable object; and causing a directed alert notification of the determined manner to be generated toward the target movable object.

Abstract: When an ADV is detected to transition from a manual driving mode to an autonomous driving mode, a first pedal value corresponding to a speed of the ADV at a previous command cycle during which the ADV was operating in the manual driving mode is determined. A second pedal value is determined based on a target speed of the ADV at a current command cycle during which the ADV is operating in an autonomous driving mode. A pedal value represents a pedal percentage of a maximum pedal pressure or maximum pedal pressed distance of a throttle pedal or brake pedal from a neutral position. A speed command is generated and issued to the ADV based on the first pedal value and the second pedal value, such that the ADV runs in a similar acceleration before and after switching from the manual driving mode to the autonomous driving mode.

Abstract: In one embodiment, when speed control command (e.g., throttle, brake commands) is issued based on a target speed, a first feedback parameters is determined based on an expected speed and an actual speed of the ADV in response to the speed control command. A second feedback parameter is determined by applying a speed control parameter adjustment (SCPA) model to a set of input parameters that are captured or measured at the point in time. The set of input parameters represents a driving environment of the ADV at the point in time. One or more control parameters of a speed controller of the ADV is adjusted based on the first feedback parameter and the second feedback parameter, where the speed controller is configured to generate and issue speed control commands. Subsequent speed control commands can be generated based on the adjusted speed control parameters of the speed controller.

Abstract: Systems, methods, and non-transitory computer readable media configured to generate enhanced training information. Training information may be obtained. The training information may characterize behaviors of moving objects. The training information may be determined based on observations of the behaviors of the moving objects. Behavior information may be obtained. The behavior information may characterize a behavior of a given object. Enhanced training information may be generated by inserting the behavior information into the training information.

Abstract: Systems, methods, and non-transitory computer readable media configured to generate enhanced three-dimensional information. Three-dimensional information of a scene may be obtained. The three-dimensional information may define a three-dimensional point cloud model of the scene. The three-dimensional information may be determined based on distances of the scene from a location. Image information may be obtained. The image information may define one or more images of an object. The object may be identified based on the image information. A three-dimensional point cloud model of the object may be obtained. Enhanced three-dimensional information of the scene may be generated by inserting the three-dimensional point cloud model of the object into the three-dimensional point cloud model of the scene.

Abstract: Systems and methods are provided for segmenting a data frame to be acquired into a number of incremental data of equal data length. A first incremental data of the data frame can be acquired from one or more sensors. The first incremental data of the data frame can be processed while a next incremental data of the data frame is being acquired from the one or more sensors. The acquiring and processing of incremental data of the data frame can continue until a last incremental data of the data frame is acquired and processed. Processed incremental data can be outputted as a processed data frame.