Systems and methods for synchronization are provided. In some aspects, a method for synchronizing an image sensor is provided. The method includes receiving image data captured using an image sensor that is moving along a pathway, and assembling an image sensor trajectory using the image data. The method also includes receiving position data acquired along the pathway using a position sensor, wherein timestamps for the image data and position data are asynchronous, and assembling a position sensor trajectory using the position data. The method further includes generating a spatial transformation that aligns the image sensor trajectory and position sensor trajectory, and synchronizing the image sensor based on the spatial transformation.

Techniques provided herein are directed toward virtually extending an updated set of output positions of a mobile device determined by a VIO by combining a current set of VIO output positions with one or more previous sets of VIO output positions in such a way that ensure all outputs positions among the various combined sets of output positions are consistent. The combined sets can be used for accurate position determination of the mobile device. Moreover, the position determination further may be based on GNSS measurements.

The present invention relates to a multi-band image generation system and method using a deep-learning network, and to a technology of generating a multi-band image based on an image of a panchromatic band by analyzing a nonlinear relationship between the panchromatic band and each multi-band using a deep-learning network.

Disclosed are a method and an apparatus for improving positioning of vehicles based on infrastructure sensing information. The method for improving positioning of vehicles based on infrastructure sensing information may include steps of (a) receiving an absolute position of a peripheral vehicle located within a certain distance to a vehicle from an infrastructure device; (b) determining a first relative distance of the peripheral vehicle through an environmental sensor of the vehicle; and (c) performing positioning correction for the absolute position of the vehicle based on an absolute position of the peripheral vehicle and a first relative distance of the peripheral vehicle.

Position enhancement for vehicle positioning is provided. Vehicle-to-everything (V2X) messages are received from a roadside unit (RSU) to an onboard unit (OBU) of a vehicle via a transceiver of the vehicle, the V2X messages indicating a location of the RSU. Image sensors of the vehicle are utilized to capture sensor data of the RSU. A current position of the vehicle is updated to a corrected current position of the vehicle based the RSU as shown in the sensor data and the location of the RSU indicated in the V2X messages.

A navigation system for providing driving instructions to a driver of a vehicle traveling on a route is provided. The driving instructions are generated by executing a multimodal fusion method that comprises extracting features from sensor measurements, annotating the features with directions for the vehicle to follow the route with respect to objects sensed by the sensors, and encoding the annotated features with a multimodal attention neural network to produce encodings. The encodings are transformed into a common latent space, and the transformed encodings are fused using an attention mechanism producing an encoded representation of the scene. The method further comprises decoding the encoded representation with a sentence generation neural network to generate a driving instruction and submitting the driving instruction to an output device.

A method, apparatus and computer program product are provided to estimate the location of a vehicle based at least in part upon two or more road signs that are depicted by one or more images captured by one or more image capture devices onboard the vehicle. By relying at least in part upon the two or more road signs, the location of the vehicle may be refined or otherwise estimated with enhanced accuracy, such as in instances in which there is an inability to maintain a line-of-sight with the satellites of a satellite positioning system or otherwise in instances in which the location estimated based upon reliance on satellite or radio signals is considered insufficient. As a result, the vehicle may be navigated in a more informed and reliable manner and the relationship of the vehicle to other vehicles may be determined with greater confidence.

The disclosure relates to a method for guiding landing of an unmanned aerial vehicle. The method for guiding landing of unmanned aerial vehicle includes: determining location information of the unmanned aerial vehicle over a target airdrome by using a plurality of position detectors in an airdrome auxiliary positioning system; generating corrected guidance information according to an offset vector between the location information and target location information, where the target location information is information representing any location within signal coverage of a guidance beacon of the target airdrome; and sending the corrected guidance information to the unmanned aerial vehicle, where the corrected guidance information is used to guide the unmanned aerial vehicle to fly into the signal coverage of the guidance beacon.

A vehicle posture calculation device includes an electronic control unit for a vehicle. The electronic control unit acquires a position and orientation of the vehicle from information of a global positioning system receiver. The electronic control unit extracts, as at least one feature point, a position of a landmark in an image acquired with a camera. The electronic control unit acquires at least one calculated reference point and calculate an inclination angle of the vehicle. The at least one calculated reference point is acquired by calculating a position of the landmark to be captured in the image with the camera. The position of the landmark is calculated from a three-dimensional map and the position and the orientation of the vehicle that are acquired. The inclination angle is calculated from displacement between the at least one feature point and the at least one calculated reference point.

A system and method for performing visual odometry is disclosed. In aspects, the system implements methods to generate an image pyramid based on an input image received. A refined pose prior information representing a location and orientation of the autonomous vehicle can be generated based on one or more images of the image pyramid. One or more seed points can be selected from the one or more images of the image pyramid. One or more refined seed representing the one or more seed points with added depth values can be generated. One or more scene points can be generated based on the one or more refined seed points. A point cloud can be generated based on the one or more scene points.