Abstract: A driver assistance system for an ego vehicle, and a method for a driver assistance system is provided. The system is configured to refine a coarse geolocation method based on the detection of the static features located in the vicinity of the ego vehicle. The system performs at least one measurement of the visual appearance of each of at least one static feature located in the vicinity of the ego vehicle. Using the at least one measurement, a position of the ego vehicle relative to the static feature is calculated. The real world position of the static feature is identified. The position of the ego vehicle relative to the static feature is calculated, which is, in turn, used to calculate a static feature measurement of the vehicle location. The coarse geolocation measurement and the the static feature measurement are combined to form a fine geolocation position. By combining the measurements, a more accurate location of the ego vehicle can be determined.

Abstract: The present technology provides systems, methods, and devices that can update aspects of a map as an autonomous vehicle navigates a route, and therefore avoids the need for dispatching a special purpose mapping vehicle for these updates. As the autonomous vehicle navigates the route, data captured by at least one sensor of an autonomous vehicle can indicate an inconsistency between pre-mapped from a high-resolution sensor system describing a location on a map, and current data describing a new feature of the location. The current data can be clustered together based on a threshold spatial closeness, where the clustering describes the new feature, and semantic labels of the pre-mapped data from the high-resolution sensor system can be updated based on the new feature described by the clustered current data.

Abstract: The present disclosure relates to a display system (1) for generating a composite view of a region behind a vehicle (V) towing a trailer (T). A first camera (C1) is provided for outputting first image data corresponding to a first image (IMG1), the first camera (C1) being configured to be mounted in a rear-facing orientation to the vehicle (V). A second camera (C2) is provided for outputting second image data corresponding to a second image (IMG2), the second camera (C2) being configured to be mounted in a rear-facing orientation to the trailer (T). An image processor (5) receives the first image data and said second image data. The image processor (5) is configured to combine said first image data and said second image data to generate composite image data corresponding to a composite image (IMG3). The present disclosure also relates to a corresponding method of generating a composite image (IMG3), and to a rig made up of a vehicle (V) and a trailer (T).

Abstract: A computer system obtains a plurality of road images captured by one or more cameras attached to one or more vehicles. The one or more vehicles execute a model that facilitates driving of the one or more vehicles. For each road image of the plurality of road images, the computer system determines, in the road image, a fraction of pixels having an ambiguous lane marker classification. Based on the fraction of pixels, the computer system determines whether the road image is an ambiguous image for lane marker classification. In accordance with a determination that the road image is an ambiguous image for lane marker classification, the computer system enables labeling of the image and adds the labeled image into a corpus of training images for retraining the model.

Abstract: Aspects of the disclosure relate to classifying the status of objects. For examples, one or more computing devices detect an object from an image of a vehicle's environment. The object is associated with a location. The one or more computing devices receive data corresponding to the surfaces of objects in the vehicle's environment and identifying data within a region around the location of the object. The one or more computing devices also determine whether the data within the region corresponds to a planar surface extending away from an edge of the object. Based on this determination, the one or more computing devices classify the status of the object.

Abstract: Computing devices and methods for reading gauges are disclosed. A gauge reading method includes capturing image data corresponding to a captured image of one or more gauges, detecting one or more gauges in the captured image, cropping a detected gauge in the captured image to provide a use image including the detected gauge, and classifying the detected gauge to correlate the detected gauge with a template image. The gauge reading method also includes attempting to perform feature detection rectification on the use image to produce a rectified image of the detected gauge, performing template matching rectification on the use image to produce the rectified image responsive to a failure to perform the feature detection rectification, and estimating a gauge reading responsive to the rectified image. A computing device may implement at least a portion of a gauge reading method.

Abstract: Systems, apparatus, methods, and articles of manufacture for Artificial Intelligence (AI) driving analysis and incentives, by utilizing on-board image object analysis to classify driving events and provide driving-based awards.

Abstract: Techniques for utilizing adaptable filters for edge-based deep learning models are described. Filters may be utilized by an edge electronic device to filter elements of an input data stream so that only a subset of the elements are used as inputs to a machine learning model run by the electronic device, enabling successful operation despite the input data stream potentially being generated at a higher rate than a rate in which the ML model can be executed. The filter can be a differential-type filter that generates difference representations between consecutive elements of the data stream to determine which elements are to be passed on for the ML model, a “smart” filter such as a neural network trained using outputs from the ML model allowing the filter to “learn” which elements are the most likely to be of value to be passed on, or a combination of both.

Abstract: A working vehicle is capable of autonomously traveling on a target traveling route and appropriately performing illumination during autonomous traveling to enable an operator to reliably confirm the presence of obstacles or the like on the target traveling route. The working vehicle includes a traveling body to autonomously travel on the target traveling route, illumination lamps located on the traveling body to respectively illuminate different directions, and a controller to change a control relating to a way of turning on the illumination lamps during the autonomously traveling.

Abstract: The present invention provides a data collection system comprising: a camera; a location module; a plurality of sensors; and a first processor communicatively coupled to the camera and the location module, the first processor programmed to: obtain a plurality of frames from the camera; obtain a plurality of locations from the location module; obtain a plurality of data measurements from the plurality of sensors; apply a previously trained first neural network model for identifying problematic road segments to frames captured by the camera; and if the first neural network model indicates that a frame is a problematic road segment, save the frame in association with a location provided by the location module.

Abstract: Provided are a marker for space recognition, a method of moving and lining up a robot based on space recognition, and a robot, and the robot that lines up and moves based on space recognition includes: a camera sensor that images a marker disposed on a traveling floor of the robot or a side of the traveling floor; and a control unit that analyzes an image captured by the camera sensor, calculates a moving direction or a moving speed of the robot on the basis of the marker, and controls a movement unit.

Abstract: The invention concerns a device and a method for detecting a tire on a vehicle to determine whether there is a single or twin tire on an axle. The device has an optical sensor for this purpose, the sensor detecting at least one region of a rim on which a tire to be determined is mounted. An evaluation unit is also provided which is designed to determine a shape of the area of the rim from the sensor signals and to generate a signal from the shape which represents the type of tire.

Abstract: The present disclosure provides a rear cross collision detection system and method. The rear cross collision detection system includes an obstacle detection unit configured to receive an electromagnetic wave reflected from a reflection point of an obstacle in order to detect the position of the obstacle, an identity determination unit configured to, when a plurality of obstacles is detected by the obstacle detection unit, determine whether the plurality of obstacles is the same object based on the positions or speeds of the detected obstacles, and a collision determination unit configured to determine the possibility of a collision with the plurality of obstacles detected by the obstacle detection unit based on the result of the determination by the identity determination unit.

Abstract: According to an aspect of the present invention, an information processing apparatus includes an object region detecting unit, a local region detecting unit, an object specifying unit. The object region detecting unit is configured to detect an object region based on one of distance information and luminance information. The local region detecting unit is configured to, when a divided area obtained by dividing the detected object region meets a predetermined condition, detect the divided area as a local region. The object specifying unit is configured to specify, as a specification target object, the object region in which the local region is continuously detected.

Abstract: A photoelectric converter includes pixels, vertical output lines to which a signal is outputted from the pixels, clippers configured to limit a potential of the output lines and a controller. Each of the clippers includes a first circuit configured to output an amplification signal according to a predetermined potential and the potential of the output line and a second circuit configured to supply a current according to the amplification signal to the output line. The controller controls each of the clippers to a state selected from states including a first state in which a range in which the potential of the output line can change is limited using the first and second circuits, and a second state in which the range in which the potential of the vertical output line can change is limited with an output of the second circuit deactivated.

Abstract: The above measurement device acquires output data from a sensor unit for detecting surrounding feature, and extracts, from the output data, data corresponding to detection result in a predetermined range in a predetermined positional relation with an own position. The predetermined range is determined in accordance with accuracy of the own position. Then, the measurement device executes predetermined processing based on the extracted data.

Abstract: A map generation device (10) generates linearization information expressing at least one or the other of a marking line of a roadway and a road shoulder edge based on measurement information of a periphery of the roadway. The measurement information is obtained by a measurement device. The map generation device (10) calculates an evaluation value expressing a reliability degree of partial information, for each partial information constituting the linearization information. A map editing device (20) displays the partial information in different modes according to the evaluation value, thereby displaying the linearization information. The map editing device (20) accepts input of editing information for the displayed linearization information.

Abstract: Localization and navigation systems and techniques are described. An electronic device comprises a processor configured to maintain a state vector storing estimates for a position of the electronic device at poses along a trajectory within an environment along with estimates for positions for one or more features within the environment. The processor computes, from the image data, one or more constraints based on features observed from multiple poses of the electronic device along the trajectory, and computes updated state estimates for the position of the electronic device in accordance with the motion data and the one or more computed constraints without computing updated state estimates for the features for which the one or more constraints were computed.

Abstract: A method for controlling a temperature of a refrigerator provided in a vehicle is provided. A method for controlling a temperature of a refrigerator provided in a vehicle according to an embodiment of the present disclosure detects a foodstuff requiring a low temperature storage included in image information of an article using an artificial neutral network model, and when the foodstuff requiring the low temperature storage is detected, can prevent deterioration of the foodstuff while the article is transported through the vehicle by controlling a temperature of the refrigerator based on storage temperature information of the foodstuff requiring the low temperature storage. A temperature control device of a refrigerator installed in a vehicle of the present disclosure is associated with an artificial intelligence module, an unmmanned aerial vehicle (UAV) robot, an augmented reality (AR) device, a virtual reality (VR) device, and a device related to a 5G service.

Abstract: A vehicle hitch assistance system includes a first image sensor in connection with a portion of the vehicle and positioned forward of a forward hitch disposed in a cargo bed of the vehicle. The system further includes a controller configured to capture first image data with the first image sensor. The first image data depicts a coupler of a trailer. The controller is further configured to identify a trailer type of the trailer based on the first image data. The trailer type is configured to connect to the forward hitch. The controller is further configured to acquire position data identifying a coupler position of the coupler in the first image data, derive a vehicle path aligning the forward hitch with the coupler, and control a maneuvering system driving the vehicle along the vehicle path.

Abstract: In various examples, a deep neural network (DNN) is trained for sensor blindness detection using a region and context-based approach. Using sensor data, the DNN may compute locations of blindness or compromised visibility regions as well as associated blindness classifications and/or blindness attributes associated therewith. In addition, the DNN may predict a usability of each instance of the sensor data for performing one or more operations—such as operations associated with semi-autonomous or autonomous driving. The combination of the outputs of the DNN may be used to filter out instances of the sensor data—or to filter out portions of instances of the sensor data determined to be compromised—that may lead to inaccurate or ineffective results for the one or more operations of the system.

Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.

Abstract: A method for determining a degree of overlap of at least one object with at least one lane via a representation of a surrounding environment of a platform as a two-dimensional pixel data field. The method includes allocating at least one lane pixel group to pixels of the two-dimensional pixel data field, which correspondingly represent at least one lane; allocating at least one object pixel group to pixels of the two-dimensional pixel data field, which correspondingly represent at least one object; defining at least one object pixel pair in the two-dimensional pixel data field, which pair characterizes a width of the at least one object pixel group; and comparing the object pixel pair and the lane pixel group in the two-dimensional pixel data field.

Abstract: A steering system of a vehicle, including an operation member to be operated by a driver, a steering device configured to steer a wheel, and a controller configured to control the steering system, wherein the controller is configured to parallelly execute a main process including a process in which the controller controls the steering device to perform steering in accordance with an operation of the operation member and an auxiliary process relating to an operation of the steering system and configured to change an execution ratio of the main process and an execution ratio of the auxiliary process.

Abstract: Methods, devices, and processor-readable media for hand-on-wheel gesture controls are described. A steering wheel is virtually segmented into a plurality of radial segments. Each segment is assigned a semantic meaning. Control commands related to control functions are mapped to different virtual segments of the steering wheel. When a user performs a gesture on the steering wheel, the system recognizes the gesture and selects a control function based on the location of the hand relative to the steering wheel. In various embodiments, on-wheel hand gestures, on-wheel hand location, and voice commands may be used in various combinations to enable a user to perform a wide selection of functions using a small number of unique commands.

Abstract: The present disclosure provides an image sensor and an image collection system. The image sensor includes: a pixel collection circuitry array including a plurality of pixel collection circuitries, each pixel collection circuitry being configured to monitor a change in a light intensity in a field of view and enter a triggered state when the change in the light intensity meets a predetermined condition; a boundary triggered pixel determination array configured to determine a boundary triggered pixel collection circuitry in the pixel collection circuitries in the triggered state; and a reading unit configured to respond to the boundary triggered pixel collection circuitry and output address information about the boundary triggered pixel collection circuitry.

Abstract: A method for assessing possible trajectories of road users in a traffic environment includes capturing the traffic environment with static and dynamic features, identifying at least one traffic user, determining at least one possible trajectory for at least one road user in the traffic environment, and assessing the at least one determined possible trajectory for the at least one road user with an adapted/trained recommendation service and the captured traffic environment.

Abstract: A vehicular control system includes a forward viewing camera disposed at an in-cabin side of a windshield of a vehicle and viewing forward of the vehicle. Road curvature of a road along which the vehicle is traveling is determined responsive at least in part to processing by an image processor of image data captured by the camera. Responsive at least in part to processing of captured image data, a traffic lane of the road along which the vehicle is traveling is determined. Upon approach of the vehicle to a curve in the road, speed of the vehicle is reduced to a reduced speed for traveling around the curve in the road at least in part responsive to at least one selected from the group consisting of (a) processing of image data captured by the forward viewing camera and (b) data relevant to a current geographical location of the equipped vehicle.

Abstract: An automotive sensor integration module including a plurality of sensors which differ in at least one of a sensing period or an output data format, an interface unit configured to receive pieces of detection data outputted from the plurality of sensors and convert the received detection data into a predetermined data format, and a signal processing unit configured to simultaneously output pieces of converted detection data from the interface unit on the basis of the sensing period of one among the plurality of sensors.

Abstract: The invention relates to a marking object that can be placed on a vehicle child seat for adaptive actuation of an airbag, which is configured to reflect electromagnetic radiation and mark a position and/or orientation of the vehicle child seat in relation to a vehicle seat for an imaging sensor based on the reflection, in order to actuate the airbag depending on the position and/or orientation of the vehicle child seat, wherein the marking object is a Quick Response code, radar reflector, lidar reflector, or infrared reflector. The invention also relates to a vehicle child seat, a method for determining a position and/or orientation of a vehicle child seat in relation to a vehicle seat, and interior monitoring system, a computer program for adaptive actuation of an airbag and a computer readable data carrier.

Abstract: Systems and methods for self-supervised depth estimation using image frames captured from a vehicle-mounted camera, may include: receiving a first image captured by the camera while the camera is mounted at a first location on the vehicle, the source image comprising pixels representing a scene of the environment of the vehicle; receiving a reference image captured by the camera while the camera is mounted at a second location on the vehicle, the reference image comprising pixels representing a scene of the environment; predicting a depth map for the first image comprising predicted depth values for pixels of the first image; warping the first image to a perspective of the camera at the second location on the vehicle to arrive at a warped first image; projecting the warped first image onto the source image; determining a loss based on the projection; and updating predicted depth values for the first image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for lighting adaptive navigation. In some implementations, map data associated with a property is received. Sensor data is obtained. Based on the map data and the sensor data, a lighting scenario is determined. Based on the lighting scenario, a modification to at least one of the lighting scenario, to a planned navigation path for the robotic device, to settings for a sensor of the robotic device, to a position for a sensor of the robotic device, or to a position of the robotic device is determined. An action is performed by based on the one or more modifications.

Abstract: A method for recognizing a parking space for a vehicle and a parking assistance system are disclosed. An obstacle is identified from successive image frames captured when the vehicle is moving and a first boundary for the obstacle is generated by a Convolutional Neural Network (CNN) algorithm based on a position of the obstacle shown in each of the successive image frames. Distances between the moving vehicle and the obstacle are detected by ultrasonic sensors. A second boundary for the obstacle is generated by a distance modification module based on the distances between the vehicle and the obstacle. A periphery of the obstacle is defined by a periphery definition module. In view of the periphery of the obstacle, a parking space is thus recognized by a parking space recognition module. The parking process can be changed to a self-drive mode, and remotely controlled by a mobile device.

Abstract: An apparatus for recognizing a division line on a road from an image captured by a camera includes: a processing area setting unit to set a processing area to the image; a statistics calculation unit to calculate statistics of the image in the processing area; a threshold value setting unit to set a plurality of threshold values on the basis of the statistics; a division line feature point extraction unit to classify a plurality of pixels contained in the image on the basis of the white line threshold value and the road surface threshold value and extracts feature points of the division line on the basis of classification results of the plurality of pixels; and a division line decision unit configured to decide the division line on the basis of the feature points extracted by the division line feature point extraction unit.

Abstract: Particulate matter, such as dust, steam, smoke, rain, etc. may cause one or more sensor types to generate false positive detections. In particular, various depth measurements may be impeded by particulate matter. Identifying a false return and/or removing a false detection based at least in part on a sensor output may comprise determining a similarity of a portion of a return signal to an emitted light pulse or an expected return signal, determining a variance of the signal portion over time, determining a difference between a power spectrum of the return relative to an expected power spectrum, and/or determining that a duration associated with the signal portion meets or exceeds a threshold duration.

Abstract: A vehicle configured to operate in an autonomous mode can obtain sensor data from one or more sensors observing one or more aspects of an environment of the vehicle. At least one aspect of the environment of the vehicle that is not observed by the one or more sensors could be inferred based on the sensor data. The vehicle could be controlled in the autonomous mode based on the at least one inferred aspect of the environment of the vehicle.

Abstract: There is provided a method for detecting a vehicle including receiving continuously captured front images, setting a search area of the vehicle in a target image based on a location of the vehicle or a vehicle area detected from a previous image among the front images, detecting the vehicle in the search area according to a machine learning model, and tracking the vehicle in the target image by using feature points of the vehicle extracted from the previous image according to a vehicle detection result based on the machine learning model. Since the entire image is not used as a vehicle detection area, a processing speed may be increased, and a forward vehicle tracked in an augmented reality navigation may be continuously displayed without interruption, thereby providing a stable service to the user.

Abstract: A partial image generating device has a processor configured to generate a partial image from an image in which the environment surrounding a vehicle has been photographed using an imaging device provided in the vehicle, and to assess whether or not the road represented in the image is straight. The processor is configured so that, when it has been assessed that the road represented in the image is straight, it generates a partial image by cutting out a first region in the image that is estimated to contain the road, based on the vanishing point of the road, and when it has assessed that the road represented in the image is not straight, it generates a partial image by cutting out a second region in the image determined based on the type of the vehicle.

Abstract: An image area including a traffic light in an image taken by a camera is determined, and the determined image area including the traffic light is extracted and the extracted image area is subjected to enlargement processing to determine whether a status of the traffic light is red or green, and notice to start crossing is provided to a user under a condition that the status of the traffic light switches from red to green. Consequently, even with image information from a single camera alone, accuracy in recognition of the traffic light can sufficiently be enhanced. As a result, crossing start notice can properly be provided without an increase in configuration complexity and weight of the system.

Abstract: A steering system of a vehicle, including an operation member to be operated by a driver, a steering device configured to steer a wheel, and a controller configured to control the steering system, wherein the controller is configured to parallelly execute a main process including a process in which the controller controls the steering device to perform steering of the wheel in accordance with an operation of the operation member and an auxiliary process relating to an operation of the steering system and configured to decrease an execution ratio of the main process and increase an execution ratio of the auxiliary process when a condition that a running speed of the vehicle is not lower than a threshold speed is satisfied.

Abstract: A sensor assembly may include a housing and a collection of optical sensors. The housing may include a base portion, and a raised portion defining a summit of the housing. A collection of optical sensors may include a first set of forward-facing optical sensors individually aligned with a corresponding opening in a front segment of the base portion for the housing, a second set of rear-facing optical sensors individually aligned with a corresponding opening in a rear segment of the base portion for the housing, and multiple sets of lateral optical sensors. Each set of lateral optical sensors may be aligned with a corresponding opening in one of multiple lateral segments of the base portion of the housing. Additionally, at least a first long distance sensor may be mounted on the summit.

Abstract: A system and methods for contrast sensitivity compensation provides for correcting the vision of users whose vision is deficient for discerning high spatial frequencies. The system and methods use measurements of the user's contrast detection as a function of spatial frequency in the image to correct images in real time. The system includes a head-mountable device that includes a camera and a processor that can provide enhanced images at video framing rates.

Abstract: Disclosed is an image processing method including adjusting a light exposure time of an image acquisition unit by using a target image converted to be output in a desired output mode among a plurality of output modes; and displaying target images acquired according to the adjustment.

Abstract: Techniques are disclosed for creating and presenting a graphical user interface for display of autonomous vehicle behaviors. The techniques include determining a trajectory of a vehicle operating in a real-world environment. Sensors of the vehicle obtain sensor data representing an object in the real-world environment. A maneuver of the vehicle to avoid a collision with the object is predicted based on the sensor data and the trajectory of the vehicle. It is determined that a passenger comfort level of a passenger riding in the vehicle will decrease based on the maneuver of the vehicle. The passenger comfort level is measured by passenger sensors of the vehicle. A graphical user interface is generated including representations of the vehicle, the object, and a graphic, text, or a symbol alerting the passenger of the predicted maneuver. The graphical user interface is transmitted to a display device of the vehicle.

Abstract: Sensor data captured by one or more sensors may be received at an analysis system. A neural network may be used to detect an object in the sensor data. A plurality of polygons surrounding the object may be generated in one or more subsets of the sensor data. A prediction of a future position of the object may be generated based at least in part on the polygons. One or more commands may be provided to a control system based on the prediction of the future position.

Abstract: A monocular visual simultaneous localization and mapping (SLAM) data processing method.

Abstract: A method and apparatus for detecting an obstacle, an electronic device, and a storage medium. A specific implementation of the method includes: detecting, by a millimeter-wave radar, position points of candidate obstacles in front of a vehicle; detecting, by a camera, a left road boundary line and a right road boundary line of a road on which a vehicle is located; separating the position points of the candidate obstacles according to the left road boundary line and the right road boundary line of the road on which the vehicle is located, and extracting position points between the left road boundary line and the right road boundary line; projecting the position points between the left road boundary line and the right road boundary line onto an image; and detecting, based on projection points of the position points on the image, a target obstacle in front of the vehicle.

Abstract: A traveling lane recognition apparatus includes a camera and a controller. The controller recognizes a linear marking position where a linear marking exists in each of detection target images, repeatedly performs image detection processing for detecting a white line or a blank at a linear marking position in each of detection target images corresponding to captured images, in an order of capturing time points of the captured images. The controller is configured to recognize a lane in which the vehicle is traveling among the plurality of lanes on the street based on a positional relationship between a solid lane line detected by the lane line detection and the vehicle and a positional relationship between the broken lane line detected by the lane line detection and the vehicle.

Abstract: A traffic signal information management system executes a region-of-interest calculation processing to calculate, based on a position information of a vehicle and a traffic signal information indicating the position of a traffic signal, a region of interest in which a traffic signal is presumed to be present in an image imaged by the camera, and also execute a traffic signal image detection processing to detect a traffic signal image included in the region of interest. The traffic signal information management system then execute an evaluation processing to perform a comparison between the position of the region of interest calculated by the region-of-interest calculation processing and the position of the traffic signal image detected by the traffic signal image detection processing and evaluate the certainty of the traffic signal information based on the comparison.

Abstract: A motor vehicle light assembly includes a housing; a light source disposed in the housing, and a light-transmissive lens operably attached to the housing. A heater member is disposed between the housing and the light-transmissive lens. The heater member is configured to radiate heat emitted from the light source, with the heater member being routed to direct the radiated heat onto the light-transmissive lens to regulate the temperature of the light-transmissive lens to inhibit fogging, frosting and icing of the light-transmissive lens.