Abstract: A control apparatus for an object moving in a specific zone while recognizing one or more markers deployed in the specific zone by a camera. The control apparatus is configured to execute detecting whether or not that the specific zone or surroundings of the object is darker than a specified brightness, and when detecting that the specific zone or the surroundings of the object is darker than the specified brightness, operating a lighting device installed in the object to illuminate the one or more markers located around the object.

Abstract: A camera system for a vehicle includes a camera having a housing defining an interior space, a memory device in the interior space, a processor in the interior space coupled to the memory device, a lens exposed on an exterior of the housing, an image sensor in the interior space coupled to the memory device, and a sensor coupled to the processor. The camera system also includes an attachment mechanism configured to secure the camera system to the vehicle. The camera is configured to move between a closed position and an open position. The memory device includes instructions configured to cause the processor to determine the camera is in the open position in response to an output signal by the sensor, and to cause the camera system to record the video captured by the image sensor in response to the camera being in the open position.

Abstract: A processor of an object detection device is configured to search for a pair of coordinates associated with a disparity approximately equal to a target disparity satisfying a predetermined condition in a second direction of a disparity map, update a first pair of coordinates to the found pair of coordinates, and calculate a height of an object corresponding to the target disparity on the basis of the first pair of coordinates. In the disparity map, a disparity acquired from a captured image is associated with a pair of two-dimensional coordinates formed by a first direction and the second direction intersecting the first direction. When a second pair of coordinates associated with a disparity approximately equal to the target disparity is present within a predetermined interval from the first pair of coordinates, the processor is configured to update the first pair of coordinates to the second pair of coordinates.

Abstract: A vehicle mirror assembly is provided. The vehicle mirror assembly, for example, includes a housing attachable to a vehicle. The vehicle mirror assembly also includes a reflective surface coupled to the housing or covering an opening in the housing. The vehicle mirror assembly further includes a movable sensor coupled to the housing or contained in a space formed by the housing and reflective surface. The vehicle mirror assembly further includes an actuator assembly configured to modify an orientation, a position, or a combination thereof of the movable sensor in response to a control signal.

Abstract: A method and system are provided to facilitate statement acquisition and verification pertaining to an incident. One or more processors are operationally coupled to one or more software modules, configured to: receive audio data between a suspect and an officer at a portable radio, detect a pre-Miranda statement made by the suspect within the audio data; detect a Miranda warning made by the officer within the audio data; detect a waiving of Miranda rights by the suspect within the audio data; detect a post-Miranda statement by the suspect within the audio data after the waiving of Miranda rights; determine when a degree of semantic similarity between the pre-Miranda statement and the post-Miranda statement fails to satisfy an admissibility condition; generate one or more questions to induce the suspect to repeat the pre-Miranda statement; and present the one or more questions to an electronic user interface.

Abstract: An object detector detects, for each of environmental sensors mounted on a vehicle, an object in an area around the vehicle from each piece of time-series environmental data generated by the environmental sensor; identifies a blind spot that is not represented in any of the pieces of environmental data respectively generated by the environmental sensors; selects, from the environmental sensors, an environmental sensor generating environmental data that can be omitted in detection of the object, based on a travel condition of the vehicle; requests blind spot data representing the blind spot from an external device equipped with an external sensor capable of generating the blind spot data; and stops detection of the object from environmental data generated by the selected environmental sensor and detects an object in the blind spot from obtained blind spot data, when the blind spot data is obtained from the external device.

Abstract: A vehicular video mirror system includes a display device having a video display screen accommodated by a mirror head of an interior rearview mirror assembly. The vehicular video mirror system is operable in a mirror mode or a display mode. A vehicle-mounted rearward-viewing digital camera is disposed at the vehicle and a trailer-mounted rearward-viewing analog camera is disposed at a trailer that is configured to be hitched to the vehicle. With no trailer hitched to the vehicle, and when the vehicular video mirror system operates in the display mode, the video display screen displays video images derived from image data captured by the vehicle-mounted rearward-viewing camera. With the trailer hitched to the vehicle, and when the vehicular video mirror system operates in the display mode, the video display screen displays rearward-view video images derived from image data captured by the trailer-mounted rearward-viewing camera.

Abstract: Disclosed herein are methods, systems, and apparatus for automated license plate recognition and methods for training a machine learning model to undertake automated license plate recognition. For example, a method can comprise dividing an image or video frame comprising a license plate into a plurality of image patches, determining a positional vector for each of the image patches, adding the positional vector to each of the image patches and inputting the image patches and their associated positional vectors to a text-adapted vision transformer. The text-adapted vision transformer can be configured to output a prediction concerning the license plate number of the license plate.

Abstract: An information processing device includes: an image acquisition unit configured to acquire an image captured by an imaging unit mounted on a vehicle; a target detection unit configured to detect a target region including a target in the acquired image; a classification identification unit configured to identify classification including a type of the detected target and a size of the detected target region; and a region determination unit configured to determine a region obtained by adding a margin corresponding to the identified classification to the target region as an image processing region.

Abstract: An analytical recognition system includes a video camera, an antenna, and a data analytics module. The video camera is configured to capture video data. The antenna is configured to capture mobile communication device data. The data analytics module is configured to correlate the video data and the mobile communication device data to generate a profile of a person associated with the video data and the mobile communication device data. The profile has profile data including any one or a combination of the captured video data and the captured mobile communication data.

Abstract: A vehicle with a road surface rendering function includes a projection member, a controller, and an external camera. The projection member is configured to project light for road surface rendering from the vehicle that is traveling to render a road surface rendered image on a road surface around the vehicle. The controller is configured to control light projection for the road surface rendering by the projection member. The external camera provided on the vehicle and configured to capture an image of the road surface so that the image includes surroundings of the road surface rendered image. The controller is configured to suppress the light projection from the projection member for the road surface rendered image by making determination on a road surface reflection state based on the image captured by the external camera.

Abstract: A method performed by an annotation system for supporting annotation of objects in image frames of a traffic environment-related video sequence. The annotation system determines an annotation of an object in an image frame of the video sequence, which annotation comprises at least a first property of the object; tracks the object through the video sequence; and assigns the at least first object property to the object in one or more previous and/or subsequent image frames of the video sequence. The annotation system further identifies at least a first image frame based on one or more criterion. Moreover, the annotation system appoints the at least first identified image frame as annotation data.

Abstract: A panoramic system can receive content (e.g., live video) recorded in a landscape orientation and use a portrait dynamic crop window to display a portrait area of the received content. The panoramic system can further display the content in a landscape dynamic crop window that has a moveable user interface control that can pan the portrait crop window as the content plays in one or both of the dynamic crop windows.

Abstract: Methods and systems are described for new paradigms for user interaction with an unmanned aerial vehicle (referred to as a flying digital assistant or FDA) using a portable multifunction device (PMD) such as smart phone. In some embodiments, a method for synchronizing video and audio is described. The method includes capturing video of a physical environment, receiving first audio of the physical environment captured by a first microphone of a first distributed electronic device, and synchronizing the video of the physical environment with the first audio of the physical environment.

Abstract: A control device for automatic stop of a vehicle, wherein the vehicle includes a radar and a sonar, the radar detecting a distance to an obstacle and detecting a height of the obstacle from a road surface, the sonar detecting the distance to the obstacle and detecting a signal level of a reflected wave from the obstacle. The control device includes a control unit having a processor configured to output a signal for triggering the automatic stop of the vehicle when the signal level of the reflected wave from the obstacle is greater than a predetermined threshold, wherein the control unit is configured to change the predetermined threshold for triggering the automatic stop of the vehicle between a first predetermined threshold and a second predetermined threshold based on the height of the obstacle detected by the radar.

Abstract: A vehicle display device includes a first display unit disposed in front of and above a driver's seat and including a display screen configured to be deployed from an interior member into the vehicle cabin and be withdrawn from the vehicle cabin into an inside of the interior member, a drive unit configured to drive the display screen, and a control unit configured to control the first display unit and the drive unit. The control unit includes a driving status acquisition unit configured to acquire a driving status of a vehicle, a drive control unit configured to change a deployment amount of the display screen based on the acquired driving status, and a display control unit configured to cause the display screen to display a rear seat image captured by an in-vehicle camera for a rear seat to fit with the deployment amount of the display screen.

Abstract: A vehicular camera includes a PCB having an imager disposed thereat, a lens barrel accommodating a lens, and a lens barrel support structure that protrudes from the PCB and at least partially circumscribes the imager. The lens barrel has an outer surface between the ends of the lens barrel. The outer surface of the lens barrel is adhesively bonded to an inner surface of the lens barrel support structure via adhesive. The outer surface of the lens barrel opposes the inner surface of the lens barrel support structure. With the adhesive in its uncured state and contacting the opposed surfaces, the imager is aligned with the lens accommodated at the lens barrel. With the imager aligned with the lens, the adhesive is cured to adhesively attach the lens barrel at the lens barrel support structure.

Abstract: A method for determining a trailer detection parameter of a trailer including receiving an image from at least one camera at a controller. The at least one camera defines a field of view including at least a portion of a vehicle trailer. The method determines a trailer angle of the vehicle trailer relative to a tractor, identifies at least one feature in an image of the trailer, determines a two-dimensional distance from the at least one feature to a predefined position on the image, and converts the two-dimensional distance to a three-dimensional distance based at least in part on the determined angle. The three-dimensional distance is a trailer detection parameter of the trailer.

Abstract: Eyewear providing an interactive augmented reality experience to users in a first physical environment viewing objects in a second physical environment (e.g., X-ray effect). The second environment may be a room positioned behind a barrier, such as a wall. The user views the second environment via a sensor system moveable on the wall using a track system. As the user in the first environment moves the eyewear to face the outside surface of the wall along a line-of-sight (LOS) at a location (x, y, z), the sensor system on the track system repositions to the same location (x, y, z) on the inside surface of wall. The image captured by the sensor system in the second environment is wirelessly transmitted to the eyewear for displayed on the eyewear displays, providing the user with an X-ray effect of looking through the wall to see the objects within the other environment.

Abstract: Methods and computing apparatus are provided for training AI/ML systems and use of such systems for performing image analysis so that the damaged parts of a physical structure can be identified accurately and efficiently. According to one embodiment, a method includes selecting an AI/ML system of a particular type; and training the AI/ML system using a dataset comprising one or more auto-labeled images. The auto-labeling was performed using the selected AI/ML system configured using a parts-identification model. The configuration of the trained AI/ML system is output as an improved parts-identification model.

Abstract: A vehicle includes a distance estimation device that estimates the distance from the vehicle to a traffic light. The distance estimation device includes an image acquisition unit that acquires an image captured by a camera for imaging the surroundings of the vehicle, a light size acquisition unit that acquires a light size of a light of the traffic light reflected in the image, and a distance estimation unit that estimates the distance from the vehicle to the traffic light based on the light size. The light size acquisition unit removes flare of the light in the image, and acquires the light size in the image after the flare is removed.

Abstract: A lane departure suppression device including a control unit that executes a lane departure suppression control (automatic steering of the steering wheel and/or a warning being issued) when it is determined that there is a possibility that a vehicle departs from a lane. The control unit does not execute the lane departure suppression control when the control unit determines that a lateral speed and a lateral acceleration of the vehicle are increased within a predetermined time from a time point at which acceleration and deceleration of the vehicle is started, and that there is an adjacent lane on a side with respect to the lane in which the lateral speed and the lateral acceleration are increased.

Abstract: A camera module comprises: a lens barrel disposed in a front body and comprising a lens; a first substrate disposed under the body; a support member partially disposed on an undersurface of the first substrate; and a second substrate disposed under the first substrate and coupled to the support member, wherein the support member comprises: a fence portion disposed between the first substrate and the second substrate; and a hook portion which comprises a region extending from the fence portion and having a coupling hole into which a partial side surface of the second substrate is inserted, and an extended portion inclined at a predetermined angle with respect to the region having the coupling hole formed therethrough.

Abstract: A remote operation system 1 includes: an image capturing device 20, provided at a forklift F; a head-mounted type image display device 10, mounted to a head of an operator O; a command reception device 11, receiving a remote operation command by the operator O; and a synthesized remote image generation device 12A, obtaining a content of the remote operation command received by the command reception device 11, an action state of the forklift F acting according to the remote operation command, and a remote image captured by the image capturing device 20, and generating a synthesized remote image by synthesizing a command display image indicating the content of the remote operation command and an action display image indicating the action state of the forklift F into the remote image. The head-mounted type image display device 10 displays the generated synthesized remote image before eyes of the operator O.

Abstract: In an imaging apparatus, a protrusion member of a lens barrel is arranged to protrude, from an outer surface of a barrel body, toward a direction away from an optical axis of a lens. The protrusion member includes an upper portion. The upper portion is located above the optical axis of the lens, and has an upper end. The protrusion member includes a lower portion. The lower portion is located below the optical axis of the at least one lens, and has a lower end. The upper end of the upper portion has a first minimum distance with respect to the optical axis of the lens, and the lower end of the lower portion has a second minimum distance with respect to the optical axis of the lens. The protrusion member is configured such that the first minimum distance is smaller than the second minimum distance.

Abstract: Methods, systems, and computer programs are presented for monitoring tailgating when a vehicle follows another vehicle at an unsafe distance. A method for enhancing a Following Distance (FD) machine learning (ML) model is disclosed. The method includes providing a management user interface (UI) for configuring FD parameters, followed by receiving FD events. A UI for manual FD annotation and another for customer review of filtered FD events are also provided. Annotations and customer review information are collected to improve the training set for the FD ML model. The FD model is then trained with the new data and downloaded to a vehicle. Once installed, the FD model is utilized to detect FD events within the vehicle, thereby enhancing the vehicle's safety and performance in driving scenarios by improving the accuracy and reliability of FD event predictions or detections.

Abstract: A system for detecting boundaries of lanes on a road is presented. The system includes an imaging system configured to produce a set of pixels associated with lane markings on a road. The system also includes one or more processors configured to detect boundaries of lanes on the road, including: receive, from the imaging system, the set of pixels associated with lane markings; partition the set of pixels into a plurality of groups, each of the plurality of groups associated with one or more control points; and generate a first spline that traverses the control points of the plurality of groups, the first spline describing a boundary of a lane on the road.

Abstract: The present disclosure relates to a hologram recording system that has an optical structure capable of replacing a polarization image sensor, thereby acquiring high-resolution holograms in real time by utilizing a high-resolution general image sensor. The hologram recording system for acquiring an interference pattern formed by self-interference of incident light from a target object is disclosed. The hologram recording system comprises a polarizer array including a plurality of polarizers, an image sensor including a plurality of pixels and an imaging optics disposed between the polarizer array and the image sensor. The imaging optics optically corresponds each of the plurality of polarizers to each of the plurality of pixels.

Abstract: An object detection device according to the present disclosure, installed in a vehicle, includes a plurality of ranging sensors and each including a transmitter configured to transmit ultrasonic waves and a receiver configured to receive reflected waves of the ultrasonic waves transmitted by the transmitter and reflected by an object around the vehicle, and processing circuitry configured to detect the object around the vehicle based on the reflected waves received by the receiver during a wave receiving period until a predetermined period of time elapses from transmission of the ultrasonic waves by the transmitter. The processing circuitry is configured to acquire an imaged image imaged by an in-vehicle camera that images surroundings of the vehicle. The processing circuitry is configured to determine whether a specific object is contained based on the imaged image.

Abstract: A measurement apparatus detects a person and an umbrella based on acquired image data, and measures the number of persons based on a detected result.

Abstract: Child seat monitoring system for a vehicle (e.g., using a computerized tool) is enabled. For example, a monitoring system for a child seat in a vehicle can comprise: a human machine interface unit, and a control unit, wherein the human machine interface unit comprises a sound system and a display unit, wherein the sound system is configured to capture a lock sound of a seat belt of the child seat, wherein the control unit is configured to identify if the lock sound corresponds to a predetermined safe locking sound of the seat belt, and wherein the control unit is configured to indicate in the display unit that the seat belt of the child seat is locked.

Abstract: Systems and methods are provided for interpreting traffic information for a vehicle. Sensor data is collected from at least one first sensor device of the vehicle. At least one relevant object is determined within the sensor data based on a window defined by a plurality of ranges and associated elevations, wherein the plurality of ranges and associated elevations are defined relative to the at least one first sensor device. A confidence score of the at least one relevant object is determined based on an identification of at least one pattern of activity of other objects associated with an intersection. A subset of sensor data is determined from at least one second sensor of the vehicle based on the confidence score of the relevant object. Traffic device data for use in controlling the vehicle is generated based on an evaluation of the subset of sensor data.

Abstract: A data transmitter is to be mounted on an autonomous driving vehicle. The data transmitter determines whether a confidence score indicating the degree of reliability of detection of the object from the area image is greater than a predetermined confidence score threshold; transmits, when the confidence score regarding the area image is greater than the confidence score threshold, the area image or a face image representing the face of a driver to a terminal, together with a first setting for displaying the area image or the face image on the terminal in first mode; and transmits, when the confidence score is less than the confidence score threshold, the area image to the terminal, together with a second setting for displaying the area image on the terminal in second mode that draws more attention of a user of the terminal than the first mode.

Abstract: A method for tracking an object. A first coordinated control of a lighting device and an optical sensor is assigned to a first visible distance range. A first recording of the first visible distance range while illuminated by the lighting device is recorded with the optical sensor. If the object is detected in the first recording within the first visible distance range, a distance between the detected object and the optical sensor is determined. A second coordinated control of the lighting device and the optical sensor and an assigned, second visible distance range are determined such that the object detected in the first recording is located in a center of the second visible distance range. A second recording of the second visible distance range while illuminated by the lighting device is recorded with the optical sensor by the second coordinated control.

Abstract: A driver assistance system for a motor vehicle is configured to receive or determine maximum assumptions about a course of a roadway; to determine a maximum left lane boundary and a maximum right lane boundary for a roadway in which the motor vehicle is located according to the maximum assumptions; to detect at least one object which is located between the maximum left lane boundary and the maximum right lane boundary; and to take the at least one object into account in the driver assistance.

Abstract: Described are techniques and systems for secure camera based IMU calibration for stationary systems, including vehicles. Existing vehicle camera systems are employed, with enhanced security to prevent malicious attempts by hackers to try and cause a vehicle to enter IMU calibration mode. IMU calibration occurs when a calibration system determines the vehicle is parked in a controlled environment; calibration targets are positioned at different viewing angles to vehicle cameras to act as sources of optical patterns of encoded data. Features of the patterns are for security as well as for alignment functionality. Images of the calibration targets enable inference of a vehicle coordinate system, from which calculations for IMU mounting error compensations are performed. A relative rotation between the IMU and the vehicle coordinate system are applied to IMU data to compensate for relative rotations between the vehicle and the IMU, thereby improving vehicle slope and bank metrics.

Abstract: An imaging apparatus provided in a moving object to capture an image of an area behind the moving object includes an imaging circuit and an optical system. The imaging circuit outputs an image based on an optical image input to a light-receiving surface. The optical system inputs the optical image to the imaging circuit. The optical system forms a first region at a first magnification and a second region at a second magnification lower than the first magnification. The second region is formed around the first region. The imaging apparatus is installed in the moving object so that, on the light-receiving surface of the imaging circuit, an axis passing through a center of the first region and extending in a direction from which the optical system receives light is inclined toward an upper side of the moving object with respect to a backward direction of the moving object.

Abstract: A system for driving a digital side mirror for vehicles, includes a moving case accommodating a camera for photographing the area surrounding the rear and the sides of a vehicle which is mounted in a housing and in a guide pipe mounted to a vehicle panel to be movable forwards and backwards thereof, wherein the camera accommodated in the moving case is controlled to photograph the area surrounding the rear and the sides of the vehicle even when the moving case is moved backwards and received in the housing and the guide pipe, facilitating a user to easily monitor the area surrounding the rear and the sides before turning on the vehicle or after turning off the vehicle.

Abstract: The present disclosure is directed to apparatuses, systems and methods for automatically classifying images of occupants inside a vehicle. More particularly, the present disclosure is directed to apparatuses, systems and methods for automatically classifying images of occupants inside a vehicle by comparing current image feature data to previously classified image features.

Abstract: The present disclosure relates to an image processing device, an image processing method, a program, and an image presentation system capable of presenting a more suitable image to the interior of a vehicle. An image processing unit generates a presentation image to be presented to the interior of a second vehicle that is traveling, on the basis of a vehicle external image obtained by capturing an environment outside a first vehicle that is traveling. The present disclosure can be applied to, for example, a projector type presentation device.

Abstract: A method includes obtaining multiple images of a scene using an imaging sensor associated with a vehicle, where the images of the scene capture lane marking lines associated with a traffic lane in which the vehicle is traveling. The method also includes identifying, in each of at least some of the images, a vanishing point based on the lane marking lines captured in the image. The method further includes identifying an average position of the vanishing points in the at least some of the images. In addition, the method includes determining one or more extrinsic calibration parameters of the imaging sensor based on the average position of the vanishing points. The one or more extrinsic calibration parameters of the imaging sensor may include a pitch angle and a yaw angle of the imaging sensor.

Abstract: An imaging device according to the present disclosure includes a front case, a rear case, and a shield member. The front case supports an imaging optical unit. The rear case includes an electrically conductive output mechanism configured to output a signal output from the imaging optical unit. The shield member electrically connects the front case and the output mechanism.

Abstract: An image capturing method has: providing an image capturing area on a display screen of a user device; providing an indication area in the image capturing area; identifying each license plate in the indication area; calculating a license plate area of said each license plate in the indication area; calculating a center point difference from a center point of said each license plate in the indication area to a center point of the indication area; marking a license plate that has a license plate area larger than half of a largest license plate area and has a smallest center point difference; and capturing an image including the marked license plate in the image capturing area.

Abstract: This disclosure provides systems, methods, and devices for wireless communication that support vehicle alerting, such as in autonomous driving networks. Vehicle alerting may provide messages alerting other vehicles and/or network components to instances of autonomous driving disengagement. A vehicle operating according to an autonomous vehicle (AV) mode may transmit an over-the-air message to one or more other devices, such as nodes of an autonomous driving network, to alert the one or more devices to the vehicle disengaging the AV mode. A device receiving an autonomous disengagement message may alter one or more autonomous operation aspects in response to the over-the-air message. Other aspects and features are also claimed and described.

Abstract: A control device includes circuitry configured to: generate, based on respective pieces of imaging data obtained by a plurality of imaging devices of a moving body, a three-dimensional image indicating a space including both the moving body and surroundings of the moving body; and cause a display device to display the generated three-dimensional image. The circuitry is capable of rotation of the space in the three-dimensional image, and the circuitry changes a rotation amount of the rotation, in a case where it is predicted that a boundary region of the respective pieces of imaging data in the three-dimensional image is present in a specific region when the rotation is stopped.

Abstract: A device for generating a front image for heavy equipment is presented, which is configured to generate a combined front image including an object in an area obstructed by a visual field obstructing component by combining an image of a preset area in a front image of a second view to a front image of a first view. The presented device for generating a front image for heavy equipment generates a first front image and a second front image by photographing the front from the upper portion and lower portion of the heavy equipment, and generates a combined front image by combining a part of the second front image to a partial area of the first front image, so that the areas thereof located at a set distance forward from the front end of the visual field obstructing component coincide with each other.

Abstract: Systems and methods are provided for verifying the accuracy of a map. Information regarding objects, such as roadway or roadway-related elements may be encoded into a map to be used for navigation and/or control of a vehicle, such as an autonomous vehicle. In order to verify that the map accurately reflects the roadway or roadway-related elements making up a section of roadway, the vehicle may be driven/ridden along the same section of roadway. A camera feed can be captured of this subsequent traversal of the section of roadway to check if the map includes the requisite roadway or roadway-related elements. The known roadway or roadway-related elements can be occluded from view in the camera feed. Accordingly, if any roadway or roadway-related elements do appear in the camera feed, they can be more easily detected by a verifier, and the processor verification is simplified.

Abstract: The present invention relates to methods and systems that utilize the production vehicles to develop new perception features related to new sensor hardware as well as new algorithms for existing sensors by using federated learning. To achieve this, the production vehicle's own worldview is post-processed and used as a reference, towards which the output of the software (SW) or hardware (HW) under development is compared. Through this comparison, a cost function can be calculated and an update of the SW parameters can be locally updated according to this cost function.

Abstract: An apparatus for estimating distance according to the present disclosure extracts feature maps from respective images including a reference image and a source image; projects a source feature map extracted from the source image onto hypothetical planes to generate a cost volume; sets sampling points on a ray extending from the viewpoint of the reference image in a direction corresponding to a target pixel in the reference image; interpolates features of the respective sampling points, using features associated with nearby coordinates; inputs the features corresponding to the respective sampling points into a classifier to calculate occupancy probabilities corresponding to the respective sampling points; and adds up products of the occupancy probabilities of the respective sampling points and the distances from the viewpoint of the reference image to the corresponding sampling points to estimate the distance from the viewpoint of the reference image to a surface of the object.

Abstract: A system and method for lateral vehicle detection is disclosed. A particular embodiment can be configured to: receive lateral image data from at least one laterally-facing camera associated with an autonomous vehicle; warp the lateral image data based on a line parallel to a side of the autonomous vehicle; perform object extraction on the warped lateral image data to identify extracted objects in the warped lateral image data; and apply bounding boxes around the extracted objects.