A method for detecting at least one intersection point of road marking lines, wherein a computing unit of a transportation vehicle receives a camera image and identifies a first road marking line based on the camera image. Using the computing unit, a search region is automatically defined in an environment of the first road marking line, and an automatic search limited to the search region is performed. At least one intersection point of the first road marking line with at least a second road marking line is identified as the result of the search.

A distortion correction component of a mobile device receives an image of a spread open multi-page document, determines a binding edge line of the spread open multi-page document, determines a first set of substantially vertical straight lines lying left of the binding edge line and a second set of substantially vertical straight lines lying right of the binding edge line. The distortion correction component then determines a first vanishing point based on the first set of substantially vertical straight lines and a second vanishing point based on the second set of substantially vertical straight lines. A first quadrangle is determined based on the first vanishing point and a second quadrangle is determined based on the second vanishing point. A corrected image for the first page is generated based on the first quadrangle and a corrected image for the second page is generated based on the second quadrangle.

An image processing apparatus and related method. The apparatus (PP) comprises an input port (IN), a classifier (CLS) and an output port (OUT). The input port is capable of receiving an image of an object acquired at a field of view (FoV) by an imager (USP). The image records a pose of the object corresponding to the imager's field of view (FoV). The classifier (CLA) is configured to use a geometric model of the object to determine, from a collection of pre-defined candidate poses, the pose of the object as recorded in the image. The output port (OUT) is configured to output pose parameters descriptive of the determined pose.

Systems, methods, models, and training data for models are discussed, for determining vehicle positioning, and in particular identifying tailgating. Simulated training images showing vehicles following other vehicles, under various conditions, are generated using a virtual environment. Models are trained to determine following distance between two vehicles. Trained models are used in detection of tailgating, based on determined distance between two vehicles. Results of tailgating are output to warn a driver, or to provide a report on driver behavior. Following distance over time is determined, and simplified following distance data is generated for use at a management device.

A method for correlating at least part of a candidate image (Ican) with at least one reference image, includes the following steps: a) implementing a relational repository (R) comprising at least: an ordered list of relational descriptors, at least one computing mode to be applied to the images in order to determine descriptors of these images, and a mode for determining the degree of similarity between two descriptors, b) implementing, for each reference image, a reference list that comprises the positions, referred to as reference points of interest, in the reference image, of descriptors of the reference image that are similar to relational descriptors from a relational repository compatible with the relational repository implemented in step a), which reference list is ordered on the basis of the order of this compatible relational repository, c) determining, in the candidate image, descriptors of the candidate image that are computed in line with each descriptor computing mode of the relational repository implemented in step a), and determining the position of each of these descriptors in the candidate image, d) determining the degree of similarity, determined in line with the determination mode of the relational repository implemented in step a), between each descriptor of the candidate image and each relational descriptor of the relational repository implemented in step a), e) determining a candidate list that comprises the positions, referred to as candidate points of interest, in the candidate image, of the descriptors of the candidate image exhibiting the greatest similarity with the relational descriptors of the relational repository implemented in step a), which candidate list is ordered on the basis of the order of this relational repository, f) processing the candidate list with respect to each reference list on the basis of the order of the candidate and reference lists.

An example device is described for facilitating polygon localization. In various aspects, the device can comprise a processor. In various instances, the device can comprise a non-transitory machine-readable memory that can store machine-readable instructions. In various cases, the processor can execute the machine-readable instructions, which can cause the processor to localize a polygon depicted in an image, based on execution of a deep learning pipeline. In various aspects, the deep learning pipeline can comprise a circular-softmax block.

Systems, methods, models, and training data for models are discussed, for determining vehicle positioning, and in particular identifying tailgating. Simulated training images showing vehicles following other vehicles, under various conditions, are generated using a virtual environment. Models are trained to determine following distance between two vehicles. Trained models are used in detection of tailgating, based on determined distance between two vehicles. Results of tailgating are output to warn a driver, or to provide a report on driver behavior. Following distance over time is determined, and simplified following distance data is generated for use at a management device.

A multi-source image correspondence method and system based on heterogeneous model fitting is provided, the method includes the following steps: constructing a multi-orientation phase consistency model, fusing phase consistency, image amplitude, and orientation detection feature points, constructing logarithmic polar coordinate descriptors with variable-size bins using sub-region grids and orientation histograms, effectively estimating model parameters through heterogeneous model fitting, accumulating matching pairs from different heterogeneous models that meet a preset joint position offset transformation error, outputting a final matching pair, and completing multi-source image correspondence. The present disclosure alleviate the influence of nonlinear radiation distortion by constructing the multi-orientation phase consistency model, constructing logarithmic polar coordinate descriptors with variable-size bins by sub-region grids and orientation histograms, removing an abnormal matching relationship in multi-source images with the heterogeneous model fitting method, thereby improving the accuracy and robustness of feature detection and improving multi-source image correspondence performance.

The image processing device counts the number of lane marking feature points. The image processing device determines whether the count number of the lane marking feature points is equal to or greater than a first threshold. The image processing device arranges the setting to use the lane marking feature points in the lane marking detection process when the count number of the lane marking feature points is equal to or greater than the first threshold. On the other hand, the image processing device counts the number of Botts' Dot feature points when the count number of the lane marking feature points is smaller than the first threshold. The image processing device arranges the setting to use the Botts' Dot feature points in the lane marking detection process when the count number of the Botts' Dot feature points is equal to or greater than the second threshold.

An object detection device that detects a specific object included in an input image includes a first candidate region specifying unit that specifies a first candidate region in which an object candidate is included from a first input image obtained by imaging a subject in a first posture, a second candidate region specifying unit that specifies a second candidate region in which an object candidate is included from a second input image obtained by imaging the subject in a second posture different from the first posture, a deformation displacement field generation unit that generates a deformation displacement field between the first input image and the second input image, a coordinate transformation unit that transforms a coordinate of the second candidate region to a coordinate of the first posture based on the deformation displacement field, an association unit that associates the first candidate region with the transformed second candidate region that is close to the first candidate region, and a same object determination unit that determines that the object candidates included in the candidate regions associated with each other by the association unit are the same object and are the specific object.