A method for detecting at least one linear object in an input image is disclosed. The input image, and/or an extract of the input image, is fed to an image classifier, which classifies specified regions of the input image or extract in each case at least into relevant regions, the center of which lies in fairly close proximity to the center point of at least one linear object passing at least partially through this region, and background regions where this is not the case. For the relevant regions, coordinates are acquired from a regression which indicate at least one local course of the linear object in the relevant regions. From these coordinates, the course of the linear object is evaluated in the entire input image.

In various examples, high beam control for vehicles may be automated using a deep neural network (DNN) that processes sensor data received from vehicle sensors. The DNN may process the sensor data to output pixel-level semantic segmentation masks in order to differentiate actionable objects (e.g., vehicles with front or back lights lit, bicyclists, or pedestrians) from other objects (e.g., parked vehicles). Resulting segmentation masks output by the DNN(s), when combined with one or more post processing steps, may be used to generate masks for automated high beam on/off activation and/or dimming or shading—thereby providing additional illumination of an environment for the driver while controlling downstream effects of high beam glare for active vehicles.

A control unit for a vehicle is configured to detect a signalling installation ahead, wherein the signalling installation has at least one signal transmitter. The control unit is configured to ascertain digital map information indicating and/or allowing an association between the at least one signal transmitter and at least one possible direction of travel of the vehicle at the signalling installation. The control unit is further configured to operate a driving function of the vehicle on the basis of the digital map information.

Systems and corresponding methods are provided for moving object predictive locating, reporting, and alerting. An exemplary method includes receiving moving object data corresponding to a moving object; receiving sensor data from a sensor; merging the received moving object data and received sensor data into a set of merged data; and based thereon, automatically determining one or more of: a predicted location or range of locations for the moving object, a potential path of travel or area for the moving object, and a potential for interaction between the moving object and subject objects. The method can include automatically generating and providing alerts based on the determining. Alert can be configured for users having potential for interaction with the moving object. A method may include receiving sensor data from third parties, and provide information generated by the system pertaining to moving objects to other third parties.

A method is provided for watermarking a machine learning model used for object detection. In the method, a first subset of a labeled set of ML training samples is selected. Each of one or more objects in the first subset includes a class label. A pixel pattern is selected to use as a watermark in the first subset of images. The pixel pattern is made partially transparent. A target class label is selected. One or more objects of the first subset of images are relabeled with the target class label. In another embodiment, the class labels are removed from objects in the subset of images instead of relabeling them. Each of the first subset of images is overlaid with the partially transparent and scaled pixel pattern. The ML model is trained with the set of training images and the first subset of images to produce a trained and watermarked ML model.

A method of generating a context-rich parking event of a target vehicle taken by a patrol vehicle including obtaining a plate read event identifying an identifier of the target vehicle; initiating a collection of a first context image of a first view of the target vehicle; obtaining of geolocation information; obtaining temporal information; verifying if at least one condition is met by calculating if at least one of: a temporal constraint threshold is reached by using the temporal information; and a position constraint threshold is reached by using the geolocation information; initiating a collection by the patrol vehicle of a second context image of a second view of the target vehicle; and causing an association between the second context image and the plate read event to generate the context-rich parking event.

Embodiments of the present disclosure provide a method, a computer program product, and an arrangement (200) for object location information provisioning for autonomous vehicle (100) maneuvering. The method comprises receiving (S21) a request for object location information from at least one autonomous vehicle (100). The method comprises retrieving (S23) vulnerable road user, VRU, data, from a plurality of VRU data sources (104a-104n), wherein the VRU data comprises respective VRU locations in a pre-determined surrounding of the autonomous vehicle (100). Further, the method comprises determining (S25) the object location information based on the retrieved VRU data. Additionally, the method comprises periodically (S27) transmitting the determined object location information to the autonomous vehicle (100).

An image processing device includes a search processor and an image region setting unit. The search processor sets a plurality of processing regions in a frame image, and calculates a vehicle degree with respect to each of the processing regions. The vehicle degree is a degree of vehicle likeliness of an image in a relevant one of the processing regions. The image region setting unit performs, on the basis of corner coordinates of four corners of each of the processing regions, weighted average calculation weighted with the vehicle degree with respect to each of the processing regions, to calculate corner coordinates of four corners of a vehicle image region including an image of a target vehicle, in the frame image.

Disclosed herein are systems, methods, and computer program products for predicting movement of an object in a real-world environment. The methods comprise: obtaining a plurality of image frames captured in a sequence during a period of time; identifying first image frames of the plurality of image frames that contain an image of at least one object with one or more turn signals; analyzing the first image frames to obtain a classification for a pose of the at least one object; using the classification of the pose of the at least one object to further obtain a type classification for at least one of the turn signals and a state classification for a state of at least one of the turn signals; and predicting movement of the at least one object based at least on the type and state classifications obtained for at least one of the turn signals.

A vehicle gear control method includes acquiring a driving scene image while a vehicle is driving, and performing image recognition on the acquired driving scene image to obtain a driving scene label including at least one of a road attribute label, a traffic attribute label, or an environment attribute label. The method further includes acquiring driving status data and driving behavior data corresponding to the vehicle. The driving status data indicates at least one of vehicle speed and vehicle acceleration and the driving behavior data indicates at least one of a brake control input, an accelerator control input, or a throttle opening degree. The method further includes determining a gear shifting mode based on the driving status data, the driving behavior data, and the driving scene label. The gear shifting mode controls the vehicle to drive according to a corresponding gear at a corresponding gear shifting time.