An object recognition device 80 includes a scene determination unit 81, a learning-model selection unit 82, and an object recognition unit 83. The scene determination unit 81 determines, based on information obtained during driving of a vehicle, a scene of the vehicle. The learning-model selection unit 82 selects, in accordance with the determined scene, a learning model to be used for object recognition from two or more learning models. The object recognition unit 83 recognizes, using the selected learning model, an object in an image to be photographed during driving of the vehicle.

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.

Methods, devices, and computer-readable media for generating color-neutral representations of driving objects are disclosed. In one embodiment, a method is disclosed comprising capturing an image, the image including an object of interest; identifying the object of interest in the image based on identifying one or more colors in the image; associating the object of interest with a known traffic object; identifying a color-neutral representation of the known traffic object; and displaying the color-neutral representation to a user.

The present disclosure relates to systems and methods for aligning navigation information from a plurality of vehicles. In one implementation, at least one processing device may receive first navigational information from a first vehicle and second navigational information from a second vehicle. The first and second navigational information may be associated with a road segment. The processor may divide the first navigational information into at least a first portion and a second portion; divide the second navigational information into at least a first portion and a second portion; align the first portion of the first navigational information with the first portion of the second navigational information; align the second portion of the first navigational information with the second portion of the second navigational information; generate a road model based on the aligned portions; and send the road model to vehicles for use in navigating along the road segment.

Systems, methods, computer-readable media, techniques, and methodologies are disclosed for performing end-to-end, learning-based keypoint detection and association. A scene graph of a signalized intersection is constructed from an input image of the intersection. The scene graph includes detected keypoints and linkages identified between the keypoints. The scene graph can be used along with a vehicle's localization information to identify which keypoint that represents a traffic signal is associated with the vehicle's current travel lane. An appropriate vehicle action may then be determined based on a transition state of the traffic signal keypoint and trajectory information for the vehicle. A control signal indicative of this vehicle action may then be output to cause an autonomous vehicle, for example, to implement the appropriate vehicle action.

Systems and methods for determining whether a vehicle is driving in an unsafe or unsatisfactory manner are disclosed. In some implementations, a system may determine one or more driving scores for a vehicle based on observations of a driving behavior of the vehicle during a time period. The system may generate an indication of unsatisfactory driving based on at least one of the one or more driving scores exceeding a threshold value. The system may provide the indication of unsatisfactory driving to one or more entities. In some aspects, the system may identify one or more dangerous driving attributes exhibited by the vehicle during the time period based on the observations received from the one or more devices. The system may also generate the indication of unsatisfactory driving based at least in part on the identified dangerous driving attributes.

A processor of a remote facility executes image generation processing to generate assistance image data to be displayed on a display based on front image data indicating front image data of a vehicle. In the image generation processing, when an image of a traffic light is included in the front image data, it is determined whether recognition likelihood of a luminescent state of a light emitting section of the traffic light is equal to or smaller than a threshold. If it is determined that recognition likelihood is less than or equal to the threshold, super-resolution processing of a preset region including the traffic light in the front image data is executed. Then, super-resolution image data of the preset region by the super-resolution processing is superimposed on a region corresponding to the preset region in the front image data. As such, the assistance image data is generated.

A device and a method for recording a drive video of a vehicle may include a camera configured for filming a front video, a rear video, and a rear-side video of the vehicle, and a controller that detects the dangerous situation of the vehicle based on the rear-side video filmed by the camera, and records the front video, the rear video, and the rear-side video of the vehicle filmed by the camera as an event video in storage in the detected dangerous situation.

Systems and methods for assisting navigation of a vehicle are disclosed. In one embodiment, a method of assisting navigation of a vehicle includes receiving navigational data relating to an intended route of the vehicle, receiving object data relating to at least one external object detected within a vicinity of a current position of the vehicle, determining whether the at least one external object affects an ability of the vehicle to proceed along the intended route, and generating at least one instruction relating to the ability of the vehicle to proceed along the intended route.

A map in a cloud service stores physical objects previously detected by other vehicles that have previously traveled over the same road that a current vehicle is presently traveling on. New data received by the cloud service from the current vehicle regarding new objects that are being encountered by the current vehicle can be compared to the previous object data stored in the map. Based on this comparison, an operating status of the current vehicle is determined. In response to determining the status, an action such as terminating an autonomous navigation mode of the current vehicle is performed.