A change point detection device includes a memory 170 that stores map information representing a structure associated with a traveling condition on and around a road, an object detection unit 162 that detects a shielding object 20 hiding the structure from an image acquired by an in-vehicle camera 110 mounted on a vehicle 100 and representing an environment around the vehicle 100, a collation unit 163 that eliminates the structure hidden by the shielding object 20 in the map information, collates the image with the map information, and calculates a coincidence degree between the image and the map information, and a change point detection unit 164 that determines, when the coincidence degree is less than or equal to a predetermined threshold value, that the structure represented in the image has a change point different from the corresponding structure represented in the map information.

In one embodiment, a perception module of an autonomous driving vehicle (ADV) detects a temporary traffic control device (TTCD) located within a first lane of a multi-lane roadway. The first lane is added to a black list of one or more lanes that the ADV is not permitted to drive within. A rerouting request is made to a planning module of the ADV to route the ADV to a second lane in the multi-lane roadway. The ADV navigates to the second lane and continues navigating along the requested rerouting. The ADV monitors for additional TTCDs. One or more boundary lines of the first lane can be marked “do not cross” so that the ADV does not navigate, even partially, back into the first lane. If there are no more TTCDs in the first lane for a predetermined distance ahead of the ADV, the first lane is deleted from the black list.

An image processing device for generating learning data that is used for machine learning includes a processor that obtains image data. The processor specifies an unprocessable region that is a region in which a predetermined process cannot be performed or a region in which the predetermined process is not performed in an image region of the image data, and generates image data on which the predetermined process is performed in a region except the unprocessable region in the image region, as the learning data.

An image processing device has a function for plotting a luminance gradient co-occurrence pair of an image on a feature plane and applying an EM algorithm to form a GMM. The device learns a pedestrian image and creates a GMM, subsequently learns a background image and creates a GMM, and calculates a difference between the two and generates a GMM for relearning based on the calculation. The device plots a sample that conforms to the GMM for relearning on the feature plane by applying an inverse function theorem. The device forms a GMM that represents the distribution of samples at a designated mixed number and thereby forms a standard GMM that serves as a standard for image recognition. When this mixed number is set to less than a mixed number designated earlier, the dimensions with which an image is analyzed are reduced, making it possible to reduce calculation costs.

A vehicle sensor training system includes a first computing device configured to receive dynamics data from a host vehicle. A receiving device is configured to receive real time object identification data from a reference target. A second computing device is configured to compile the dynamics data from the first computing device and the real-time object identification data from the receiving device. The second computing device is configured to train a vehicle sensor with the real-time object identification data.

A lighting ECU determines whether or not a road sign relating to an urban area or a residential area is detected, while it is performing an automatic high beam control. When the detected road sign is a road sign indicating a start point of the urban area or of the residential area, the lighting ECU terminates the automatic high beam control, and maintain a light distribution pattern to a pattern corresponding to low beam. The lighting ECU restarts the automatic high beam control, when the detected road sign is a road sign indicating an end point of the urban area or of the residential area.

Systems and methods for lane marking and road sign recognition are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes one or more road scenes having lane markings and road signs. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

A method of road sign classification utilizing a knowledge graph, including detecting and selecting a representation of a sign across a plurality of frames, outputting a prompt initiating a request for a classification associated with the representation of the sign, classifying one or more images including the sign, querying the knowledge graph to obtain a plurality of road sign classes with at least one same attribute as the sign, and classifying the sign across the plurality of frames in response to a confidence level exceeding a threshold.

An apparatus, method and computer program product are provided for determining a state of visibility of a road object, such as a road sign, using vehicle sensor data. For example, the apparatus determines whether one or more sensors of a first vehicle observes a road sign. If the road sign is not observed by the one or more sensors, the apparatus determines whether one or more second vehicles is obscuring the road sign. If the one or more second vehicles is not obscuring the road sign, the apparatus determines whether the road sign is obscured due to a weather condition. If the road sign is obscured due to the weather condition, the apparatus generates a signal indicating that the road sign was obscured due to the weather condition.

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 of image data captured by the camera. Responsive at least in part to processing of captured image data, speed of the vehicle is controlled by an adaptive cruise control system of the vehicle. Upon approach of the vehicle to a curve in the road along which the vehicle is traveling, speed of the vehicle is reduced by the adaptive cruise control system to a reduced speed for traveling around the curve in the road. Speed of the vehicle is increased by the adaptive cruise control system when the vehicle is traveling along a straighter section of road after the curve in the road.