Aspects of the disclosure relate to training and using a phrase recognition model to identify phrases in images. As an example, a selected phrase list may include a plurality of phrases is received. Each phrase of the plurality of phrases includes text. An initial plurality of images may be received. A training image set may be selected from the initial plurality of images by identifying the phrase-containing images that include one or more phrases from the selected phrase list. Each given phrase-containing image of the training image set may be labeled with information identifying the one or more phrases from the selected phrase list included in the given phrase-containing images. The model may be trained based on the training image set such that the model is configured to, in response to receiving an input image, output data indicating whether a phrase of the plurality of phrases is included in the input image.

A computer implemented method for object detection includes the following steps carried out by computer hardware components: acquiring an image; determining a pixel of the image as a base pixel; determining coordinates of a plurality of sets of target pixels, each set of target pixels including a plurality of pixels in a respective pre-determined relationship to the base pixel; for each of the sets of target pixels, determining information representing values of the pixels in the respective set of target pixels; and determining whether a pre-determined object is shown in the image based on the determined information.

Systems and methods for situational behavior of an autonomous vehicle are disclosed. In one aspect, an autonomous vehicle includes at least one perception sensor configured to generate perception data indicative of at least one other vehicle on a roadway, a non-transitory computer readable medium, and a processor. The processor is configured to determine that the other vehicle is violating one or more rules of the roadway based on the perception data, tag the other vehicle as a non-compliant driver, and modify control of the autonomous vehicle in response to tagging the other vehicle as a non-compliant driver.

A list of images is received. The images were captured by a sensor of an ADV chronologically while driving through a driving environment. A first image of the images is identified that includes a first object in a first dimension (e.g., larger size) detected by an object detector using an object detection algorithm. In response to the detection of the first object, the images in the list are traversed backwardly in time from the first image to identify a second image that includes a second object in a second dimension (e.g., smaller size) based on a moving trail of the ADV represented by the list of images. The second object is then labeled or annotated in the second image equivalent to the first object in the first image. The list of images having the labeled second image can be utilized for subsequent object detection during autonomous driving.

An imaging system includes a light emitter that emits light toward the surroundings of a vehicle, an imager that captures an image of a range including a region that is illuminated with light emitted by the light emitter, and a difference image generator that generates (n−1) difference images from n captured images captured by the imager (n is an integer no smaller than 3). The difference image generator generates a difference image based on an image included in the n captured images and captured while the light emitter is on and an image included in the n captured images and captured while the light emitter is dimmed.

A method for detecting lost image information via a lighting device and an optical sensor. The lighting device and the optical sensor are controlled so as to be chronologically aligned with each other. A visible spacing region in an observation region of the optical sensor is determined from the chronological alignment of the control of the lighting device and the optical sensor. A recording of the observation region with the optical sensor is generated via the aligned control. Image information is identified in the recording in regions outside of the spacing region visible in the image, so as to make the identified image information accessible.

An autonomous vehicle (AV) includes features that allows the AV to comply with applicable regulations and statues for performing safe driving operation. Example embodiments disclosed herein provide enhanced high-precision operation of an AV in low-speed environments, such as a toll booth facility or heavy traffic. One example method disclosed herein includes a control computer identifying a starting point of the toll booth facility on the roadway and a plurality of toll lanes associated with the toll booth facility; selecting a particular toll lane; determining a trajectory for the AV that extends through the particular toll lane; and in response to the autonomous vehicle arriving at the starting point for the toll booth facility, transmitting, over a subsystem interface to one or more drive subsystems of the AV, instructions configured to cause the drive subsystems to operate together to cause the AV to travel according to the trajectory.

Systems and techniques are described for consuming data in an intelligent transport system. In some implementations, a system includes a display screen device and sensors. The sensors generates data describing sensor observations of a roadway at a first location and provides data describing the observations to the display screen device. The display screen device receives the data and determines an event and a type of the event. The display screen device displays second data indicative of the type of event, the second data being of a format that is consumable by a sensor on a vehicle traversing the roadway towards the first location, the sensor (i) located within a first resolution distance from the display screen device and (ii) located outside a second resolution distance of detecting the event, wherein the second data is used by an on-board processing system of the vehicle to adjust its driving behavior.

The present invention relates to the guidance of autonomous vehicles and in particular, relates to guiding an autonomous vehicle along a roadway by means of active devices with a system which works during normal and inclement, weather as well as under any luminous conditions, These active devices are embedded in the passive and/or active road details such as traffic signs, traffic lights, warning lights etc. These active devices provide data relating to road conditions, speed, road layout etc. as well as other information such as availability of parking spaces. Accordingly, through networks of sensors and devices the autonomous vehicle can obtain road details in real-time in any weather, illumination, visibility etc.

In an approach to safely facilitate driver responses to road traffic event alerts, computer-implemented methods, computer program products, and computer systems for reducing vehicle occupant distractions are described. The computer-implemented method includes processors configured for receiving vehicle alert data corresponding to a road traffic event, generating a user alert prompt corresponding to the vehicle alert data, transmitting the user alert prompt to a user vehicle satisfying a first condition, and receiving a user response from an occupant of the user vehicle. Responsive to receiving an affirmative user response, activating one or more vehicle activity systems to reduce vehicle cabin activity by occupants within the user vehicle.