An interactive vehicle safety system having capabilities to improve peripheral vision, provide warning, and improve reaction time for operators of vehicles. For example, the interactive vehicle safety system may have capabilities for portraying objects, which are being blocked by any of the structural pillars and/or mirrors of a vehicle (such as a truck, van, train, etc.). The interactive vehicle safety system disclosed may comprise one or more image capturing devices (such as camera, sensor, laser), distance and object sensors (such as ultrasonic sensor, LIDAR radar sensor, photoelectric sensor, and infrared sensor), a real-time image processing of an object, and one or more display systems (such as LCD or LED displays). The interactive vehicle safety system may give a seamless 360-degree front panoramic view to a driver.

Techniques described herein relate to using head detection to improve pedestrian detection. In an example, a head can be detected in sensor data received from a sensor associated with a vehicle using a machine learned model. Based at least partly on detecting the head in the sensor data, a pedestrian can be determined to be present in an environment within which the vehicle is positioned. In an example, an indication of the pedestrian can be provided to at least one system of the vehicle, for instance, for use by the at least one system to make a determination associated with controlling the vehicle.

Methods and systems for jointly estimating a pose and a shape of an object perceived by an autonomous vehicle are described. The system includes data and program code collectively defining a neural network which has been trained to jointly estimate a pose and a shape of a plurality of objects from incomplete point cloud data. The neural network includes a trained shared encoder neural network, a trained pose decoder neural network, and a trained shape decoder neural network. The method includes receiving an incomplete point cloud representation of an object, inputting the point cloud data into the trained shared encoder, outputting a code representative of the point cloud data. The method also includes generating an estimated pose and shape of the object based on the code. The pose includes at least a heading or a translation and the shape includes a denser point cloud representation of the object.

A method for determining a safe state for a vehicle includes disposing a camera at a vehicle and disposing an electronic control unit (ECU) at the vehicle. Frames of image data are captured by the camera and provided to the ECU. An image processor of the ECU processes frames of image data captured by the camera. A condition is determined via processing at the image processor of the ECU frames of image data captured by the camera. The condition includes a shadow present in the field of view of the camera within ten frames of image data captured by the camera or a damaged condition of the imager within two minutes of operation of the camera. The ECU determines a safe state for the vehicle responsive to determining the condition.

A method for determining the posture of a driver of a vehicle. The vehicle includes a camera capable of generating a sequence of images of the position of the driver of the vehicle and an electronic control unit including a memory zone, in which a plurality of image processing masks is recorded, with each mask being associated with a predetermined posture of the driver in their seat. The method includes the camera generating a sequence of images of the position of the driver and sending the sequence of images to the electronic control unit, computing, by the electronic control unit, for each mask of the plurality of masks, the convolution product of the mask with at least one image of the sequence of images received from the camera in order to obtain a correlation coefficient, and determining the posture of the driver from the mask with the highest correlation coefficient.

A computer-implemented method comprises receiving, by an image processing system, a depth image captured by a stereo camera on an unmanned aerial vehicle (UAV). One or more pixels of the depth image are associated with corresponding depth values indicative of distances of one or more objects to the stereo camera. The image processing system determines that one or more pixels of the depth image are associated with invalid depth values. The image processing system infers, based on a distribution of the one or more pixels of the depth image that are associated with invalid depth values, a presence of a potential obstacle in an environment of the UAV. The UAV is controlled based on the inferred presence of the potential obstacle.

A method includes capturing, by a sensor on an unmanned aerial vehicle (UAV), an image of a delivery location. The method also includes determining, based on the image of the delivery location, a segmentation image. The segmentation image segments the delivery location into a plurality of pixel areas with corresponding semantic classifications. The method additionally includes determining, based on the segmentation image, a percentage of obstacle pixels within a surrounding area of a delivery point at the delivery location, wherein each obstacle pixel has a semantic classification indicative of an obstacle in the delivery location. The method further includes based on the percentage of obstacle pixels being above a threshold percentage, aborting a delivery process of the UAV.

An apparatus of controlling a vehicle and a method for controlling the same includes a camera, a processor operatively connected to the camera, and a storage operatively connected to the processor to store instructions executed by the processor. The processor obtains an image of a surrounding of a door of the vehicle, which is captured through the camera, obtains depth information from the obtained image, transforms the depth information into three dimensional (3D) point information, determines collision possibility of the door with an obstacle, based on distribution of the 3D point information to determine collision possibility, and warns the collision of the door when the collision possibility is present, when executing the instructions.

A moving body support system supports a moving body that recognizes a marker arranged in a predetermined area. The moving body support system estimates brightness at a position of the marker in the predetermined area without using an image captured by a camera mounted on the moving body. The moving body support system calculates a luminance correction value of an image including the marker according to the brightness at the position of the marker. The moving body support system acquires a first image including a target marker around the moving body by using the camera. The moving body support system generates a second image by correcting luminance of the first image by using the luminance correction value for the target marker. Then, the moving body support system recognizes the target marker based on the second image.

Systems and methods are disclosed for identifying landmarks. A method for identifying a landmark may include initiating identification of a landmark based on one or more images from a camera, for use in autonomous vehicle navigation, the landmark including a traffic sign; initiating updating a road model with a location of the landmark; and initiating distribution of the road model with the location of the traffic sign to a plurality of autonomous vehicles.