This document describes techniques and systems for generating a fused object bounding box based on uncertainty. At least two bounding boxes, each associated with a different sensor, is generated. A fused center point and yaw angle as well as length, width, and velocity can be found by mixing the distributions of the parameters from each bounding box. A discrepancy between the center points of each bounding box can be used to determine whether to refine the fused bounding box (e.g., find an intersection between at least two bounding boxes) or consolidate the fused bounding box (e.g., find a union between at least two bounding boxes). This results in the fused bounding box having a confidence level of the uncertainty associated with the fused bounding box. In this manner, better estimations of the uncertainty of the fused bounding box may be achieved to improve tracking performance of a sensor fusion system.

A distance image generating device includes a light emitter that emits light pulses; a light receiver that includes light receiving elements and receives reflected light; a distance calculator that generates a distance image based on an amount of the reflected light; and a light amount adjuster that determines an emission count in accordance with which the light emitter is to emit the light pulses and an exposure count in accordance with which the light receiver is to receive the reflected light based on the distance image and causes the light emitter to emit the light pulses in accordance with the determined emission count and the light receiver to receive the reflected light in accordance with the determined exposure count. The distance calculator calculates the distance based on an amount of the reflected light received at the exposure count by the light receiver.

A ranging processing device includes: a four-phase ranging operation unit that performs an operation to calculate depth indicating a distance to an object by using all eight detection signals two of which are detected for each of irradiated light of first to fourth phases; a two-phase ranging operation unit that performs the operation to calculate the depth indicating the distance to the object by alternately using four detection signals based on the irradiated light of the first phase and the irradiated light of the second phase and four detection signals based on the irradiated light of the third phase and the irradiated light of the fourth phase among the eight detection signals; and a condition determination unit that makes condition determination based on the detection signals and switch between the four-phase ranging operation unit and the two-phase ranging operation unit to be used.

Disclosed are a depth image processing method, a depth image processing apparatus (10), and an electronic device (100). The depth image processing method is applied in the electronic device (100) including a depth image capturing apparatus (20) configured to capture an initial depth image. The depth image processing method includes: obtaining (01) target depth data for a number of regions of interest of the initial depth image; determining (02) whether the number of regions of interest is greater than a predetermined value; grouping (03), in response to the number of regions of interest being greater than the predetermined value, the number of regions of interest based on the target depth data to obtain a target depth of field; obtaining (04) a target blurring intensity based on the target depth of field; and blurring (05) the initial depth image based on the target blurring intensity to obtain a blurred depth image.

The present disclosure provides a method and an apparatus for creating an occupancy grid map, as well as a processing apparatus. The method includes: creating a current occupancy grid map based on a location of the vehicle and a previous occupancy grid map; and determining a current probability that each grid in the current occupancy grid map belongs to each of occupancy categories based on last environment perception information received from the sensors and updating an occupancy category to which each grid in the current occupancy grid map belongs based on the current probability that the grid belongs to each of the occupancy categories, in accordance with an asynchronous updating policy.

A system and method are provided for determining mistrack conditions in work vehicles such as excavators having first and second tracks. A controller uses data from onboard sensors (e.g., cameras, lidar) having an external field of view to detect a first position of, e.g., a track of the work vehicle relative to a first external point in a local reference system independent of a global reference system and to detect, upon the work vehicle having advanced from the detected first position a predetermined distance, a second position of the at least first component of the work vehicle relative to a second external point in the local reference system. The controller further determines an amount of mistrack error corresponding to a difference between the detected second position and an expected second position, and generates an output signal based on the determined amount of mistrack error.

Autonomously driven vehicles operate in rain, snow and other adverse weather conditions. An on-board vehicle sensor has a beam with a diameter that is only intermittently blocked by rain, snow, dust or other obscurant particles. This allows an obstacle detection processor is to tell the difference between obstacles, terrain variations and obscurant particles, thereby enabling the vehicle driving control unit to disregard the presence of obscurant particles along the route taken by the vehicle. The sensor may form part of a LADAR or RADAR system or a video camera. The obstacle detection processor may receive time-spaced frames divided into cells or pixels, whereby groups of connected cells or pixels and/or cells or pixels that persist over longer periods of time are interpreted to be obstacles or terrain variations. The system may further including an input for receiving weather-specific configuration parameters to adjust the operation of the obstacle detection processor.

A laser scanner and a system with a laser scanner for measuring an environment. The laser scanner includes an optical distance measuring device, a support, a beam steering unit rotatably fixed to the support which rotates around a beam axis of rotation. The beam steering unit includes a mirrored surface which deflects radiation used in the optical distance measurement and an angle encoder for recording angle data. The optical distance measurement is performed by a progressive rotation of the beam steering unit about the beam axis of rotation and the continuous emission of a distance measurement radiation, the emission being made through an outlet area arranged in the direction of the mirrored surface on the support, the receiving optics for receiving radiation are arranged on the support, and wherein the outlet area has a lateral offset with respect to the optical axis of the receiving optics.

A measuring device can have a scanning functionality for optical surveying of an environment, wherein the measuring device has a sensor comprising an assembly of microcells as a receiving surface and direction-dependent active sections of the receiver are defined depending on the transmission direction of the transmitted radiation, in order to adapt the active receiver surface to a varying imaging position of the received radiation.

An optical measuring device having a base for placing the measuring device and a targeting unit that is rotatable with respect to the base and defines a target axis for targeting a target object that is to be measured. The targeting unit has a first beam path for emitting optical measurement radiation in the direction of the target object that is to be measured. The targeting unit furthermore has a diffractive optical element (DOE), which is arranged or arrangeable in the beam path such that the optical measurement radiation is homogenized.