An optical device is provided. The optical device includes a time-of-flight (TOF) sensor array, a photon conversion thin film, and a light source. The photon conversion thin film is disposed above the time-of-flight sensor array. The light source emits light with a first wavelength towards the photon conversion thin film to be converted into light with a second wavelength received by the time-of-flight sensor array. The second wavelength is longer than the first wavelength.

A presence detection system includes a presence detection field of an amusement park attraction, multiple transmitters, multiple receivers, and a controller. The multiple transmitters send multiple light beams of multiple wavelengths and the multiple receivers receive the multiple light beams of the multiple wavelengths. The controller receives input from the multiple transmitters and receivers and determines presence of an object in the presence detection field based on an interruption of the multiple light beams as indicated by the input. The controller also determines reflected light beams of the multiple wavelengths, absorbed light beams of the multiple wavelengths, or both, based on the input. The controller determines the object as a known object or an unknown object based at least in part on the reflected light beams, the absorbed light beams, or both.

An object recognition device includes a recognition unit and an object determination unit. The object determination unit includes a detection unit, an estimation unit, and a pseudo-determination unit. The estimation unit assumes that a shielding object is a vehicle and estimates a length of a side surface of the shielding object based on the width of the shielding object. The pseudo-determination unit determines whether a candidate object is a pseudo-object by using the length of the side surface. The pseudo-determination unit determines that the candidate object is the pseudo-object, if it is determined that transmission waves radiated in a direction in which the candidate object is located are reflected from the side surface and if another object is recognized at a location apart from a reflection point in a reflection direction by the same distance as a distance from the reflection point to the candidate object.

A CPU acquires a distance image or a visible light image obtained by imaging a marker for measuring an SID as an object to be imaged using a TOF camera or a visible light camera. In addition, the CPU derives a marker distance between the TOF camera or the visible light camera and the marker from an image of a marker region corresponding to the marker in the acquired distance image or visible light image. Further, the CPU derives the SID on the basis of the derived marker distance and information indicating a positional relationship between an acquisition unit and the marker.

A lane extraction method uses projection transformation of a 3D point cloud map, by which the amount of operations required to extract the coordinates of a lane is reduced by performing deep learning and lane extraction in a two-dimensional (2D) domain, and therefore, lane information is obtained in real time. In addition, black-and-white brightness, which is most important information for lane extraction on an image, is substituted by the reflection intensity of a light detection and ranging (LiDAR) sensor so that a deep learning model capable of accurately extracting a lane is provided. Therefore, reliability and competitiveness is enhanced in the field of autonomous driving, the field of road recognition, the field of lane recognition, and the field of HD road maps for autonomous driving, and the fields similar or related thereto, and more particularly, in the fields of road recognition and autonomous driving using LiDAR.

A method and an apparatus optimizes scan data obtained by sensors on vehicle, and corrects trajectory for a vehicle/robot based on the optimized scan data. The method for optimizing the scan data obtained by scanning environment elements, includes: step of obtaining the scan data, including obtaining at least two frames of scan data respectively corresponding to different timings; step of cluster processing, based on the characteristic of the data points, including classifying the plurality of data points in each frame of the scan data into one or more clusters; step of establishing correspondence, among the at least two frames of scan data, including searching and obtaining at least one set of clusters having correspondence; step of optimizing clusters, among the at least two frames of scan data, including conducting calculation to each set of the at least one set of clusters having correspondence, to obtain optimized clusters respectively corresponding to each set of the at least one set of clusters having correspondence; and step of optimizing the scan data, including accumulating all optimized clusters to obtain an optimized scan date for the at least two frames of scan data.

Provided is an object recognition device for performing object recognition on a field of view (FoV). The object recognition device includes a light detection and ranging (LiDAR) data acquisition module configured to acquire data for the FoV from a sensor configured to project the FoV with a laser and receive reflected light, and a control module configured to perform object recognition on an object of interest in the FoV using an artificial neural network, wherein the control module includes a region of interest extraction module configured to acquire region of interest data based on acquired intensity data for the FoV, and an object recognition module configured to acquire object recognition data using an artificial neural network, and recognize the object of interest for the FoV.

Systems and methods for object detection in a dusty environment can enhance the ability of autonomous machines to distinguish dust clouds from solid obstacles and proceed appropriately. A library of dust classifiers can be provided, where each dust classifier is separately trained to distinguish airborne dust from objects in the environment. Different dust classifiers can correspond to different categories of dusty environments. Based on current conditions, control logic in an autonomous machine can categorize its environment and select a corresponding dust classifier. The dust classifier output can be used to alter a behavior of the autonomous machine, including a behavior of the control logic. For instance, the control logic can apply a consistency check to the output of the dust classifier and an output of an AI-based object classifier to detect instances where the object classifier misidentifies dust as an object.

In a distance measurement device, a control unit performs a charge distribution process in which in a first period, charge generated in a charge generation region is transferred to a first charge storage region and, in a second period, the charge generated in the charge generation region is transferred to a second charge storage region. The control unit applies an electric potential to a first overflow gate electrode so that a potential energy of a region immediately below the first overflow gate electrode is lower than a potential energy of the charge generation region in the first period, and applies an electric potential to a second overflow gate electrode so that a potential energy of a region immediately below the second overflow gate electrode is lower than a potential energy of the charge generation region in the second period.

A method of foreign object debris discrimination includes illuminating a particle located within a sensing volume with a modulated electromagnetic radiation pulse emitted from a source; receiving one or more electromagnetic radiation return signals that have been scattered by the particle illuminated by the modulated electromagnetic radiation pulse at a detector; mixing, using a controller, the electromagnetic radiation return signal of amplitude I.sub.RS and frequency f.sub.RS with a reference signal of amplitude I.sub.LS and frequency f.sub.RS; analyzing, using the controller, an amplitude of the mixed signal √{square root over (I.sub.LSI.sub.RS)}, and frequency of the mixed signal, f.sub.RS−f.sub.LS; and classifying, using the controller, a particle position, a velocity, and electromagnetic characteristic of the particle based on the amplitude, √{square root over (I.sub.LSI.sub.RS)}, and frequency, f.sub.RS−f.sub.LS of the mixed signal.