A method of classifying an object according to an embodiment includes extracting a first feature by transforming rectangular coordinates of points included in the box of the object, obtained from a point cloud acquired using a LiDAR sensor, into complex coordinates and performing Fast Fourier Transform (FFT) on the complex coordinates, obtaining an average and a standard deviation as a second feature, the average and the standard deviation being parameters of a Gaussian model for the points included in the box of the object, and classifying the type of object based on at least one of the first feature or the second feature.

A method, apparatus and computer program product are provided to generate a model of one or more objects relative to a vehicle. In the context of a method, radar information is received in the form of in-phase quadrature (IQ) data and the IQ data is converted to one or more first range-doppler maps. The method further includes evaluating the one or more first range-doppler maps with a machine learning model to generate the model that captures the detection of the one or more objects relative to the vehicle. A corresponding apparatus and computer program product are also provided.

A sensor calibration method and apparatus, and a storage medium are provided. In the method, multiple scene images and multiple first point clouds of a target scene are acquired by an image sensor and a radar sensor. A second point cloud of the target scene is constructed according to the multiple scene images. A first distance error between the image sensor and radar sensor is determined according to first feature point sets and a second feature point set. A second distance error of the radar sensor is determined according to multiple first feature point sets. A reprojection error of the image sensor is determined according to a first global position of the second feature point set in the global coordinate system and first image positions of pixel points corresponding to the second feature point set in the scene image. The radar sensor and image sensor are calibrated.

A method and system of operating a vehicle includes a first sensor generating first sensor data for an object comprising a first bounding box from a first sensor. The first sensor data comprising a first confidence score. A second sensor generates second sensor data for the object comprising a second bounding box from a second sensor different than the second sensor. The second sensor data comprises a second confidence score. A bounding box circuit is programmed to generate a third confidence score for the object based on the first sensor data and the second sensor data and utilize the first sensor data, the second sensor data and the third confidence score to control operation of a vehicle system.

A flight control system for a rotary-wing aircraft includes a shape sensor and a controller. The shape sensor is configured to measure a shape of a rotor blade during movement of the rotor blade. The controller is communicably coupled to the shape sensor and is configured to (i) receive, from the shape sensor, a first signal indicative of a first blade shape; (ii) receive a blade characteristic regarding the rotor blade; and (iii) determine at least one of a moment or force associated with the rotor blade based on the first signal and the blade characteristic.

A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Systems and methods described herein relate to reducing Light Detection and Ranging (LIDAR) target broadening. One embodiment acquires a frame including a plurality of points; identifies a first set of points for which the energy returned to a detector exceeds a predetermined energy threshold; identifies a second set of points adjacent to the first set of points that has a range differing from that of the first set of points by less than a predetermined range threshold; defines, as a border, an outline of the second set of points; iteratively reduces laser power for the first set of points, acquires a new frame, identifies the second set of points, and defines as the border, the outline of the second set of points until the border converges to a stable size; and outputs an estimated size of an object based, at least in part, on the stable size of the border.

An imaging system comprising circuitry configured to obtain (S2) image data of a scene that is illuminated with patterned light (PL), determine (S5, S6) bright regions and dark regions based on the image data, and relate image information related to the bright regions to image information related to the dark regions in order to determine characteristics of atmospheric aerosol particles (AP).

A target recognition device includes a target recognition unit, a tracking unit, a target registration unit, a condition determination unit, and a registration requirement setting unit. The condition determination unit determines whether a target satisfies predetermined conditions J1 to J3. The registration requirement setting unit sets a requirement for registering a target by the target registration unit to be stricter for the target determined to satisfy all of the conditions J1 to J3 than for the target determined to satisfy not all of the conditions J1 to J3.

The disclosed technology provides solutions for improving object classification using machine-learning techniques. In particular, solutions for improving detection/classification in rare-event scenarios are provided. In some approaches, a process of the invention can include steps for: receiving road data, wherein the road data comprises sensor data associated with a driving scene, receiving object data from an object database, and inserting a virtual object, at a first location, within the driving scene, wherein the virtual object is based on the object data. In some aspects, the process can further include steps for performing an object identification process to classify the virtual object at the first location in the driving scene. Systems and machine-readable media are also provided.