A time of flight (ToF) system includes a light source, a photosensor, a signal generator and a processor. The signal generator outputs a reference signal corresponding to a modulation function for modulated light and a modified transmitted light signal corresponding to a phase shift of the reference signal. The light source outputs the modified transmitted light signal and pixels in the photosensor receives its reflections off the scene. The reference signal is applied to the pixels and the processor determines a depth map for the scene based on values recorded by the pixels. In some examples, the phase shift is implemented using a phase locked loop controller. One or more component phases of the phase shift and an exposure time for each component phase are determined and output by the phase locked loop controller.

Aspects of the present disclosure involve systems, methods, and devices for fault detection in a Lidar system. A fault detection system obtains incoming Lidar data output by a Lidar system during operation of an AV system. The incoming Lidar data includes one or more data points corresponding to a fault detection target on an exterior of a vehicle of the AV system. The fault detection system accesses historical Lidar data that is based on data previously output by the Lidar system. The historical Lidar data corresponds to the fault detection target. The fault detection system performs a comparison of the incoming Lidar data with the historical Lidar data to identify any differences between the two sets of data. The fault detection system detects a fault condition occurring at the Lidar system based on the comparison.

A method for in-situ and real-time collection and processing of geometric parameters of railway lines, in a particular but non-limiting manner to those related to the height and stagger of the contact wire in electrified lines and the gauges to specific elements of the infrastructure in any line, generated based on static measurements starting from two-dimensional scenes perpendicular to the track axis, by determining the number of angular positions per scene, determining the minimum number of passes in each position, obtaining the raw coordinates, applying an averaging algorithm, applying offset corrections, transforming coordinates and applying either the steps to salve for height and stagger of the overhead contact line, or applying the steps to salve for gauges to specific elements of the infrastructure. An optimized, efficient and simple method is achieved which enables the real-time management and processing of the data obtained from the railway infrastructure.

The control unit 15 of the in-vehicle device 1 is configured to acquire point cloud data outputted by the lidar 2. Then, the control unit 15 is configured to associate, through matching between the acquired point cloud data and voxel data that is position information of an object for each of unit areas (voxels) into which a space is divided, measurement points constituting the point cloud data with voxels, respectively. The control unit 15 performs the position estimation of a moving body equipped with the lidar 2 based on the measurement points associated with any of the voxels which have corresponding voxel data VD and the position information of the object for the associated voxels. The control unit 15 calculates a reliability index of a position acquired by the position estimation based on a DAR that is a ratio of the number of the measurement points associated with any of the voxels to the number of the measurement points constituting the point cloud data.

A measurement control apparatus (10) according to the present disclosure includes: a detection unit (11) configured to detect an abnormal part of point group data acquired from a three-dimensional optical sensor; a control unit (12) configured to control the orientation of the three-dimensional optical sensor in accordance with the abnormal part detected by the detection unit (11); and a determination unit (13) configured to determine the case of the abnormality of the abnormal part detected by the detection unit (11) based on the point group data measured by the three-dimensional optical sensor in the orientation controlled by the control unit (12).

An orientation-position determining device is provided which is used for a sensor installed in a vehicle. The orientation-position determining device includes an imaging unit and an orientation-position detector. The imaging unit works to obtain a ranging image and an ambient light image from the sensor. The ranging image represents a distance to a target lying in a light emission region to which light is emitted from the sensor. The ambient light image represents an intensity of ambient light and has a resolution higher than that of the ranging image. The orientation-position detector works to use the ranging image and the ambient light image to detect an orientation and/or a position of the sensor.

A ballistic detection system includes a first camera; a second camera; a solar block device associated with at least one camera of the first and second cameras, wherein the solar block device is configured and arranged to block a solar disc in a field of view of the at least one camera; and a ballistics analysis computer configured to obtain image data captured by the first and second cameras, determine at least two points in three-dimensional space, which correspond to image artifacts of a projectile, using intrinsic and extrinsic parameters of the first and second cameras, define a trajectory of the projectile within a target volume using the at least two points in three-dimensional space, and find a point of intersection of the trajectory of the projectile with an object associated with the target volume.

The invention relates to a system and a method for simultaneous range and velocity measurement in an FMCW LiDAR system. A first light source (16) produces first light having a first frequency that varies according to a first chirp rate. A second light source (18) produces second light having a second frequency that is constant or that varies according to a second chirp rate being different from the first chirp rate. Measuring light obtained by combining the first and second light therefore has two different frequency components during a measurement interval. A splitter (22) separates the measuring light into reference light and output light, and a scanning unit (28) directs the output light towards an object (12) and receives input light that is obtained by reflection of the output light at the object (12). A detector (32) detects a superposition of the reference light and the input light. A computing unit (34) computes unambiguously the range and relative velocity by analyzing beat frequencies resulting from the superposition, wherein ambiguities due to Doppler frequency shifts are removed by performing a decision tree analysis.

An approach is provided for biasing machine learning models towards potential risks for controlling vehicles/robots. The approach involves, for example, determining an occluded space that is occluded in sensor data collected from one or more sensors of a vehicle or a robot. The approach also involves generating a sensor space completion that represents the occluded space based on biasing a generation of one or more potential risks to the vehicle or the robot originating from the occluded space. The approach further involves providing the sensor space completion to a system of the vehicle or the robot for generating a control decision, a warning, or a combination thereof.

Object identification may be provided herein. A feature extractor may extract a first set of visual features, extract a second set of visual features, concatenate the first set of visual features, the second set of visual features, and a set of bounding box information, determine a number of object features and a global feature for a scene, and receive ego-vehicle feature information associated with an ego-vehicle. An object classifier may receive the number of object features, the global feature, and the ego-vehicle feature information, generate relational features with respect to relationships between each of the number of objects from the scene, and classify each of the number of objects from the scene based on the number of object features, the relational features, the global feature, the ego-vehicle feature information, and an intention of the ego-vehicle.