Abstract: We disclose adaptive active safety systems which utilize a sensing system to detect road conditions and actuate an active safety routine based thereon. One disclosed method includes transmitting, with a multispectral LIDAR system on a vehicle, a multispectral light beam directed at an anticipated region of travel of the vehicle within a road, and analyzing a response, of a photodetector, to a return of the multispectral light beam. The method also includes determining, based on the analyzing of the response, a hazardous surface condition in the anticipated region of travel of the vehicle, and actuating, based on the determination of the hazardous surface condition, an active safety routine. The method can be executed by an ADAS in which the determinations of the hazardous surface conditions on the road in the anticipated region of travel are executed in real time to thereby produce a road aware ADAS.

Abstract: Disclosed is a method and a system for retrieving a location of a base point of a wheeled vehicle in a local coordinate system of a tridimensional sensor mounted on the vehicle. The method includes acquiring point cloud frames while the wheeled vehicle is moving along a straight path and a curved path and a point cloud representative of a portion of the vehicle, computing a main direction vector, a main direction line and a location of an instantaneous centre of rotation of the wheeled vehicle in the local coordinate system, and retrieving the location of the base point.

Abstract: A method for detecting intrusions in a monitored volume in which: N tridimensional sensors acquire local point clouds in respective local coordinate systems, a central processing unit receives the acquired local point clouds and, for each sensor, computes updated tridimensional position and orientation of the sensor in a global coordinate system of the monitored volume by aligning a local point cloud acquired by said tridimensional sensor with a global tridimensional map of the monitored volume, and generates an aligned local point cloud on the basis of the updated tridimensional position and orientation of the sensor, the central processing unit monitors an intrusion in the monitored volume by comparing a free space of the aligned local point cloud with a free space of the global tridimensional map.

Abstract: A method and a system for dynamically generating and updating a global tridimensional map of an environment surrounding one or several moving vehicles on which N tridimensional sensors are mounted and communicates with a central processing unit. Each sensor generates a continuous stream of point cloud frames, in parallel and asynchronously with the other sensors, the point cloud frames are representative of object surfaces located in a local volume of the environment surrounding each sensor. The central processing unit continuously receives the continuous streams from the sensors, store them in a memory and, for each newly received point cloud frame of each stream, generates or updates a global cumulated tridimensional map of the environment of the at least one vehicle by determining an aligned point cloud frame in a global coordinate system of the environment, and updating the global cumulated tridimensional map by merging the aligned point cloud frame.

Abstract: The invention belongs to motion detection and three-dimensional image analysis technology fields. It can be applied to movement detection or intrusion detection in the surveillance of monitored volumes or monitored spaces. It can also be applied to obstacle detection or obstacle avoidance for self-driving, semi-autonomous vehicles, safety systems and ADAS. A three-dimensional imaging system stores 3D surface points and free space locations calculated from line of sight data. The 3D surface points typically represent reflective surfaces detected by a sensor such as a LiDAR, a radar, a depth sensor or stereoscopic cameras. By using free space information, the system can unambiguously derive a movement or an intrusion the first time a surface is detected at a particular coordinate. Motion detection can be performed using a single frame or a single 3D point that was previously a free space location.

Abstract: We disclose systems and methods for object tracking which utilize a spectral response and a geometric aspect of a set of points. One method includes transmitting, with a multispectral lidar system, a multispectral light beam and analyzing a response, of a photodetector, to a return of the beam. The method also includes generating a point cloud with a set of points and determining a set of spectral responses of the set of points based on the analyzing of the response. The method also includes determining a set of material compositions for the set of points based on the set of spectral responses of the set of points. The method also includes grouping points in the set of points into groups based on both the set of material compositions and a geometric aspect of the set of points and creating one or more tracking object definitions using the groups.

Abstract: A method and apparatus of performing object detection on a path of travel is described. The invention is also related to obstacle detection on railway tracks. Object detection over irregular surfaces or traveling over know paths is also provided. The invention can be applied to railways for obstacle detection on train tracks with a look-ahead sensor system such as a lidar and/or camera system. The object detection may involve the use of multispectral lidar and material identification as well as artificial intelligence for object identification. A reference map is created during a first pass through a virtual tunnel of travel. A vehicle travelling through the tunnel of travel the vehicle will register with reference map and use differences between scans and the reference map to perform object detection. Responses are performed based on the object detection or object identification.

Abstract: A method, system, and computer program product is provided for automatically configuring a detection device. The method includes scanning, with a LiDAR device, a region to generate LiDAR data, analyzing the LiDAR data to determine a material classification for the region, determining a zone of interest within the region based on the material classification, the zone of interest comprising a subset of the region defined by a spatial boundary, monitoring the zone of interest with the detection device, identifying an event occurring within the spatial boundary of the zone of interest based on monitoring the region with the detection device, and in response to identifying the event occurring within the spatial boundary, automatically initiating at least one responsive action.

Abstract: We disclose systems and methods for object tracking which utilize a spectral response and a geometric aspect of a set of points. One method includes transmitting, with a multispectral lidar system, a multispectral light beam and analyzing a response, of a photodetector, to a return of the beam. The method also includes generating a point cloud with a set of points and determining a set of spectral responses of the set of points based on the analyzing of the response. The method also includes determining a set of material compositions for the set of points based on the set of spectral responses of the set of points. The method also includes grouping points in the set of points into groups based on both the set of material compositions and a geometric aspect of the set of points and creating one or more tracking object definitions using the groups.

Abstract: A continuous-wave frequency-modulated (FMCW) LiDAR system comprises: a laser cavity around a solid gain medium; an optical source configured to optically pump the solid gain medium at a power that determines a relaxation oscillation frequency; a structure configured to apply force to the solid gain medium associated with a mechanical resonance frequency, wherein the relaxation oscillation frequency is equal to the mechanical resonance frequency within a factor of 5; an optical arrangement configured to transmit at least one optical beam from the laser cavity towards a target, and to couple into the laser cavity a received optical signal comprising at least a portion of the optical beam reflected from the target; and circuitry configured to determine at least one of an estimated distance to the target or a speed of motion of the target based at least in part on a signal from the laser cavity.

Abstract: A method for detecting intrusions in a monitored volume in which: N tridimensional sensors acquire local point clouds in respective local coordinate systems, a central processing unit receives the acquired local point clouds and, for each sensor, computes updated tridimensional position and orientation of the sensor in a global coordinate system of the monitored volume by aligning a local point cloud acquired by said tridimensional sensor with a global tridimensional map of the monitored volume, and generates an aligned local point cloud on the basis of the updated tridimensional position and orientation of the sensor, the central processing unit monitors an intrusion in the monitored volume by comparing a free space of the aligned local point cloud with a free space of the global tridimensional map.

Abstract: A method for identifying a composition material of an object located in an environment surrounding at least one device, in which at least one sensor is mounted on the device and communicates with at least one central processing unit.

Abstract: A scanning device for laser detection and ranging (LiDAR), the scanning device includes, arranged in optical free space: an optical input for receiving a pulsed broadband laser beam having a linear polarization; a separating unit configured for transmitting the laser beam along a scanning optical path while changing the polarization into a circular one; a wavelength selection unit; and a scanning unit. The separating unit is configured for deviating the reflections (4) on a broadband detector while changing the orthogonal circular polarization into an orthogonal linear polarization compared to the linear polarization of the laser beam. The broadband detector is configured to receive the deviated reflections, and to detect a time-of-flight and an optical power of the light reflection.

Abstract: A method for identifying a composition material of an object located in an environment surrounding at least one device, the object moving relative to the device, in which at least one sensor is mounted on the device and communicates with at least one central processing unit.

Abstract: We disclose sensor systems, and associated calibration systems and methods, that provide efficient and reliable depth and texture fusion. One disclosed method includes transmitting a first light beam from a first perspective, transmitting a second light beam from a second perspective, aligning a visible light photodetector with the second perspective, aligning a depth sensor with the first perspective, and mutually registering the visible light photodetector and the depth sensor using a return of the first light beam, a return of the second light beam, and a reference map. The reference map can include a transform from a reference frame based on the first perspective and a reference frame based on the second perspective.

Abstract: A method for detecting intrusions in a monitored volume in which: N tridimensional sensors acquire local point clouds in respective local coordinate systems; a central processing unit receives the acquired local point clouds and, for each sensor; computes updated tridimensional position and orientation of the sensor in a global coordinate system of the monitored volume by aligning a local point cloud acquired by the tridimensional sensor with a global tridimensional map of the monitored volume; and generates an aligned local point cloud on the basis of the updated tridimensional position and orientation of the sensor; the central processing unit monitors an intrusion in the monitored volume by comparing a free space of the aligned local point cloud with a free space of the global tridimensional map.

Abstract: A lighting system (1) includes six equally circumferentially spaced apart and radially diverging light modules (3, 4, 5, 6, 7 and 8) for emitting light. The modules are disposed closely adjacent to each other and the light collectively defines a beam of light that is directed along a primary axis (9) in a first axial direction (10). A plurality of heat conductors, in the form of six like sets (13, 14, 15, 16, 17 and 18) of heatpipes, allow heat to be drawn away from respective modules (3, 4, 5, 6, 7 and 8). Each set of heatpipes includes eight separate continuous heatpipes, and each heatpipe in each set includes a first end (19) that is thermally connected to the relevant module and a second end (20) that is radially spaced apart from the first end (19).