Abstract: A method for creating training data for an artificial intelligence system to classify hyperspectral data. The method including receiving a hyperspectral image from a data source, wherein the hyperspectral image includes a first pixel group associated with a first classification, forming from the hyperspectral image a first augmented image using a first augmentation algorithm and a second augmented image using a second augmentation algorithm, selecting a first group of sample pixels from the hyperspectral image, the first augmented image and the second augmented image, wherein each pixel of the selected first group of sample pixels is having an association with the first classification or with a second classification and providing the selected first group of sample pixels and the associated classifications of each pixel for an artificial training system to be used as a training data.

Abstract: A system for remote labelling of hyperspectral data, the system including: visible-light camera(s), hyperspectral camera(s), Light Detection and Ranging (LiDAR) scanner for capturing LiDAR data, geolocation device for generating geolocation data, and processor(s) configured to: control hyperspectral camera(s) to capture hyperspectral image(s) of first location in real-world environment; control visible-light camera(s) to capture visible-light image(s) of first location; georeference hyperspectral image(s) and visible-light image(s) using at least LiDAR data and geolocation data; align hyperspectral image(s) and visible-light image(s) with respect to each other in pixel-wise manner; and label pixels of hyperspectral image(s) to generate labelled hyperspectral image(s), by using corresponding pixels of visible-light image(s) as ground truth material.

Abstract: A system including primary camera(s) arranged on vehicle that is employed for surveying real-world environment; secondary camera(s) coupled to steering unit(s) that is arranged on vehicle; geolocation sensor that, in operation, detects geographical location and orientation of vehicle; and processor(s) configured to receive primary image(s) captured by primary camera(s); process primary image(s) to detect asset(s) (P1, P2, P3, P4, X, Y) and location and orientation of asset(s); control steering unit(s) to adjust pose of secondary camera(s) based on location and orientation of asset(s) and geographical location and orientation of vehicle, for enabling secondary camera(s) to capture secondary image(s) of asset(s); receive secondary image(s) captured by secondary camera(s); process secondary image(s) to detect anomalous phenomena in asset(s); and locate anomalous phenomena based at least on location and orientation of asset(s).

Abstract: A method and a system for processing a point-cloud data. The method includes splitting the point-cloud data into a training dataset and a test dataset; segmenting the point-cloud data in the training dataset to define a plurality of point-cloud data tiles corresponding to an area of predetermined size; sampling the plurality of point-cloud data tiles to select the point-cloud data tiles including at least one data point corresponding to one or more predefined classes; dividing each of the selected point-cloud data tiles into a plurality of voxels of a predetermined volume; filtering a data point from each of the plurality of voxels having a lowest value for corresponding pulse returns ratio; normalizing the point-cloud data tiles with the filtered data points; and implementing the normalized point-cloud data tiles in a graph neural network for training thereof.

Abstract: A method for remotely analysing trees present in environment, including: obtaining LiDAR dataset of environment; detecting tree(s) represented in LiDAR dataset using pre-trained graph neural network, wherein tree(s) is assigned unique identifier upon detection; identifying trunk of tree(s) using statistical technique(s); determining directional vector of trunk of tree(s) using linear fitting technique(s); determining diameter of trunk of tree(s) at predetermined height from highest point of ground surface surrounding trunk, wherein directional vector is employed for determining diameter of the trunk; and predicting age of tree(s), based at least on diameter of trunk.

Abstract: A method for optimizing image data for generating orthorectified image(s) related to an area of interest in an environment. The method includes receiving a first image dataset of the area of interest captured therein, identifying each of multiple objects in the area of interest, receiving attribute information related to each of the multiple identified objects, determining if one or more of the multiple identified objects satisfy at least one of a risk criteria based on the attribute information therefor, identifying a maximum relevant second area including at least the area of interest and each of the one or more of the multiple identified objects satisfying the at least one of risk criteria, and processing the first image dataset to either discard or down-sample areas other than the maximum relevant second area captured therein.

Abstract: A method for creating training data for an artificial intelligence system to classify hyperspectral data. The method including receiving a hyperspectral image from a data source, wherein the hyperspectral image includes a first pixel group associated with a first classification, forming from the hyperspectral image a first augmented image using a first augmentation algorithm and a second augmented image using a second augmentation algorithm, selecting a first group of sample pixels from the hyperspectral image, the first augmented image and the second augmented image, wherein each pixel of the selected first group of sample pixels is having an association with the first classification or with a second classification and providing the selected first group of sample pixels and the associated classifications of each pixel for an artificial training system to be used as a training data.

Abstract: A method including: obtaining first LiDAR dataset and second LiDAR dataset of environment from LiDAR database, first LiDAR dataset and second LiDAR dataset being captured at first time period and second time period, respectively, second time period being later than first time period; dividing first and second LiDAR datasets into first and second LiDAR subsets; matching given first LiDAR subset with given second LiDAR subset; detecting first objects and second objects in given first and second LiDAR subsets; determining average offset between locations of first objects and locations of second objects; creating given link between given first object and at least one second object, said second object lying within predefined threshold distance from given first object in direction of average offset; and evaluating validity of given link, based upon whether or not given link satisfies growth criterion, given first object is associated with at most one valid link.

Abstract: A method including: obtaining first LiDAR dataset and second LiDAR dataset of environment from LiDAR database, first LiDAR dataset and second LiDAR dataset being captured at first time period and second time period, respectively, second time period being later than first time period; dividing first and second LiDAR datasets into first and second LiDAR subsets; matching given first LiDAR subset with given second LiDAR subset; detecting first objects and second objects in given first and second LiDAR subsets; determining average offset between locations of first objects and locations of second objects; creating given link between given first object and at least one second object, said second object lying within predefined threshold distance from given first object in direction of average offset; and evaluating validity of given link, based upon whether or not given link satisfies growth criterion, given first object is associated with at most one valid link.

Abstract: A method and system for capturing images of an asset using an unmanned aerial vehicle. The method includes acquiring structural information of the asset, acquiring surrounding information associated with the asset, analyzing the structural information and the surrounding information of the asset to define image capturing points for the unmanned aerial vehicle, and capturing the images of portions of the asset from the defined image capturing points. Moreover, each of the defined image capturing points allows the unmanned aerial vehicle to capture an image of a portion of the asset with an even background.

Abstract: A method for determining a lone temperature of an overhead power line of a power transmission setup. The method includes capturing an image of a section of the power transmission setup. The image of the section represents the overhead power line carrying current and a non-current carrying element of the power transmission setup. The method also includes analyzing the captured image to determine temperatures of the overhead power line and the non-current carrying element. The temperature of the overhead power line is based on a heat generated by the carried current and an environmental factor around the section of the power transmission setup, and the temperature of the non-current carrying element is based on the environmental factor. The method further includes using the determined temperatures of the overhead power line and the non-current carrying element for determining the lone temperature of the overhead power line.

Abstract: An apparatus for providing maintenance and shelter to at least one drone. The apparatus includes at least one maintenance unit operable to provide maintenance to a drone that has arrived for maintenance thereat; a base structure for providing support to the at least one maintenance unit; at least one landing structure suitable for the drone to land thereat, each landing structure including a first actuator that is operable to move the landing structure in relation to the base structure, so as to align the drone landed on the landing structure with respect to the at least one maintenance unit; and means for supporting the base structure on ground, the means for supporting the base structure operable to alter position of the base structure to provide shelter to the landing structure.

Abstract: Disclosed are a method and a system for modifying flight parameters of a remotely piloted aircraft. The remotely piloted aircraft includes a clock, at least one radio receiver and at least one radio transmitter for communicating with at least one radio transmitter of a ground station, via at least one radio communication network. The method includes analysing a communication between the remotely piloted aircraft and the ground station, such as calculating a communication quality. The method also includes modifying at least one flight parameter based on the calculated communication quality and pre-loaded instructions. The pre-loaded instructions comprise at least one threshold value of the communication quality and allowed flight parameters.

Abstract: A planar imaging sensor is provided. The planar imaging sensor includes a plurality of photo detectors divided into at least a first group of photo detectors and a second group of photo detectors, the first group of photo detectors having a first detection window and the second group of photo detectors having a second detection window, wherein the second detection window is configured to start later in time than the first detection window.

Abstract: A method and a system for inertial measurement. The method includes controlling at least one imaging sensor to capture at least two consecutive images, processing the at least two consecutive images to identify at least one feature therein and determining at least one parameter associated with the at least one feature, and determining a change in a position and an orientation of the at least one imaging sensor, based upon the at least one parameter associated with the at least one feature. The at least one parameter includes at least one of: a presence or absence of the at least one feature in at least one of the at least two consecutive images, respective pixel locations of the at least one feature in the at least two consecutive images, and/or three-dimensional locations of the at least one feature with respect to the at least one imaging sensor.

Abstract: A system having a drone and a payload frame connected to the drone, wherein the payload frame includes a mechanism for attaching at least one payload module to the payload frame and electrically coupling the at least one payload module to the payload frame. The electrical coupling includes a communication interface for communicating with a controller of the drone, and is configured to communicate a relative location of the at least one payload module in the payload frame, a weight of the at least one payload module and a volume of the at least one payload module. The controller of the drone is configured to calculate a weight distribution within the payload frame, based on the relative location of the at least one payload module, the weight of the at least one payload module and the volume of the at least one payload volume.

Abstract: Disclosed are a method and a system for modifying flight parameters of a remotely piloted aircraft. The remotely piloted aircraft includes a clock, at least one radio receiver and at least one radio transmitter for communicating with at least one radio transmitter of a ground station, via at least one radio communication network. The method includes analyzing a communication between the remotely piloted aircraft and the ground station, such as calculating the latency of the communication. The method also includes modifying at least one flight parameter based on the calculated latency and pre-loaded instructions.

Abstract: Disclosed is a system for monitoring a power line. The system includes a ground unit and one or more airborne measurement devices for measuring distances between the power line and objects spatially located in proximities of the power line. Each of the one or more airborne measurement devices includes a computing hardware, one or more cameras for capturing images and a data memory for storing pattern-recognition software. The pattern-recognition software is executed on the computing hardware to process the images to identify a unique identifier attached to the ground unit. Each of the one or more airborne measurement devices maintains a line-of-sight with the ground unit during flight by tracking with computer vision the unique identifier attached to the ground unit.

Abstract: Disclosed is a drone having at least one rotor. The at least one rotor comprises a mast and at least two blades having a proximal end and a distal end. The at least two blades are arranged in connection with the mast by their proximal ends. The at least one of the blades comprises an electrically conductive element extending a distance D between its distal end and its proximal end. The electrically conductive element is electrically coupled with means for stopping the blades, thus forming an electrical circuit. The means for stopping the blades is arranged to be actioned when at least one electrical property of the electrical circuit change.

Abstract: A communication system is provided. The system comprises a ground station, one or more airborne measurement devices, and an airborne device tethered to the ground station using one or more wires. The airborne device is operable to communicate with the one or more airborne measurement devices.