132 results about "Aerial photos" patented technology

The invention relates to a fire monitoring and warning method on the basis of an unmanned aerial vehicle. The fire monitoring and warning method comprises the following steps: utilizing the unmanned aerial vehicle carrying a digital camera and a GPS (Global Position System) receiver to circularly monitor and shoot images, recording the shot images as well as a GPS position and a shooting gesture at a shooting moment, and sending back to a ground station in real time; scanning the received images by the ground station, identifying a potential fire point (grid) and a fired fire point (grid), and obtaining an accurate fire scene position and a scope; calculating boundaries and a gravity center of a plurality of fire scene scopes at adjacent moments by the ground station on the basis of continuously shot aerial photos, thereby obtaining a point farthest away from the gravity center of the fire scenes, namely, obtaining a fire starting point; and analyzing the change in the position of the fire starting point, so as to judge the fire extending direction and calculate the fire extending speed and acceleration. The fire monitoring and warning method has the advantages that the demand on image processing capacity of a carried device on the unmanned aerial vehicle is low, the load of the unmanned aerial vehicle is light, the continuous flying polling time is long, the risk in losing or damaging the device is low, the fire extending direction is automatically extracted, the fire extending speed and acceleration are automatically calculated, and the practical applicability is strong.

The invention discloses an optimal route selection method for overhead transmission line route. Onboard lidar equipment is adopted to acquire laser point cloud data and aerial digital photo data of the transmission line route corridor range; the onboard lidar data is processed after the wave filtering and the sorting of the laser point cloud data, and the points of the ground surface are made into a digital elevation model with high precision; then data processing is carried out by utilizing the data of the digital elevation model with high precision and ortho-rectification is carried out to the aerial photo by utilizing the internal and external orientation elements of the aerial digital photo to generate digital orthophoto maps; through the overlying of the digital elevation model and the digital orthophoto maps, the tridimensional visualization of the transmission line route corridor can be realized to optimize the transmission line route selection; finally prearrangement of power pole and power pole arrangement are carried out according to the data of plane cross sections. The route selection platform of the invention has simple operation and lifelike tridimensional scene, thus being convenient for full roaming and multi-view observation and greatly improving the efficiency of the inner plane cross section survey operation. Compared with the optimal route selection technology based on the aerial photographing measuring method, the efficiency of the inner plane cross section survey operation can be improved by about 75 percent.

The invention discloses a high-precision urban three-dimensional modeling method integrating an airborne LIDAR (Laser Intensity Direction And Ranging) technology and a vehicle-mounted mobile laser scanning measurement technology, comprising the following steps of: firstly, acquiring high-precision three-dimensional laser point clouds and high-resolution digital aerial photos of a measuring region by adopting airborne LIDAR, fast extracting a high-precision digital elevation model and a digital orthoimage product, carrying out high-precision modeling on a building to make the scenes of an urban three-dimensional electronic sand table and an urban three-dimensional building body frame model; secondly, completing the acquisition of the high-density laser point clouds and high-precision digital photos of urban scenes positioned at both sides of a road of the measuring region by adopting vehicle-mounted mobile laser scanning measurement, carrying out the quality optimization of vehicle-mounted data by referring to airborne LIDAR results, and then fast carrying out three-dimensional modeling on various urban piece elements; and finally integrating three-dimensional digital model results acquired through the airborne LIDAR and the vehicle-mounted mobile laser scanning measurement, therefore the quality and the work efficiency of the urban three-dimensional modeling are greatly enhanced. The invention can greatly reduces the development cost of projects.

The invention relates to a LIDAR data city fast reconstruction method based on a layered outline. The LIDAR data city fast reconstruction method is designed according to self characteristics of domestic airborne LIDAR data and is capable of still achieving the effect of high efficiency under the condition that the data are low in point cloud density, deficiency in point cloud, large in point cloud noise, free from returning echo, non-normal-incidence and mismatched between aerial photo images and point cloud. The LIDAR data city fast reconstruction method is capable of widely processing current LIDAR data of China, LIDAR data in the collecting part can be obtained through an airborne three-dimensional laser LIDAR, aerial photo orthoimages in the collecting part can be obtained through an airborne high resolution digital camera, and a processing platform and a display part can finish functions through an ordinary personal computer (PC). The LIDAR data city fast reconstruction method based on the layered outline can process rapidly and achieve acceptable effects under the condition that data size is large and the data are not accurate, and is wide in application prospect.

The invention relates to a privacy protection device for interfering in a UAV. The protection device comprises an optical trapping device, an image analyzing device, a tracking and locking device and an interference emitting device. The privacy protection device interferes in work of an aerial photo unit of the UAV to protect privacy within certain range, the privacy can be protected in high efficiency and low cost, the privacy protection devices uses an optical passive manner for tracking and needs not to emit electric signals so that normal work of other electronic equipment is not influenced, after interference, an image obtaining device can still obtain normal images, and a balance is made between public security and personal privacy protection caused by aerial photo of the UAV.

The invention provides a method and system for obtaining a three-dimensional model of a building. According to the method and system for obtaining the three-dimensional model of the building, optimal side faces and optimal oblique aerial photos which correspond to all the actual side faces of the building are selected according to exterior orientation elements of the oblique aerial photos and a method for calculating areas of oblique aerial photos, blocking parts between the optimal side faces are removed, and differential rectification and clipping are conducted on the optimal side faces, with the blocking parts being removed, in the optimal oblique aerial photos, so that the side face textures of the building are obtained and the accuracy of the side face textures of the building is improved; the one-to-one correspondence between the obtained side face textures of the building and a building blank pattern is established according to the optimal side faces, so that the textures, obtained through oblique photographing, of the building are automatically mapped to the building blank pattern, and the obtained side face textures and top surface textures of the building are mapped to the obtained building blank pattern, so that the three-dimensional model, provided with the side face textures and the top surface textures, of the building is obtained. The method and device for obtaining the three-dimensional model of the building have the advantages that the mapping processes are simplified, the automation degree is improved, and the modeling cycle is shortened.

The invention discloses an oil and gas pipeline inspection system based on unmanned aerial vehicle aerial photo images and an inspection method thereof. The system comprises an information collectionsystem, a ground mobile station and a data management center, wherein the information collection system is used for collecting image information along oil and gas pipelines and determining geographical location information of the images; the ground mobile station is used for reshipping equipment and processing and uploading collected data; and the data management center is used for communication with the ground mobile station and information interaction with a PC and a mobile terminal. According to the oil and gas pipeline inspection system based on unmanned aerial vehicle aerial photo imagesdisclosed by the invention, quick inspection can be realized along the oil and gas pipelines, and the dangerous conditions for the oil and gas pipelines such as irregular construction vehicles, illegal construction buildings and exposed ground surface appearing along the peripheries of the oil and gas pipelines can be automatically recognized, the inspection efficiency is greatly improved, and thelabor intensity of manual inspection is reduced.

The invention discloses a highway reorganization and expansion surveying method and relates to the fields of surveying and mapping and highway engineering design. The method comprises the following steps of: laying a ground target control point, and acquiring a three-dimensional space coordinate; performing vehicle-mounted movable laser scanning measurement, and acquiring a vehicle-mounted measured original data result; taking the three-dimensional space coordinate of the ground target control point as a reference, performing data processing on vehicle-mounted point cloud in the vehicle-mounted measured original data result, and acquiring a high-precision vehicle-mounted ground point cloud; establishing a first triangulation network for the high-precision vehicle-mounted ground point cloud, and generating a highway pavement digital elevation model; performing survey area vehicle-mounted LIDAR aerial survey, and acquiring a vehicle-mounted measured original data result; acquiring a digital elevation model and a high-precision central pile cross section map by using a 1:2000 measuring scale according to the vehicle-mounted measured original data result; and taking the vehicle-mounted measured original data result as the basis, and manufacturing digital line graphs by using the 1:2000 measuring scale in a respective 300m range on two sides of the highway by integrating the vehicle-mounted ground point cloud and digital aerial photos.

The embodiment of the invention provides a data processing method and a data processing device, wherein the method comprises the following steps: obtaining an original mobile measuring track and original point cloud data and aerial photo point cloud data corresponding to the original mobile measuring track; calibrating the original point cloud data by adopting the aerial photo point cloud data to obtain excursion information of the original point cloud data; calculating correcting information of the original mobile measuring track according to the excursion information of the original point cloud data; correcting the original mobile measuring track by adopting the correcting information to obtain a target mobile measuring track; generating target point cloud data according to the target mobile measuring track. The data processing method can enable the point cloud data to have description of measuring details, guarantees the measuring precision and improves the data processing effectiveness and accuracy.

The invention discloses a rendering method and device of three-dimensional space data. The method includes the steps that the three-dimensional space data are obtained; a first quadtree for updating and rendering two-dimensional satellite images and altitude data is set, and a second quadtree for updating and rendering aerial photo three-dimensional model data is set; node auxiliary information and terrain block offset information corresponding to nodes of the two quadtrees are obtained, the three-dimensional space data are rendered according to the node auxiliary information and the terrain block offset information, the node auxiliary information indicates data types corresponding to the nodes, and the terrain block offset information is used for correcting drawn practical positions of the aerial photo three-dimensional model data corresponding to the terrain blocks. According to the method, updating and drawing are conducted simultaneously through the two quadtrees, the two quadtrees are independent from each other, so the aerial photo three-dimensional model data can be overlapped on the two-dimensional satellite images and the altitude which are subjected to data coordinate encryption deflection to be drawn at the same time; accordingly, in the scene transition and splicing process of a three-dimensional electronic map, manual intervention is eliminated, and uncertain factors of model making and the complexity of data making are reduced on the premise of guaranteeing data display accuracy.

An imaging device that gives a ground based user immediate access to a detailed aerial photograph of the entire area for a given radius about his present position. The device can be launched into the air, and rotates in a predictable pattern to scan an imager over every point of the ground, from a vantage point high in the air. These pictures can be stored or transmitted to the ground and assembled on a computer to form a spherical picture of everything surrounding the imaging device in the air.

The invention provides a live video method. The live video method comprises the following steps: user equipment sends a request message of obtaining an operation interface of an unmanned aerial vehicle live video to a network server that provides an unmanned aerial vehicle live video function; the user equipment triggers to perform connection pairing with an unmanned aerial vehicle remote controller after receiving the operation interface of the unmanned aerial vehicle live video returned by the network server, and performs interaction to obtain a session description protocol; and the user equipment receives and live broadcasts video streams transmitted by a media channel established by the unmanned aerial vehicle remote controller through IMS. The scheme can realize the live video of images shot by an unmanned aerial vehicle, can also live broadcasts aerial photo videos shot by the unmanned aerial vehicle to friends and allow the interaction among friends, thereby improving the user experience.

The present invention discloses an aerial photo video motion object detection method. The method comprises the steps of: performing image matching of an input video sequence, and obtaining a difference image after background compensation; performing energy accumulation of the difference image after the background compensation, and obtaining an accumulated difference image; performing morphologicalopening processing of the accumulated difference image, removing noise and capturing a general target area; and performing edge detection to obtain an edge of a target image, and performing marking of the target area. The aerial photo video motion object detection method is suitable for multi-motion object detection in different scenes and is high in detection accuracy.

The invention relates to the field of rat damage image processing, and aims at providing a grassland rat damage monitoring method based on low-altitude remote sensing, and the method comprises the steps: obtaining an aerial photo of an experiment region through an unmanned plane, processing the aerial photo through a Pix4D map platform, and obtaining four low-altitude remote sensing orthoimages; wherein the images comprise a zokor damage area image in spring, a zokor damage area image in summer, a marmot damage area image in spring and a marmot damage area image in summer. On the basis of fully mastering surface features of different rodent damages, surface rodent damage information of four images is extracted one by one by using four methods of gray threshold segmentation, color texture optimization, rule-based object-oriented and BP neural networks, and then the extraction precision is evaluated by using double evaluation standards of spatial precision and quantitative precision so as to obtain the surface rodent damage information of the four images. The method for extracting the rat damage information in the images in different seasons is reasonable in structure, ingenious in design and suitable for popularization.

The invention discloses an insulator chain automatic positioning method based on binary image shape features and belongs to the field of image processing techniques and power transmission and transformation equipment running state maintenance. The method comprises the following specific steps: 1) performing morphological filtering and micro-region removing processing on a binary image; 2) performing digitalization description on three shape features of an insulator chain, and processing the image based on the above to remove the regions not satisfied with the three shape features and keep the regions satisfied with the three shape features; and 3) utilizing a minimum bounding rectangle to mark the regions satisfied with the shape features of the insulator chain and thus positioning is achieved. The problem that the positioning of the insulator chain in a complicated-background aerial image is difficult is solved by fully utilizing the shape features of the insulator chain and by adopting the method based on binary image shape feature description. The method is practicable and feasible; better positioning effect is achieved; time needed is short; no labour is needed; and the method provides a certain reference meaning for scheme design of related problems.

The present invention provides a data compression transmission method based on an air-ground integration car networking system, belonging to the field of the data compression technology. The problems are solved that the data volume is large in the car networking system based on air-ground integration and the data compression efficiency is low and the transmission speed is low in the transmission process. The method comprises: extracting data collected at N time moments, and performing pre-compression process of partial extracted data; and processing the average speed data, the N rows of traffic density data, n rows of traffic flow data, I rows of environment temperature data through adoption of a run coding compression algorithm. The run coding compression algorithm comprises: after performing classification processing of the n rows of road vehicle average speed data, n rows of traffic density data, n rows of traffic flow data and I rows of environment temperature data, transmitting the data after run coding compression to a vehicle terminal through the number one wireless transmitter-receiver set of an aerial photo unmanned aerial vehicle system. The data compression transmission method based on the air-ground integration car networking system is suitable for data compression and transmission.

The invention discloses a retractable landing gear of an unmanned aircraft. The retractable landing gear comprises a base, a steering engine, a first rod member, a supporting frame and a fixed seat, wherein the steering engine is fixed in the hollow base, a steering engine output shaft penetrating through the side of the base is fixedly connected to a drive end of the first rod member, a linking end of the first rod member is hinged to the supporting frame, the supporting frame is hinged to the middle part of the fixed seat, and the upper part of the fixed seat is hinged to the base. The retractable landing gear of the unmanned aircraft has two stable states: supporting of the fixed seat and retraction of the fixed seat. In the aerial photo process, the fixed seat of a landing rack can be retracted, the retracted fixed seat does not hinder a photograph camera, and the 360-degree all-around smooth photographing of the camera can be guaranteed; meanwhile, the retracted fixed seat can alleviate the affection of lateral wind for the landing rack, and the stable photographing of the unmanned aircraft can be facilitated.

The invention discloses a multi-source remote sensing data classification method for extracting classification sample points based on an unmanned aerial vehicle, and the method comprises the steps: uniformly extracting the classification sample points from aerial photos of the unmanned aerial vehicle, and carrying out the preparation and calibration of each type of sample points; obtaining a classified remote sensing data set, performing image processing on the remote sensing data set, and performing geographic positioning on the classified sample points according to the classified remote sensing image data set, wherein the classified remote sensing data set comprises a microwave data Sentinel-1 data set, a multispectral Sentinel-2 data set, a vegetation index data set based on the Sentinel-2 data set and a digital elevation model data set; and obtaining a classification result by utilizing a random forest classification model through the classification sample points with the geographic space information positioning. According to the multi-source remote sensing data random forest classification method based on the classification sample points extracted by the unmanned aerial vehicle, the earth surface type classification drawing process can be rapidly, effectively and cheaply realized; and meanwhile, after the influence of edge classification sample points is eliminated, the classification precision is obviously improved, and particularly, the precision of the kappa coefficient is better.

The invention provides an unmanned-aerial-vehicle-based automatic identification and early warning method for vendors in a no-peddler area. The unmanned-aerial-vehicle-based automatic identification and early warning method comprises the following steps: obtaining an aerial shooting image of the no-peddler area in a city in a jurisdiction range, and extracting a plurality of pixel areas from the image as feature comparison elements; collecting feature images of various roadside vendors in the market at various angles, acquiring feature image information of a plurality of vendors, and extracting vendor feature image spots from pixel areas of the image images according to the feature image information of the vendor, wherein the unmanned aerial vehicle is used for aerial photography of the jurisdiction no-peddler area to obtain an aerial photography picture; obtaining a plurality of pixel areas in the aerial image; and comparing and identifying suspected vendor image spots in the pixel region of the aerial photo with vendor feature image spots in a feature library, and when a threshold value of an identification matching result is greater than a set threshold value, giving an alarm. Through an artificial intelligence mode, the vendors in the no-peddler area are rapidly positioned, and the pressure on city management is reduced.

The invention relates to an automatic control system of a three-wing two-paddle recombination type unmanned aerial vehicle (UAV). In order to improve the operational speed and ensure the stability and the reliability of the control system of a UAV, a field programmable gate array (FPGA) processor is introduced into a one-chip data signal processor (DSP) to form a DAP+FPGA dual-core processor, the structure adopting a single paddle of the conventional UAV is abandoned, and a structure with a single wing and positive and negative paddles is introduced into the system, so that the power performance of the system is greatly improved; in order to prolong the aerial photo time of the UAV, the system adopts a high-performance lithium ion battery to realize a function of synchronously controlling a six-axis motor by a single controller; and a multi-axis servo system with the maximum workload in the control system of the UAV and data signal processing are processed by an FPGA to give full play to the characteristic of high data processing speed of the FPGA, so that the division of work of the DSP and the FPGA processor is realized, and the DSP is freed from the heavy workload.

The invention discloses a simple digital map manufacturing method based on an aerial photo. The manufacturing method comprises the following steps of: building a coordinate system for the aerial photo of a local area; identifying the coordinate of each building in the photo; building a conversion method with actual longitude and latitude; building the relation between longitude and latitude of two points with a unit distance from each other; building a constraint condition between two points which are not more than m meters from each other by using such relation, wherein all points which enable the condition to be true are not more than m meters from a central point. The method is suitable for common users, professional knowledge or professional tools are not required, and the requirement on professional is low; the manufacturing process can be realized by a computer completely, and thus the manual work load is low and the manufacturing cost is low; and all objects but not only symbolic objects such as rivers and bridges in the actual scene can be displayed in detail. The method can be widely used in service systems based on position, and also can be combined with e-government affairs, to directly serve government management and decision analysis through identifying detailed information of objects.

The invention discloses a vision-based power transmission line tower online identification and inclination detection method, and belongs to the field of image processing and power transmission line detection. The implementation method comprises the following steps: carrying out angle correction on an aerial photo of the unmanned aerial vehicle; preprocessing the acquired image and extracting linesegment features by using an LSD algorithm; filtering the obtained line segment features of the picture to obtain line segments with the filtered inclination smaller than a preset threshold value, andfusing the filtered interrupted line segments meeting a preset line segment fusion standard; searching an outermost tower foot line segment of the tower according to the outermost tower foot characteristics, and identifying and positioning a tower area, wherein the outermost tower foot characteristics refer to that the outermost tower foot line segment of the tower meets two corresponding constraint conditions; calculating included angles between the central lines of the tower foot line segments on the outermost sides of the two towers and the vertical direction, the included angles being thecalculated inclinations of the towers in the direction, and respectively calculating the inclinations of the towers in four directions around the towers to realize inclination detection of the towers.

The invention discloses a three-dimensional simulated electronic drawing for sea channels. The three-dimensional simulated electronic drawing is formed by the following method: forming FLT (Fault-Locating Test) topography geometry data and RGB (Red, Green and Blue) topography texture, 3D geometry data and RGB topography data by utilizing the DEM (Digital Elevation Model) topographic data and DOM (Document Object Model) image data, editing 3D model design data and aerial photo model data through a CREATOR tool, a PHOTOSHOP tool and a 3DMAX tool; forming FLT topography data by utilizing a 3D model geometry data to lead the RGB topography texture through the CREATOPH tool; and forming three-dimensional simulated electronic drawing for sea channels in VEGA according to the two formed FLT topography data. The model of the three-dimensional simulated electronic drawing for sea channels expands the visualization concept; and through the mode, the visualization technology penetrates through the whole GIS (Geographic Information System) running process.

The invention discloses an inverse compensation stable-attitude quadrotor unmanned aerial vehicle. The inverse compensation stable-attitude quadrotor unmanned aerial vehicle comprises a vehicle body, wherein four arms are fixedly connected to the vehicle body, a rotor wing is installed at the tail end of each arm, the arms are arranged in a pairwise opposite mode, every two opposite arms are located on the same straight line, and the positions where two opposite arms are connected with the vehicle body are higher than the positions where the other two opposite arms are connected with the vehicle body; a chamber channel is formed in each arm, the chamber channels of every two opposite arms are communicated through a pipeline arranged in the vehicle body to form parallel channels, and balancing blocks are arranged in the parallel channels and driven by driving devices arranged on the parallel channels. By the adoption of the inverse compensation stable-attitude quadrotor unmanned aerial vehicle, the problem that the vehicle shakes under continuous strong wind high in the sky is effectively solved, and the quality of an aerial photo is more stable.

The invention relates to a system and method for remotely triggering a shutter of a photographic apparatus based on a pulse-width modulation signal. The system comprises a pulse-width modulation signal generator, a wireless transmitting module, a wireless receiving module, a single chip microcomputer, an optical coupler and a photographic apparatus; the pulse-width modulation signal generator is connected with the wireless transmitting module; wireless communication between the wireless transmitting module and the wireless receiving module is performed to transmit the pulse-width modulation signal; the wireless receiving module receives the pulse-width modulation signal and transmits the pulse-width modulation signal to the single chip microcomputer to identify and judge; the single chip microcomputer is connected with the optical coupler; and the optical coupler is connected with a shutter control line of the photographic apparatus so as to trigger the shutter of the photographic apparatus to act. The system and the method are less affected by barriers and the property of a control signal in resisting interference is high, so that the purpose of remotely triggering the photographic apparatus is fulfilled; the product provided by the invention is compact in structure, small in size, light in weight and very beneficial to the carrying of a light unmanned aerial vehicle, thereby providing a guarantee to the remote control of an aerial photo of the light unmanned aerial vehicle.

The invention discloses a water and soil conservation method of an electric power transmission line engineering construction, belongs to the technical field of agriculture, and in particular, relates to the water and soil conservation method of the electric power transmission line engineering construction. The method comprises the following steps: (1) optimizing item design and reducing water and soil loss: a path is optimized; a tower position is optimized; the selection of the tower position in such places of easily causing the water and soil loss as cragged slopes or channel river sides is prevented through a line-position combining mode by fully using the advantages of aerial photo path selection in field positioning; an universal iron tower with different long legs, a high-low foundation and a deep-shallow foundation are used, so that the excavated volume of earthworks, the destruction of vegetation and the water and soil loss can be reduced to the greatest extent; the excavated volume is reduced by a slope folding method in the slope treatment; the optimal design is performed for slope toes of upper slopes; the distances from the slope toes of the upper slopes to a foundation pit in the inner side of the tower position are reduced by combining with actual conditions of the site construction; and the slope toes forward move to reduce a large quantity of the earthworks.

The invention discloses an unmanned aerial vehicle. The unmanned aerial vehicle comprises a support and a driving system arranged on the support, wherein the driving system comprises a motor and a plurality of rotor wings, a synchronous driving mechanism is arranged between each rotor wing and the motor, and the motor drives the plurality of rotor wings to rotate at the same speed by the synchronous driving mechanisms respectively. According to the unmanned aerial vehicle, one motor is arranged and is used for driving all the rotor wings to rotate synchronously, and as only one motor is arranged, the cost is low, and the weight is light; compared with a plurality of motors, one motor can greatly weaken the influence of high-frequency vibration on aerial photo definition; besides, one motor can drive all the rotor rings to rotate simultaneously, so that the synchronicity can be controlled easily.

The invention discloses an image and radio frequency communication data fused parcel map automatic generation method. The image and radio frequency communication data fused parcel map automatic generation method comprises the steps that a plurality of electrical boundary points are allocated to all households, and serial numbers of the electrical boundary points and land attribute information of all households are written in the electrical boundary points; the electrical boundary points are placed in order according to the land scopes of all households, and radio frequency communication signals are controlled to be transmitted; ortho-photo images are acquired through aerial photo of an unmanned aerial vehicle and treatment, and location coordinates of the electrical boundary points are extracted; the radio frequency communication signals transmitted by the electrical boundary points are received; according to the location coordinates of the electrical boundary points in the ortho-photoimages mapping to the radio frequency communication signals, an SURF algorithm is used for matching the placing order of the electrical boundary points and the land attribute information of all households, connecting is conducted according to the order of the serial numbers, and a panel is formed by boundary points wiring, and thus parcel maps of all households are acquired. According to the image and radio frequency communication data fused parcel map automatic generation method, the workload of household-entry boundary identifying carrying out of house site authentic right can be reduced, and accuracy and high efficiency of confirmation of land right are achieved.

The present invention provides a multi-rotor unmanned aerial vehicle target real-time tracking shooting system and method. The hardware system comprises a multi-rotor unmanned aerial vehicle, a flightcontrol unit, a holder, a manual and automatic control signal switching module, an image data processing unit and a monocular camera. The hardware devices are installed on an unmanned aerial vehicle,the camera is installed on the unmanned aerial vehicle holder, and the images shot by the camera are transmitted to the image processing unit. The target tracking method is employed to obtain a target position and convert the position information to flight control signals transmitted to the flight control unit to achieve tracking flight of a target. The multi-rotor unmanned aerial vehicle targetreal-time tracking shooting system and method are low in cost, low in power consumption, stable in tracking and complete in function, can perform real-time and accurate tracking shooting for the selected target, can be used for tracking of criminal offenders or vehicles and can be also used for travel aerial photo.

The invention relates to an unmanned aerial vehicle ground target positioning method based on different-source image matching, and the method comprises the following steps: S1, obtaining a high-resolution remote sensing satellite map of a flight region of an unmanned aerial vehicle from the Internet according to a flight task of the unmanned aerial vehicle; s2, the unmanned aerial vehicle carries a visible light camera, carpet type search is carried out in the flight area, the pitch angle of the camera is adjusted so that the camera can keep ortho-shooting on the target, and an ortho-image of the target is shot; s3, processing the aerial image; s4, performing sliding window search on the satellite base map to obtain a plurality of base map blocks, and searching a base map block closest to the aerial photo in all the base map blocks; and S5, according to a matching pair obtained by carrying out heterogeneous image matching on the aerial image and the closest base image block, calculating a homography matrix M of the two images by utilizing OpenCV, mapping the central point of the aerial image to the satellite base image by M, and obtaining the central point of the aerial image, namely the longitude and latitude of the center of the target. The method provided by the invention is stronger in anti-interference capability, can better adapt to a field environment, and can carry out unmanned aerial vehicle ground target positioning without depending on a GPS (Global Positioning System).