91 results about "Vehicle search" patented technology

The invention relates to the technical field of vehicle-mounted terminals, and discloses a vehicle-mounted terminal control method and system and a vehicle, and the method comprises the following steps: S1, multi-dimensional environment perception and scene judgment: collecting GPS signal intensity, Beidou signal intensity, mobile network signal intensity, vehicle altitude and environment illumination intensity through a perception module; through Beidou + inertial navigation integrated positioning + null shift calibration, the basement positioning precision is higher, the parking position monitoring and vehicle searching requirements are met, the three-level redundant link (mobile network + LoRa + Bluetooth) and distributed gateway design is adopted, the basement information transmission success rate is higher, emergency information is not interrupted, data security is guaranteed through full-link encryption, and the service life of the system is prolonged. Misjudgment of temporary weak signals on the ground is avoided through multi-dimensional sensing (signal + altitude + illumination + duration), the mode switching accuracy is higher, bandwidth waste is reduced through a priority dynamic adjustment mechanism, the emergency information response speed is increased, and link congestion is avoided through a common information caching strategy.

The invention discloses a parking lot parking space management method and device, electronic equipment and a storage medium. The method comprises the following steps: receiving parking space state information of each parking space in a parking lot in real time; according to the binding relationship between the crossroad and the parking space in the parking lot, in combination with the parking space state information of each parking space in the parking lot, controlling a guide screen at the crossroad in the parking lot to display the remaining parking space guide information; after the target vehicle is parked in the target parking space according to the remaining parking space guiding information, receiving binding relation data, uploaded by the parking space camera, of the target parking space and the target vehicle; when the vehicle owner triggers reverse searching of the target vehicle through the mobile terminal, the real-time position of the mobile terminal is determined according to a Bluetooth signal received and uploaded by the mobile terminal from the Bluetooth transmitting device in real time; and according to the real-time position of the mobile terminal and the position of the target parking space in the binding relation data, generating and displaying a real-time vehicle searching navigation path so as to guide a vehicle owner to search a vehicle. The problems of difficult parking and difficult vehicle searching in the parking lot are solved.

The present application relates to the field of unmanned aerial vehicle flight control, more particularly, the present application relates to unmanned aerial vehicle flight control method and system based on unmanned aerial vehicle search and rescue platform, the method comprises: based on the preset time window calculates the current attitude stability and wind resistance consumption of unmanned aerial vehicle, and then the excess proportion is obtained and the comprehensive wind resistance index is calculated, according to which the weak machine is judged; Then calculate the next moment of weak machine traction (current traction minus release amount) and strong machine next moment of traction (original traction plus weak machine release amount total sum of increments), complete the reassignment of unmanned aerial vehicle cluster traction. The present application can intelligently evaluate the wind resistance of unmanned aerial vehicle and dynamically adjust the traction distribution, combined with accurate prediction and environmental adaptation, significantly improve the task execution stability and reliability of unmanned aerial vehicle cluster in wind disturbance environment, ensure that the task allocation is more scientific and reasonable.

The invention relates to a multi-unmanned aerial vehicle (UAV) search strategy optimization method based on genetic programming (GP), which is characterized in that under a distributed model predictive control (DMPC) framework, each UAV is guided by a target function to realize a search trajectory optimization process, and essentially, a search strategy is converted into a mathematical logic mapping relation. In a traditional method, objective function construction mainly depends on a design thought dominated by artificial experience, and the fixed search mode based on subjectivity has the limitations of insufficient environmental adaptability, weak strategy generalization ability and the like in a complex dynamic environment. In order to solve the problem, the invention provides a search strategy optimization method based on a genetic programming algorithm, and online dynamic evolution and parameter adaptive adjustment of a search strategy are realized by establishing a dynamic mapping model between a strategy parameter space and a search performance index.

The invention relates to the technical field of parking space detection and vehicle control, and discloses a micropower geomagnetic parking space detection method and device, and the method comprises the steps: fusing the vector intensity and direction angle according to pre-obtained empty parking space geomagnetic vector data and real-time geomagnetic vector data, constructing a geomagnetic reference map, and calculating a real-time geomagnetic rotation angle; comparing and analyzing the geomagnetic reference map and the real-time geomagnetic rotation angle, generating a high-frequency sampling signal, acquiring high-frequency geomagnetic vector data of high-frequency sampling, and constructing a dynamic feature set; the adjacent vehicle interference condition is analyzed, a dynamic parking space state monitoring mechanism is configured, and the real-time state of a parking space is obtained; in response to a real-time vehicle moving task, planning and optimizing a vehicle moving path in real time to obtain an optimized path, and controlling the vehicle to move; the parking space state is adjusted in real time in combination with the adjacent vehicle interference condition, the accuracy of the parking space state detection result is improved, the optimal vehicle moving path is planned, the vehicle locating time is shortened, and the vehicle moving efficiency is improved.

The application discloses a battery replacing method and a battery replacing system, and relates to the field of battery replacing. The battery replacing method comprises the following steps: moving a battery replacing tool and a full-battery to a target battery replacing position by a battery replacing vehicle; and removing a depleted battery from the target battery replacing equipment located at the target battery replacing position by the battery replacing tool, and installing the full-battery to the target battery replacing equipment. The application can at least solve the problems of sudden power failure in the driving route, inconvenience in movement and the like in the vehicle searching for power mode.

The invention relates to a course training design method for multi-unmanned aerial vehicle search flight path planning, and belongs to the technical field of unmanned aerial vehicle flight path planning. A current multi-unmanned aerial vehicle route planning algorithm is easy to fall into local optimum; in the aspect of collaboration, task allocation and collaborative decision-making are difficult, and system performance is affected. According to the method, a course learning thought is introduced to train a multi-unmanned aerial vehicle flight path planning model, three types of course learning contents are set: shape features of threats, the number of threats and the degree of dispersion of spatial distribution of threat points, and a plurality of learning stages from easy to difficult are set for each type of course. The second class of courses are embedded in each stage of the first class of courses, and the third class of courses are also embedded in each stage of the second class of courses. And designing a reward function in the training process to judge the training degree. In this way, the convergence speed and generalization ability of the model are improved, and rapid modeling and decision making in a complex environment are achieved.

The invention provides a communication system and a communication method. The communication system includes a wireless communication apparatus, a control center apparatus, and an unmanned aerial vehicle. The control center apparatus controls the unmanned aerial vehicle to fly within a first range, so that the unmanned aerial vehicle searches for the wireless communication apparatus within the first range. When the unmanned aerial vehicle finds the wireless communication apparatus within the first range, the control center apparatus controls the unmanned aerial vehicle to fly within a second range. The second range is equal to or less than a communicable range of the wireless communication apparatus. The unmanned aerial vehicle continuously receives a physiological information signal with physiological information transmitted by the wireless communication apparatus. The unmanned aerial vehicle transmits the physiological information signal back to the control center apparatus.

The application relates to the technical field of unmanned aerial vehicle search and rescue, and discloses a sound source positioning system based on an unmanned aerial vehicle platform, which comprises a flying vehicle, a closed bin, a main image acquisition module, a noise reduction module, an anti-inertia damping release module, a sound acquisition module, a collection control module and a micro image acquisition module. The anti-inertia damping release module is arranged in the inside of the closed bin and is used for adjusting the distance between the main image acquisition module and the sound acquisition module, so that the sound acquisition precision in a dense forest area is improved. The sound acquisition module and the main image acquisition module are separated and arranged in parallel by using the anti-inertia damping release module, time delay positioning is combined, a positioning mode of high-position sound acquisition and low-position sound acquisition is realized, the influence of the dense forest on sound energy reduction is reduced by using the crown-adhering flight of the sound acquisition mechanism, and the sound acquisition quality is poor when the sound acquisition is applied to mountainous areas and dense forest search and rescue, the low-position flight image acquisition area is too small, and the search and rescue precision and the search and rescue quality are improved.

The invention provides an automatic parking system based on a parking lot plane map, belongs to the field of intelligent driving, constructs a parking lot full-scene structure map based on the plane map by obtaining the plane map of a parking lot, plans a global path for parking based on the structure map, and can cruise in the whole parking lot. In the cruising process, the vehicle can build a local map around the vehicle, obstacle avoidance is carried out based on the local map, surrounding available parking spaces are searched, after the available parking spaces are searched, the vehicle is switched to a parking mode, and the vehicle is parked in a target parking space. The problem of automatic parking in an unmapped parking lot can be effectively solved under the condition of avoiding high-cost reconstruction of a field end, and the efficiency of automatic parking is improved.

The invention provides a highway fee evasion vehicle intelligent identification and trans-provincial retailer method and system. The method comprises the steps of obtaining a trans-provincial compensation work order, querying a portal transaction flow of a province, obtaining a candidate portal flow data set, carrying out license plate matching judgment according to the data set, carrying out similar vehicle searching and generating a checking conclusion if the data set is not completely matched, and storing license plate identification evidence and checking an exit transaction flow if the data set is completely matched. And finally, constructing a structured evidence chain based on the data set, the search result and the check conclusion. According to the invention, through an intelligent license plate matching and similar vehicle searching mechanism, the problem that the cross-provincial fee evasion vehicle is difficult to retrack due to license plate recognition errors and fee evasion by using a similar license plate fake plate is effectively solved, the accuracy and efficiency of retrack checking are improved, a complete, credible and traceable evidence chain system is constructed, and the method and the device have a wide application prospect. And a reliable technical support is provided for realizing accurate compensation of trans-provincial vehicles.

The application belongs to the field of sea unmanned vehicle search, and particularly discloses a multi-unmanned vehicle target search algorithm based on ant colony optimization. The algorithm mainly uses the ant colony optimization method, so that the unmanned vehicle cluster can search for the lost target in the shortest possible time, and ensure the optimal search trajectory. The application updates the target probability graph composite target moving route based on the Markov prediction model, guides the unmanned vehicle cluster to move to the area with high target existence probability for target search task, which not only can guarantee the best solution, but also can accelerate the convergence speed of the algorithm and improve the efficiency of the target search task. Compared with other algorithms, the target search algorithm based on ant colony optimization can effectively avoid obstacles for the unmanned vehicle cluster, and ensure the safety of the unmanned vehicle cluster in the search process. In addition, when the multi-unmanned vehicle cooperatively searches for unknown dynamic targets, it has the advantages of information sharing and regional search division, can expand the search range and shorten the time to search for the target.

1. The name of the design product: airborne communication load and its main body. 2. The use of the design product: the whole and part of the design product are used for air relay communication of 400MHz-510MHz ground communication terminal, air data collection of ground sensor, and unmanned aerial vehicle search and rescue scene. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: design 1 perspective view 1. 5. Design 1 is designated as the basic design. 6. Other circumstances that need to be explained: design 2 and design 3 are partial designs, and the dashed line indicates the part not claimed.

Method for providing a free parking space (4a, 4b, 4c) for a vehicle (6a, 6b) searching for a parking space, wherein, if at least one other vehicle (8a, 8b, 8c) finds at least one free parking space (4a, 4b, 4c), this at least one parking-searching vehicle (8a, 8b, 8c) sends information about the at least one free parking space (4a, 4b, 4c) to its surroundings using vehicle-to-vehicle communication, wherein, if a parking space (4a, 4b, 4c) among the at least one found free parking space (4a, 4b, 4c) is suitable for at least one parking-searching vehicle (6a, 6b) in the vicinity, this suitable free parking space (4a, 4b, 4c) is indicated by this at least one parking-searching vehicle (6a, 6b) using vehicle-to-vehicle communication. parking space search vehicle (8a, 8b, 8c) is claimed, whereby at least one parking space search vehicle (8a, 8b,8c) a claim is received from the at least one vehicle (6a, 6b) searching for a parking space, wherein this vehicle (8a, 8b, 8c) uses vehicle-to-vehicle communication to send information to its surroundings that this suitable parking space (4a, 4b, 4c) is now claimed, wherein a free parking space (4a, 4b, 4c) is found first among several vehicles (8a, 8b, 8c) searching for a parking space, wherein information about the first finding of this free parking space (4a, 4b, 4c) is sent by the first vehicle (8a, 8b, 8c) searching for a parking space to its surroundings using vehicle-to-vehicle communication, wherein in the event that at least one other vehicle searching for a parking space (8a, 8b, 8c) among the several vehicles finding parking spaces (8a, 8b, 8c) this parking space (4a, 4b,4c) after the first parking space search vehicle (8a, 8b, 8c) has found it, this vehicle fails to provide at least one further parking space search vehicle (8a, 8b, 8c) with information about its finding of this already found parking space (4a, 4b, 4c).

The integrated rescue system for the seaborne drowning wounded personnel comprises a protection device, a seaborne rescue device and a transporting and throwing system, the protection device comprises a protection shell, a shell hoisting mechanism and a shell pulling and locking mechanism, and the shell hoisting mechanism and the shell pulling and locking mechanism are installed on the shell; the marine rescue device comprises a foldable air bag mechanism, a foldable stretcher mechanism, a stretcher hoisting mechanism and a positioning system. The transporting and delivering system comprises an unmanned aerial vehicle and a dispenser. The dispenser mounting shell hoisting mechanism achieves hoisting of the protection device, and the unmanned aerial vehicle searches and positions the position of the wounded falling into water and then releases the protection device. The shell zipper mechanism is unlocked under the pulling effect so as to release the sea rescue device, the air bag mechanism is inflated and unfolded, the stretcher mechanism is spliced and unfolded, and the drowning wounded person lies on the unfolded stretcher mechanism; the positioning system reports the position to the rescue command center in real time, the stretcher hoisting mechanism enables the air bag mechanism to be separated from the stretcher mechanism under the upward hoisting action of the rescue helicopter, and only the stretcher mechanism for fixing the drowning wounded person is hoisted.

The invention discloses a vehicle searching method, electronic equipment, a vehicle, a system, a medium and a product, and belongs to the field of vehicle positioning. The method is executed by the electronic equipment and comprises the steps that under the condition that a vehicle searching condition is met, Bluetooth channel detection CS information is sent to a to-be-searched vehicle at a first moment and a second moment, and the electronic equipment is located at different positions at the first moment and the second moment; receiving first positioning information and second positioning information sent by the vehicle, wherein the first positioning information and the second positioning information are used for indicating the distance and direction information of the electronic equipment relative to the vehicle at the first moment and the second moment; determining position change information of the electronic equipment between the first moment and the second moment; vehicle position information is determined based on the first positioning information, the second positioning information and the position change information, and the vehicle position information comprises the distance and direction information of the vehicle relative to the electronic equipment at the second moment; and displaying the vehicle position information.

The invention relates to the technical field of intelligent parking, and discloses an intelligent parking lot map drawing system and method based on Bluetooth beacons and applets, and the system comprises a Bluetooth beacon deployment layer, a user terminal layer, a management server layer, and a data interaction layer. Bluetooth beacons are deployed according to a gridding rule, a user terminal applet processes signals through adaptive filtering and dynamic compensation, and sub-meter accurate positioning is realized by adopting a mixed algorithm of multi-beacon joint positioning and fingerprint correction; the applet constructs a parking lot three-dimensional map and carries out semantic annotation, and the parking space state, the vehicle position and the charging pile information are refreshed in real time through an incremental updating unit; the system supports user interaction functions such as vehicle searching navigation and charging pile screening, and the management end can monitor the parking space flow in real time and perform dynamic scheduling. The accuracy of positioning data and the reliability of navigation service are ensured, and the efficiency and the service quality of intelligent management of the parking lot are improved.

An example method can comprise receiving an indication of a scheduled delivery at a remote computing device and from a first device. The indication of the scheduled delivery can comprise one or more delivery parameters. A delivery schedule comprising the indication of the scheduled delivery can be transmitted from the remote computing device to a second device. A delivery update adjusting one or more of the delivery parameters can be received from a third device, and the delivery schedule can be updated based on the received delivery update. The updated delivery schedule can be transmitted to the second device. One or more security actions can be performed on a delivery vehicle based at least in part on the updated delivery schedule.

This invention provides a reverse vehicle search method, apparatus, device, and storage medium, comprising: acquiring a target person identifier and target vehicle information of a target vehicle; acquiring target image data collected by multiple cameras in a designated area; the multiple cameras are distributed along a driving lane in the designated area, and parking spaces are set around the driving lane; based on the target vehicle information and the target person identifier, performing target tracking and trajectory fitting processing on the target image data of each camera to determine a first driving trajectory corresponding to the target vehicle and a second movement trajectory corresponding to the user; performing trajectory collision analysis on the first driving trajectory and the second movement trajectory to determine the target location where the target vehicle is parked, and determining a reverse vehicle search path based on the user's current location and the target location. Using this invention can reduce the hardware cost of reverse vehicle search.

The invention discloses a vehicle searching method and device, electronic equipment and a storage medium, and belongs to the technical field of computer application. The vehicle searching method comprises the following steps: receiving a vehicle searching request for a target vehicle; obtaining a geomagnetic fingerprint of the position of the target vehicle; based on the geomagnetic fingerprint of the current position of the user terminal and the geomagnetic fingerprint of the position of the target vehicle, obtaining the position coordinate of the user terminal and the position coordinate of the target vehicle by using a pre-trained positioning model; and determining a navigation path according to the position coordinates of the user terminal, the position coordinates of the target vehicle and environment sensing data acquired in real time. By applying the technical scheme provided by the invention, the navigation path can be quickly determined, and the vehicle searching efficiency is improved.

The invention provides a remote control parking method, a vehicle and a storage medium, and relates to the technical field of vehicle control. The method comprises the steps that when a driver in a vehicle searches a parking space, identity information of the driver is acquired; when the remote control parking function of the vehicle is started, determining a driver within a preset range of the vehicle according to the identity information of the driver, and obtaining the position and feature data of the driver; according to the position and the feature data of the driver, whether a parking monitoring risk exists currently or not is judged; and if the parking monitoring risk exists at present, the vehicle is controlled, and risk prompting is carried out. In the remote control parking process, the in-the-loop monitoring state of a driver can be accurately verified in real time, corresponding processing is carried out, and therefore the safety of remote control parking is improved.

The invention discloses a dynamic parking space distribution and guidance method for an expressway intelligent service area, relates to the technical field of intelligent traffic, and aims to solve the problem that a conventional service area parking space management mode is difficult to adapt to dynamic changes of vehicle model proportions in traffic flows at different time periods and is easy to cause low utilization rate of parking spaces in the service area. The technical scheme of the invention can adapt to the dynamic change of the vehicle model proportion in the traffic flow in different time periods, realizes the secondary distribution of the parking spaces in the service area, reduces the vehicle location searching conflict, avoids the disordered parking order in the service area, and improves the parking resource utilization rate in the service area.

The invention relates to a vehicle searching method, system and device, a medium, a product and a vehicle, and is applied to the vehicle, and the method comprises the steps: responding to the received vehicle searching request information, forwarding the vehicle searching request information, and sending the vehicle searching request information to a target vehicle, and the vehicle searching request information is used for a user terminal to search the target vehicle. According to the method, the user terminal and the target vehicle do not need to be connected with the Internet and the GPS, the vehicle searching process can be completed, the vehicle searching convenience and success rate are improved, and the vehicle searching complexity and cost are reduced.

The embodiment of the application discloses a vehicle searching method based on a vehicle-mounted ETC label, a vehicle-mounted ETC label and a system, and relates to positioning technology.The method comprises the following steps: the vehicle-mounted ETC label acquires first current positioning information of the vehicle-mounted ETC label from a positioning module in real time, and acquires second current positioning information of a terminal in real time; the vehicle-mounted ETC label calculates the distance between the first current positioning information and the second current positioning information in real time; if it is determined that the distance exceeds a set threshold, the first current positioning information is sent to a third communication module of the terminal through a first communication module; and if it is determined that the distance does not exceed the set threshold, the first current positioning information is sent to a fourth communication module of the terminal through a second communication module.The vehicle searching scheme based on the vehicle-mounted ETC label is provided, and the vehicle searching demand of a user is met.

The invention relates to a parking lot navigation method, device and equipment based on an AR technology, and belongs to the technical field of enhanced vision. The method comprises the steps that a geomagnetic sensor sends a vehicle arrival signal to a main control module, and the main control module obtains source parking space information of the vehicle arrival signal; an identification signal is sent to an image identification camera, and the image identification camera obtains a parking space picture. And carrying out image identification on the parking space picture, and sending the identified license plate information to the main control module. And the state of the parking space number is updated to be unavailable, the license plate and the parking space are associated and stored in a database, the idle parking space in the available state is counted, and the idle parking space is sent to the user interaction terminal. And the user interaction terminal queries the parking space associated with the license plate of the vehicle to be searched by the user, obtains user positioning, performs path planning on the parking space and the user positioning to obtain a vehicle searching path, and renders and displays the vehicle searching path. Therefore, the vehicle owner can be helped to carry out parking planning well, and efficient flow of parking spaces is realized.

The application discloses a multi-target perception fusion method in a multi-unmanned aerial vehicle search process. First, an unmanned aerial vehicle A uses a camera to search and track a target, obtains a target image position and number, and calculates a three-dimensional position of each target. If no new target appears, target information in a fusion target pool is updated; otherwise, the information component of unmanned aerial vehicle A is deleted from the fusion target pool, a target pool subset to be matched is obtained, an adjacent relationship bipartite graph is constructed, the bipartite graph is simplified, and matching is performed by taking the maximum matching number and the minimum shape gap as a correlation measure. Finally, an updated multi-target fusion result is calculated from each target information in the fusion target pool. The application can realize multi-target perception and fusion in a multi-unmanned aerial vehicle search process, retains shape features of original calculation results, uses an adjacent judgment and a shape matching strategy, and solves the problem of a high correlation matching error rate of a traditional matching fusion algorithm when a target is low-speed, gathered, and the like.

The invention provides a vehicle searching method based on multi-modal perception and edge calculation, and the method comprises the steps: collecting multi-modal data through multiple sensors, carrying out the processing of the multi-modal data, and constructing an SLAM map; identifying the vehicle parking space number and the parking lot marker coordinate, and binding the vehicle parking space number and the parking lot marker coordinate with an SLAM map to generate a semantic parking lot map; dynamically acquiring real-time positioning data of the vehicle according to the positioning signal intensity; and generating an optimal path based on the vehicle real-time positioning data and the semantic parking lot map, and automatically searching a vehicle based on the optimal path. According to the method, UWB and visual SLAM fusion positioning is adopted, and compared with the prior art, the positioning precision is higher, and automatic vehicle searching is more accurate.

The application discloses a new energy logistics vehicle remote searching system and method, and relates to the field of new energy vehicle remote intelligent control.The system comprises a user terminal, a vehicle networking platform, a T-Box, a vehicle body controller, double flash lights, a whistle horn, a vehicle controller and an SMS platform.The application binds the license plate number, the frame number and the T-Box SN number through the vehicle networking platform, and supports the operation enterprise to accurately and remotely search for batch vehicles.The T-Box enters a deep sleep state after the vehicle is powered off, and when the vehicle needs to be searched, the vehicle networking platform judges the T-Box online state, and if it is not online, the SMS platform is called to send a wake-up SMS to wake up the T-Box from the deep sleep state.The application effectively reduces the vehicle static power consumption, prolongs the standby time, and realizes accurate and efficient remote searching for batch new energy logistics vehicles, and is particularly suitable for large-scale vehicle management scenarios of electric vehicle operation enterprises.

The present application relates to the technical field of vehicle positioning, in particular to a multi-floor vehicle searching method for underground garage. The method comprises the following steps: establishing a garage information database; in response to the change of vehicle driving slope, obtaining height data of the vehicle from the garage entry position to the parking position; matching the height data with the height range interval corresponding to each floor number in the garage information database; determining the floor number corresponding to the vehicle parking position according to the matching result; and sending the determined floor number to the user terminal. The present application can obtain the specific floor position of the vehicle in the vertical dimension, thereby helping the user to accurately record and remind the floor where the parking position is located in the complex underground garage environment, so that the user can smoothly search for the vehicle when leaving the garage, and avoid the difficulty in searching for the vehicle due to the inaccurate parking floor.

The present application relates to the technical field of computer vision and unmanned aerial vehicle search and rescue, in order to solve the problem that the personnel target detection accuracy in the unmanned aerial vehicle aerial image is low, easy to miss detection and false detection, and the timeliness and effectiveness of rescue decision are affected, a model training method, an aerial image target identification method and device are provided, the aerial image personnel identification method is based on a high-resolution parallel framework and an adaptive feature enhancement module, an aerial image identification model is established, multi-scale feature extraction and feature enhancement are carried out on the aerial image, thereby the representation ability of small target personnel target discriminant information is enhanced, in the model training stage, based on the true value label and the fuzzy reconstruction guide module, the feature representation of the model is constrained to be sensitive to the foreground and insensitive to the background, effectively alleviating the imbalance problem of foreground and background features caused by the sparse distribution of personnel targets in the search and rescue scene, thereby improving the personnel target identification accuracy in the unmanned aerial vehicle aerial image.