CN111369760A - Night pedestrian safety early warning device and method based on unmanned aerial vehicle - Google Patents
Night pedestrian safety early warning device and method based on unmanned aerial vehicle Download PDFInfo
- Publication number
- CN111369760A CN111369760A CN201811586153.3A CN201811586153A CN111369760A CN 111369760 A CN111369760 A CN 111369760A CN 201811586153 A CN201811586153 A CN 201811586153A CN 111369760 A CN111369760 A CN 111369760A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- ground station
- target
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000004891 communication Methods 0.000 claims abstract description 27
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims abstract description 22
- 230000000007 visual effect Effects 0.000 claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 10
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 7
- 238000012790 confirmation Methods 0.000 claims description 5
- 238000013459 approach Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000012806 monitoring device Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000012546 transfer Methods 0.000 claims 1
- 238000005286 illumination Methods 0.000 abstract description 5
- 230000009471 action Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 10
- 238000001514 detection method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000032258 transport Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
- B64C39/024—Aircraft not otherwise provided for characterised by special use of the remote controlled vehicle type, i.e. RPV
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2101/00—UAVs specially adapted for particular uses or applications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2201/00—UAVs characterised by their flight controls
- B64U2201/20—Remote controls
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Emergency Alarm Devices (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a night pedestrian safety early warning method and device based on an unmanned aerial vehicle, which mainly comprise an unmanned aerial vehicle body, a flight control system, a visual system, an illumination and alarm system, a ground station system, a cloud server and a mobile phone APP; cell-phone APP calls unmanned aerial vehicle with ground station communication, ground station sends the instruction of taking off and plans the airline to unmanned aerial vehicle, and unmanned aerial vehicle arrives near the target according to the airline, confirms the target that needs the tracking according to the sign that APP shows, continuously tracks the target and detects unusual action simultaneously to upload the video image to cloud server storage, when detecting unusual action or start the acousto-optic warning according to pedestrian's needs, provide the guarantee for pedestrian's safety at night.
Description
Technical Field
The invention relates to the technical fields of target tracking, Internet of things and the like, in particular to a night pedestrian safety early warning device and method based on an unmanned aerial vehicle.
Background
With the rapid development of electronic information technology, public security departments monitor criminals more and more, and fixed video monitoring devices, unmanned aerial vehicles and the like are powerful tools for assisting the public security departments in limiting illegal crimes. However, these devices are required to be actively used by public security agencies, and video monitoring is often arranged in areas with large pedestrian flow, so that the monitoring range cannot be fully covered in areas with rare pedestrian flow, and meanwhile, the effect of the existing video monitoring is greatly reduced in dark night environments.
At present, the safety of the independent personnel at night is still difficult to guarantee, and a large amount of manpower and material resources are consumed if a fixed monitoring mode is arranged in a large range. The unmanned aerial vehicle has the characteristics of light weight, low cost and the like, is widely concerned, and is greatly put into the fields of national defense and civil security. After the unmanned aerial vehicle is additionally provided with the embedded image processor and is networked through the ground station, an active monitoring task based on the unmanned aerial vehicle can be initiated by a pedestrian for completing the whole-course non-blind-area monitoring when the pedestrian walks, and meanwhile, possible lawless persons are warned. Therefore, it is very necessary to develop a night pedestrian safety early warning system based on the unmanned aerial vehicle.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a night pedestrian safety early warning device and method based on an unmanned aerial vehicle, and guarantees the safety of pedestrians at night to a certain extent.
The invention adopts the technical scheme that the night pedestrian safety early warning device based on the unmanned aerial vehicle comprises an unmanned aerial vehicle body, a flight control system, a visual system, an illumination and alarm system, a ground station system, a cloud server and a mobile phone APP; the visual system and the flight control system are both built in the center of the unmanned aerial vehicle body, the ground station system is in wireless communication connection with the flight control system, the ground station system is in wireless communication connection with the visual system, and the visual system is in serial communication connection with the flight control system.
The invention has the beneficial effects that: the invention combines the computer vision technology, the unmanned aerial vehicle control technology and the Internet of things technology, realizes the active flight of the unmanned aerial vehicle initiated by the pedestrian, completes a series of tasks such as detection, tracking, alarming and the like at night, improves the coverage range and the coverage time of monitoring, and is beneficial to ensuring the safety of the pedestrian walking at night.
Furthermore, the vision system comprises a video acquisition card, a high-definition motion camera, an infrared camera, a video processing module and an image transmission module; the video acquisition card, the high-definition motion camera and the infrared camera are mounted on the unmanned aerial vehicle body and used for acquiring a video image of the environment where the unmanned aerial vehicle body is located; the video processing module is connected with the video acquisition card through a USB interface and is used for processing the video image; the image transmission module is in communication connection with the high-definition motion camera and the infrared camera, is in wireless communication connection with the ground station, and is used for sending the acquired video images to the ground station.
The beneficial effects of the further scheme are as follows: the vision processing subsystem in the invention applies video acquisition and computer vision processing technology, and can transmit the acquired video image to the ground station for storage, and simultaneously, the video processing module carries out target detection, identification and tracking on the video image so as to provide corresponding indication for the control of the flight control subsystem.
Further, the video processing module adopts a Jetson TX2 embedded development board.
The beneficial effects of the further scheme are as follows: the Jetson TX2 embedded development board has the characteristic of high performance, can detect, identify and track the target of the video image collected by the video collection card, the motion camera and the infrared camera, accelerates the video image processing speed and increases the real-time performance of the system.
Furthermore, the flight control subsystem comprises a power module, a power management module, a sensor module, a GPS positioning module, a wireless communication module and a control module; the power management module is electrically connected with the rest modules in the flight control subsystem and is used for providing adaptive power for each module; the control module is in communication connection with the power module, modulates the power module through a PWM control technology and provides flight power for the unmanned aerial vehicle body; the sensor module is in communication connection with the control module and transmits the acquired data information to the control module through an SPI/IIC data transmission standard; the GPS positioning module is in communication connection with the control module through a UART interface and is used for positioning the unmanned aerial vehicle body; the wireless communication module is in communication connection with the control module through the SPI interface, is in wireless communication connection with the ground station and is used for realizing communication between the flight control subsystem and the ground station.
The beneficial effects of the further scheme are as follows: the flight control subsystem of the invention takes the target detection and recognition results obtained by the vision processing subsystem as control input data, and controls the unmanned aerial vehicle through the high-performance control module to execute corresponding actions and tasks.
Further, the power module comprises an electronic speed regulator and a brushless motor; the sensor module comprises a gyroscope, an accelerometer, a barometer and an electronic compass and is used for acquiring the pose, the direction and the acceleration of the unmanned aerial vehicle body and the atmospheric pressure information of the environment where the unmanned aerial vehicle body is located; the control module employs an STM32F427 microcontroller.
The beneficial effects of the further scheme are as follows: the invention adopts the sensor module to collect the pose, direction and acceleration of the unmanned aerial vehicle body and the air pressure information of the environment, so that the unmanned aerial vehicle can stabilize the pose conveniently, and the robustness of the detection of the video acquisition card and the camera is improved; the STM32F427 microcontroller serves as a control module that is well suited to coordinate the functions of the various modules in the flight control subsystem.
Furthermore, the unmanned aerial vehicle body is provided with an illumination system and an acousto-optic alarm system, and the illumination system is used in an environment with dark light at night, so that the shooting effect of the high-definition motion camera can be improved, and the pedestrian can be illuminated; acousto-optic warning system comprises the speaker of carry on unmanned aerial vehicle and warning light, and the pedestrian can open unmanned aerial vehicle's acousto-optic warning system through cell-phone APP when experiencing danger, and the speaker can send out the alarm sound when then, and the warning light also will flash fast simultaneously for warn relevant personnel.
The beneficial effects of the further scheme are as follows: the unmanned aerial vehicle is used as a public platform, and any pedestrian can call the unmanned aerial vehicle through a mobile phone when needing protection; the lighting system and the sound and light alarm system that unmanned aerial vehicle carried on can select to open through APP, provide the guarantee for pedestrian's safety night.
The invention also provides a night pedestrian safety early warning method based on the unmanned aerial vehicle, which comprises the following steps:
step S1: the pedestrian calls the unmanned aerial vehicle through the mobile phone APP;
step S2: the ground station transports the unmanned aerial vehicle out of the containing box after receiving the call, and sends a take-off instruction and a flight track to the unmanned aerial vehicle;
step S3: the aircraft flies to the sky of a target according to a flight path given by the ground station, and the pedestrian information is searched by using an infrared camera;
step S4: after the unmanned aerial vehicle detects the pedestrian, the high-definition motion camera is used for detecting identification information around the pedestrian, whether the identification is matched or not is confirmed to the ground station, if so, the target recognition work is finished, and if not, the step S3 is returned to continue searching around the target coordinate point;
step S5: the unmanned aerial vehicle tracks a target and detects abnormal behaviors through the infrared camera and GPS data, and simultaneously transmits a real-time video shot by the high-definition camera back to the ground station and uploads the real-time video to the server through the ground station;
step S6: the unmanned aerial vehicle continuously tracks the target, the unmanned aerial vehicle judges early warning levels according to the geographic position in the tracking process, if abnormal behaviors are detected, specific sound and light alarms are sent out according to different early warning levels, and pedestrians can also select to compensate the light intensity and send out the sound and light alarms or not through the mobile phone APP;
step S7: when a user finishes a task through a mobile phone APP or the electric quantity of the unmanned aerial vehicle is insufficient, the unmanned aerial vehicle requests to return to a ground station, after confirmation of the ground station, the unmanned aerial vehicle returns according to a given flight path, and when the electric quantity is insufficient and the unmanned aerial vehicle returns, the ground station sends out another unmanned alternative work;
step S8: after the unmanned aerial vehicle that navigates back descends at the appointed sign position of ground satellite station, convey it by the ground satellite station and charge the containing box, wait for next task.
The invention has the beneficial effects that: the pedestrian initiatively initiates the monitoring request, realizes the pedestrian tracking monitoring of the road at night, and sends out the acousto-optic alarm under the necessary condition to warn lawless persons, protect the safety of the pedestrian, save manpower and material resources, and have good practicability and expandability.
Further, in step S3, a yolov3 network is used to detect the pedestrian in the infrared camera, and the specific steps are as follows:
a1, converting the video image to a uniform size, e.g., 416 × 416, 448 × 448, or 224 × 224 and dividing into 7 × 7 meshes.
Predicting 2 frames and a category information by adopting each grid, and predicting five values of (x, y, w, h) and confidence of each frame; wherein (x, y) represents the two-dimensional coordinates of the frame on the image, w and h represent the width and the height of the frame respectively, and the confidence value comprises two information of the confidence of the target contained in the frame and the accuracy of frame prediction.
And multiplying the category information of each grid prediction and the confidence information of the frame prediction to obtain the specific classification confidence of each frame.
And setting a confidence threshold, filtering the frames with the specific classification confidence degrees smaller than the confidence threshold, and performing non-maximum suppression processing on the reserved frames to obtain a final detection result.
The beneficial effects of the further scheme are as follows: the yolov3 network has the advantages of high detection precision, sensitivity to small target detection, excellent real-time performance and strong robustness, and is suitable for unmanned aerial vehicles to carry out target detection on pedestrians.
Further, in step S4, the color identifier of the pedestrian mobile phone screen is identified by using the HSV color space, and the target is confirmed, which specifically includes:
b1, converting the environment color image into an HSV space, wherein the conversion formula is as follows:
in the formula,
is a color in the RGB color space,
is a color in the HSV color space,
representing a linear transformation.
And carrying out histogram equalization on the image in the HSV space.
And traversing all the pixel points to identify the colors.
And confirming whether the color information is matched with the ground station, if so, entering the step B5, and otherwise, switching to the next target.
And the ground station switches the color identification once, if the matching is successful again, the current pedestrian is considered as the target to be monitored, and the step B6 is carried out, otherwise, the next target is switched.
And the ground station confirms whether the target is correct or not to the APP, if the target is correct, the recognition is completed, and if not, the next target is switched.
The beneficial effects of the further scheme are as follows: the adoption of the HSV space can intuitively express the brightness, tone and brightness of colors, and is convenient for color comparison; the accuracy of target identification at night is guaranteed through 2 times of color comparison and target confirmation on APP.
Further, in step S5, a DSST algorithm is used to fuse the GPS data for target tracking, and the specific steps are as follows:
c1, obtaining the target position according to the detected result in the step A4;
c2, extracting target characteristics to obtaindDimensional characteristicsfTraining is carried out to obtain a filter templateHThe function used to train the model is:
in the formula,
is the two-dimensional DFT of each dimension of the feature f, G is the two-dimensional DFT of the response constructed by the gaussian function;
c3, predicting the target position in the next frame of image by combining GPS data, extracting characteristic z, calculating response y by using the trained model, wherein the maximum value position of the response is the center position of the new target, and the response calculation formula is as follows:
wherein,
is the two-dimensional DFT of feature z;
and C4, estimating the current position of the target according to the target position, the current GPS position and the last GPS position in the image, controlling the unmanned aerial vehicle to fly, updating the filter template, and calculating the response of the next frame.
The beneficial effects of the further scheme are as follows: DSST is an accurate scale estimation method in visual tracking, and combines GPS position data to ensure stability in a target following process.
Further, in steps S5 and S6, an abnormal behavior recognition module is used to determine whether to issue an audible and visual alarm, and the specific steps are as follows:
d1, acquiring the early warning level of the current section;
d2, continuously detecting and tracking other pedestrians around the target;
d3, judging the states of other pedestrians to obtain the danger levels of the pedestrians;
d4, sending out sound and light alarm according to the early warning level;
in step D1, the early warning level is classified into 4 levels, and the levels required to be early warned are preset according to different regions: the early warning grade of school districts and road sections with other monitoring devices is 4, the early warning grade of urban and rural road sections without monitoring is 3, the early warning grade of remote roads without monitoring is 2, and the early warning grade of road sections with crime behaviors is 1.
In step D3, the other pedestrian states include 5 danger levels, for example: the danger level of the situation that no other pedestrians are around the tracking target is 5, the danger level that the other pedestrians and the tracking target always keep following at a certain distance is 4, the danger level that the other pedestrians slowly approach the tracking target is 3, the danger level of the situation that the other pedestrians quickly approach the tracking target is 2, and the danger level of the situation that the other pedestrians and the tracking target send a physical conflict is 1.
In step D4, the audible and visual alarms are classified into 3 levels, the brightness flashing in the red and blue warning lamps is a 3-level alarm, the brightness flashing in the red and blue warning lamps is a 2-level alarm accompanied by a medium-volume alarm, and the brightness flashing in the red and blue warning lamps is a 1-level alarm accompanied by a high-volume alarm. Unmanned aerial vehicle combines early warning grade and dangerous grade to judge and sends out reputation alarm grade, and concrete judgement mode is: and the sum of the early warning level and the danger level is less than 4, the alarm of level 1 is sent, the sum of the early warning level and the danger level is between 4 and 6 (including 4 and 6), the alarm of level 2 is sent, and the sum of the early warning level and the danger level is more than 6, and the alarm of level 3 is sent.
The beneficial effects of the further scheme are as follows: judge unusual action by unmanned aerial vehicle, foresee danger in advance, remind other personnel of target simultaneous warning, initiatively send out sound, light alarm when the pedestrian because the unable operation cell-phone of external reason, provide the warning effect, provide the protection for the pedestrian.
Drawings
Fig. 1 is an overall structure diagram of a night pedestrian safety early warning device and method based on an unmanned aerial vehicle.
Fig. 2 is a schematic view of a visual system structure of the night pedestrian safety early warning device and method based on the unmanned aerial vehicle.
Fig. 3 is a schematic structural diagram of a flight control system of the night pedestrian safety early warning device and method based on the unmanned aerial vehicle.
Fig. 4 is a schematic diagram of main functions of a mobile phone APP of the night pedestrian safety early warning device and method based on the unmanned aerial vehicle.
Fig. 5 is a schematic diagram of main steps of a night pedestrian safety early warning device and method based on an unmanned aerial vehicle.
Fig. 6 is a flowchart of target confirmation through a mobile phone identifier in the night pedestrian safety early warning device and method based on the unmanned aerial vehicle of the present invention.
Fig. 7 is a target tracking flow chart in the night pedestrian safety early warning device and method based on the unmanned aerial vehicle of the invention.
Fig. 8 is a flow chart of the night pedestrian safety early warning method and device based on the unmanned aerial vehicle for emitting acousto-optic early warning.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
The first embodiment is as follows:
as shown in fig. 1, a night pedestrian safety early warning device based on an unmanned aerial vehicle comprises an unmanned aerial vehicle body, a flight control system, a vision system, a lighting and alarm system, a ground station system, a cloud server and a mobile phone APP; visual system, flight control system, illumination and alarm system set up on unmanned aerial vehicle organism center, ground station system wireless communication visual system, visual system serial communication flight control system, cell-phone APP and ground station system pass through the GPRS communication.
As shown in fig. 2, the infrared vision system of the unmanned aerial vehicle body comprises an embedded platform Jetson TX2, a thermal infrared imager FLIR TAU2, a high definition camera, a video capture card and a picture transmission system; the thermal infrared imager FLIR TAU2 and the high-definition camera are respectively connected with the video acquisition card and the image transmission system; in the graph transmission system communication ground station system, the video acquisition card is connected with an embedded platform Jetson TX2, and the embedded platform Jetson TX2 is connected with a flight controller.
As shown in fig. 3, the flight control system comprises a microcontroller STM32F427, a brushless motor, an electronic speed regulator, a gyroscope, an electronic compass, an accelerometer, a barometer, a GPS module and a wireless communication module, wherein the microcontroller STM32F427 is respectively connected with the brushless motor, the electronic speed regulator, the gyroscope, the electronic compass, the accelerometer, the barometer, the GPS module and the wireless communication module.
As shown in fig. 4, the functions of the mobile phone APP mainly include communicating with a ground station, calling an unmanned aerial vehicle, sharing real-time location information, and displaying a special identifier for the unmanned aerial vehicle to recognize.
Example two:
as shown in fig. 5, a night pedestrian safety early warning method based on an unmanned aerial vehicle includes the following steps:
step S1: the pedestrian calls the unmanned aerial vehicle through the mobile phone APP;
step S2: the ground station transports the unmanned aerial vehicle out of the containing box after receiving the call, and sends a take-off instruction and a flight track to the unmanned aerial vehicle;
step S3: the aircraft flies to the sky of a target according to a flight path given by the ground station, and the pedestrian information is searched by using an infrared camera;
step S4: after the unmanned aerial vehicle detects the pedestrian, the high-definition motion camera is used for detecting identification information around the pedestrian, whether the identification is matched or not is confirmed to the ground station, if so, the target recognition work is finished, and if not, the step S3 is returned to continue searching around the target coordinate point;
step S5: the unmanned aerial vehicle tracks a target and detects abnormal behaviors through the infrared camera and GPS data, and simultaneously transmits a real-time video shot by the high-definition camera back to the ground station and uploads the real-time video to the server through the ground station;
step S6: the unmanned aerial vehicle continuously tracks the target, the unmanned aerial vehicle judges early warning levels according to the geographic position in the tracking process, if abnormal behaviors are detected, specific sound and light alarms are sent out according to different early warning levels, and pedestrians can also select to compensate the light intensity and send out the sound and light alarms or not through the mobile phone APP;
step S7: when a user finishes a task through a mobile phone APP or the electric quantity of the unmanned aerial vehicle is insufficient, the unmanned aerial vehicle requests to return to a ground station, after confirmation of the ground station, the unmanned aerial vehicle returns according to a given flight path, and when the electric quantity is insufficient and the unmanned aerial vehicle returns, the ground station sends out another unmanned alternative work;
step S8: after the unmanned aerial vehicle that navigates back descends at the appointed sign position of ground satellite station, convey it by the ground satellite station and charge the containing box, wait for next task.
Claims (9)
1. A night pedestrian safety early warning device based on an unmanned aerial vehicle is characterized by comprising an unmanned aerial vehicle body, a flight control system, a vision system, a lighting and alarm system, a ground station system, a cloud server and a mobile phone APP; the visual system and the flight control system are both built in the center of the unmanned aerial vehicle body, the ground station system is in wireless communication connection with the flight control system, the ground station system is in wireless communication connection with the visual system, and the visual system is in serial communication connection with the flight control system.
2. The unmanned-aerial-vehicle-based nighttime pedestrian safety warning device of claim 1, wherein the vision system comprises an embedded platform Jetson TX2, a thermal infrared imager FLIR TAU2, a high-definition motion camera, a video capture card and a picture transmission system; the image transmission system is in communication connection with a ground station system, the video acquisition card is connected with an embedded platform Jetson TX2, and the embedded platform Jetson TX2 is connected with a flight control module.
3. The unmanned aerial vehicle-based night pedestrian safety warning device of claim 1, wherein the flight control system comprises a microcontroller STM32F427, a brushless motor, an electronic governor, a gyroscope, an electronic compass, an accelerometer, a barometer, a GPS module and a GPRS wireless communication module, and the microcontroller STM32F427 is connected with the brushless motor, the electronic governor, the gyroscope, the electronic compass, the accelerometer, the barometer, the GPS module and the GPRS wireless communication module respectively.
4. The night pedestrian safety warning device based on the unmanned aerial vehicle as claimed in claim 1, wherein the ground station system communicates with the mobile phone APP, the cloud server and the unmanned aerial vehicle through GPRS, the ground station system can be arranged on a roof or a balcony, and the ground station system is divided into an unmanned aerial vehicle transmission part, an unmanned aerial vehicle storage box, a wireless charging part and a communication controller.
5. The ground station system of claim 4, wherein the platform with the special mark is used to guide the unmanned aerial vehicle to land, and the platform and the unmanned aerial vehicle are transmitted to the unmanned aerial vehicle storage box by the transmission mechanism, wherein the unmanned aerial vehicle storage box has a rainproof function and provides wireless charging for the unmanned aerial vehicle.
6. The ground station system of claim 4, wherein the system is configured to coordinate information transfer between the mobile phone APP and the unmanned aerial vehicle, and upload the video to the cloud server.
7. The unmanned-aerial-vehicle-based night pedestrian safety warning method according to claim 1, comprising the steps of:
step S1: the pedestrian calls the unmanned aerial vehicle through the mobile phone APP;
step S2: the ground station pushes the unmanned aerial vehicle out of the containing box after receiving the call, and sends a take-off instruction and a flight track to the unmanned aerial vehicle;
step S3: the aircraft flies to the sky of a target according to a flight path given by the ground station, and the pedestrian information is searched by using an infrared camera;
step S4: after the unmanned aerial vehicle detects the pedestrian, the high-definition motion camera is used for detecting identification information around the pedestrian, whether the identification is matched or not is confirmed to the ground station, if so, the target recognition work is finished, and if not, the step S3 is returned to continue searching around the target coordinate point;
step S5: the unmanned aerial vehicle tracks a target and detects abnormal behaviors through the infrared camera and GPS data, and simultaneously transmits a real-time video shot by the high-definition camera back to the ground station and uploads the real-time video to the server through the ground station;
step S6: the unmanned aerial vehicle continuously tracks the target, the unmanned aerial vehicle judges early warning levels according to the geographic position in the tracking process, if abnormal behaviors are detected, specific sound and light alarms are sent out according to different early warning levels, and pedestrians can also select to compensate the light intensity and send out the sound and light alarms or not through the mobile phone APP;
step S7: when a user finishes a task through a mobile phone APP or the electric quantity of the unmanned aerial vehicle is insufficient, the unmanned aerial vehicle requests to return to a ground station, after confirmation of the ground station, the unmanned aerial vehicle returns according to a given flight path, and when the electric quantity is insufficient and the unmanned aerial vehicle returns, the ground station sends out another unmanned alternative work;
step S8: after the unmanned aerial vehicle that navigates back descends at the appointed sign position of ground satellite station, convey it by the ground satellite station and charge the containing box, wait for next task.
8. The night pedestrian safety warning method based on the unmanned aerial vehicle as claimed in claim 7, step S5, wherein the specific steps are as follows:
c1, obtaining the target position according to the detected result in the step A4;
c2, extracting target characteristics to obtaindDimensional characteristicsfTraining is carried out to obtain a filter templateHThe function used to train the model is:
in the formula,
is the two-dimensional DFT of each dimension of the feature f, G is the two-dimensional DFT of the response constructed by the gaussian function;
c3, predicting the target position in the next frame of image by combining GPS data, extracting characteristic z, calculating response y by using the trained model, wherein the maximum value position of the response is the center position of the new target, and the response calculation formula is as follows:
wherein,
is the two-dimensional DFT of feature z;
and C4, estimating the current position of the target according to the target position, the current GPS position and the last GPS position in the image, controlling the unmanned aerial vehicle to fly, updating the filter template, and calculating the response of the next frame.
9. The pedestrian safety warning method at night based on the unmanned aerial vehicle as claimed in claim 7, wherein the steps S5 and S6 are as follows:
d1, acquiring the early warning level of the current section;
d2, continuously detecting and tracking other pedestrians around the target;
d3, judging the states of other pedestrians to obtain the danger levels of the pedestrians;
d4, sending out sound and light alarm according to the early warning level;
in step D1, the early warning level is classified into 4 levels, and the levels required to be early warned are preset according to different regions: the early warning grade of school districts and road sections with other monitoring devices is 4, the early warning grade of urban and rural road sections without monitoring is 3, the early warning grade of remote roads without monitoring is 2, and the early warning grade of road sections with crime behaviors is 1.
In step D3, the other pedestrian states include 5 danger levels, for example: the danger level of the situation that no other pedestrians are around the tracking target is 5, the danger level that the other pedestrians and the tracking target always keep following at a certain distance is 4, the danger level that the other pedestrians slowly approach the tracking target is 3, the danger level of the situation that the other pedestrians quickly approach the tracking target is 2, and the danger level of the situation that the other pedestrians and the tracking target send a physical conflict is 1.
In step D4, the audible and visual alarms are classified into 3 levels, the brightness flashing in the red and blue warning lamps is a 3-level alarm, the brightness flashing in the red and blue warning lamps is a 2-level alarm accompanied by a medium-volume alarm, and the brightness flashing in the red and blue warning lamps is a 1-level alarm accompanied by a high-volume alarm. Unmanned aerial vehicle combines early warning grade and dangerous grade to judge and sends out reputation alarm grade, and concrete judgement mode is: and the sum of the early warning level and the danger level is less than 4, the alarm of level 1 is sent, the sum of the early warning level and the danger level is between 4 and 6 (including 4 and 6), the alarm of level 2 is sent, and the sum of the early warning level and the danger level is more than 6, and the alarm of level 3 is sent.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811586153.3A CN111369760A (en) | 2018-12-25 | 2018-12-25 | Night pedestrian safety early warning device and method based on unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811586153.3A CN111369760A (en) | 2018-12-25 | 2018-12-25 | Night pedestrian safety early warning device and method based on unmanned aerial vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111369760A true CN111369760A (en) | 2020-07-03 |
Family
ID=71211364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811586153.3A Pending CN111369760A (en) | 2018-12-25 | 2018-12-25 | Night pedestrian safety early warning device and method based on unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111369760A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113242409A (en) * | 2021-04-26 | 2021-08-10 | 深圳市安星数字系统有限公司 | Night vision early warning method and device based on unmanned aerial vehicle, unmanned aerial vehicle and storage medium |
| CN113358100A (en) * | 2021-05-25 | 2021-09-07 | 电子科技大学 | Embedded unmanned aerial vehicle real-time target recognition system with YOLO4 improved algorithm |
| CN113741516A (en) * | 2021-08-30 | 2021-12-03 | 中国科学院地理科学与资源研究所 | Multi-unmanned aerial vehicle stacking operation method and system, storage medium and electronic equipment |
| CN113900160A (en) * | 2021-10-22 | 2022-01-07 | 北京登火汇智科技有限公司 | Meteorological detection equipment |
-
2018
- 2018-12-25 CN CN201811586153.3A patent/CN111369760A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113242409A (en) * | 2021-04-26 | 2021-08-10 | 深圳市安星数字系统有限公司 | Night vision early warning method and device based on unmanned aerial vehicle, unmanned aerial vehicle and storage medium |
| CN113242409B (en) * | 2021-04-26 | 2023-09-12 | 国网安徽省电力有限公司天长市供电公司 | Night vision early warning method and device based on unmanned aerial vehicle, unmanned aerial vehicle and storage medium |
| CN113358100A (en) * | 2021-05-25 | 2021-09-07 | 电子科技大学 | Embedded unmanned aerial vehicle real-time target recognition system with YOLO4 improved algorithm |
| CN113741516A (en) * | 2021-08-30 | 2021-12-03 | 中国科学院地理科学与资源研究所 | Multi-unmanned aerial vehicle stacking operation method and system, storage medium and electronic equipment |
| CN113900160A (en) * | 2021-10-22 | 2022-01-07 | 北京登火汇智科技有限公司 | Meteorological detection equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111369760A (en) | Night pedestrian safety early warning device and method based on unmanned aerial vehicle | |
| CN110674746B (en) | Method and device for realizing high-precision cross-mirror tracking by using video spatial relationship assistance, computer equipment and storage medium | |
| CN109804367B (en) | Distributed video storage and search using edge computation | |
| CN107274695B (en) | Intelligent lighting system, intelligent vehicle and vehicle driving assisting system and method thereof | |
| US20210027060A1 (en) | Person search system | |
| US9970774B2 (en) | Automatic content analysis method and system | |
| US20150179088A1 (en) | Traffic light detecting system and method | |
| JP7420734B2 (en) | Data distribution systems, sensor devices and servers | |
| Sarkar et al. | Intelligent drone-based surveillance: application to parking lot monitoring and detection | |
| CN112750170B (en) | Fog feature recognition method and device and related equipment | |
| KR102161917B1 (en) | Information Processing System and method for rescue in mountain area using UAS | |
| CN105741466A (en) | Aircraft for environmental protection monitoring | |
| CN108320497B (en) | Method and device for detecting behavior of pedestrian running red light and computer readable storage medium | |
| CN113205515A (en) | Target detection method, device and computer storage medium | |
| CN105761275A (en) | Fire-fighting early warning aircraft with binocular visual structure | |
| CN108881846B (en) | Information fusion method and device and computer readable storage medium | |
| US20140169628A1 (en) | Method and Device for Detecting the Gait of a Pedestrian for a Portable Terminal | |
| CN111422128B (en) | Server, in-vehicle apparatus, vehicle, storage medium, and information providing method | |
| CN109863540A (en) | Quick responding method and system based on autopilot facility, storage medium | |
| KR101865835B1 (en) | Monitoring system for a flying object | |
| US20230319397A1 (en) | Information processing apparatus, information processing method, and program | |
| CN107292818B (en) | Automatic positioning system and method for line capture device based on panoramic camera | |
| JP2022124993A (en) | Identification device, identification program and identification method | |
| CN114592411A (en) | Carrier parasitic type intelligent road damage inspection method | |
| CN207133979U (en) | A kind of traffic events based on car networking intelligently put to the proof device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200703 |