阅读说明：本技术 一种定位监控方法及装置 (Positioning monitoring method and device ) 是由 刘若鹏 栾琳 季春霖 杨亮 于 2019-12-18 设计创作，主要内容包括：本发明提供了一种定位监控方法及装置,方法包括：主控板获取云台水平朝向的视角D<Sub>h</Sub>和垂直朝向的视角D<Sub>v</Sub>；主控板通过内置的检测模块识别被摄物身份；主控板将可见光机芯焦距变焦至预设焦距,通过双目测距法计算被摄物与云台在同一水平面下的垂线距离L；主控板通过与其连接的北斗模块获取云台当前的坐标；主控板将云台水平朝向的视角D<Sub>h</Sub>、被摄物与云台在同一水平面下的垂线距离L、以及云台当前的坐标上传至监控平台,监控平台绘制被摄物的地理位置预设焦距通过对传统热成像云台做成像机制改进,加入北斗、九轴惯性传感器,集成深度学习算法识别模块,计算获取被摄物准确地理坐标,大幅提升出警效率,尽可能减少财产损失。(The invention provides a positioning monitoring method and a positioning monitoring device, wherein the method comprises the following steps: main control board acquires visual angle D of horizontal orientation of holder h And a vertically oriented viewing angle D v (ii) a The main control board identifies the identity of a shot object through a built-in detection module; the main control board zooms the focal length of the visible light machine core to a preset focal length, and the distance L of a vertical line of the shot object and the holder under the same horizontal plane is calculated through a binocular distance measurement method; the main control board acquires the current coordinate of the holder through a Beidou module connected with the main control board; visual angle D of horizontal orientation of holder by main control board h The vertical distance L between the shot object and the holder under the same horizontal plane, and the holderThe front coordinates are uploaded to a monitoring platform, the monitoring platform draws the preset focal length of the geographic position of the shot object, the traditional thermal imaging holder is improved through a camera system, a Beidou and nine-axis inertial sensor is added, a deep learning algorithm identification module is integrated, the accurate geographic coordinates of the shot object are calculated and obtained, the alarm efficiency is greatly improved, and property loss is reduced as far as possible.)

1. A method of location monitoring, comprising:

main control board acquires visual angle D of horizontal orientation of holder_hAnd a vertically oriented viewing angle D_v；

The main control board identifies the identity of a shot object through a built-in detection module;

the main control board zooms the focal length of the visible light machine core to a preset focal length, and the distance L of a vertical line of the shot object and the holder under the same horizontal plane is calculated through a binocular distance measurement method;

the main control board obtains the current coordinate (X) of the holder through the Beidou module connected with the main control board_A,Y_A）；

Visual angle D of horizontal orientation of holder by main control board_hThe vertical distance L between the shot object and the holder under the same horizontal plane, and the current coordinate (X) of the holder_A,Y_A) Uploading the geographic position of the shot object to a monitoring platform, and drawing the geographic position of the shot object by the monitoring platform;

the main control board identifies the identity of the shot object through a built-in detection module and comprises the following steps:

the visible light movement carries out color imaging on the collected shot object, simultaneously, the image output after the color imaging is carried out is sent to a deep learning algorithm module of a main control board CPU, the algorithm module distinguishes the shot object and intercepts a picture from the output image, the intercepted picture is compared with a shot object database stored in a local flash, and the identity of the shot object is confirmed;

or the main control board identifies the identity of the shot object through a built-in detection module, and the method comprises the following steps:

after finding a shot object with the temperature within a preset temperature threshold range in advance by the thermal imaging core, starting the visible light core and the laser light supplement lamp to carry out black-and-white imaging on the shot object, sending a black-and-white image to the CPU deep learning algorithm module after passing through the ISP, distinguishing the shot object by the algorithm module, intercepting a picture from an output image, comparing the intercepted picture with a shot object database stored in local flash, and confirming the identity of the shot object.

2. The positioning monitoring method according to claim 1, wherein the main control board obtains a view angle D of the horizontal orientation of the pan/tilt head_hAnd a vertically oriented viewing angle D_vThe method comprises the following steps:

according to the data of the nine-axis inertial sensor, the holder obtains a north positive point and a horizontal reference point, and the initial horizontal visual angle of the holder is set at the north positive point.

3. The positioning monitoring method according to claim 2, wherein before the pan-tilt obtaining the north positive point and the horizontal reference point based on the nine-axis inertial sensor data, further comprising: and (4) powering on the cradle head for self-checking.

4. The positioning monitoring method according to claim 1, wherein the main control board obtains a view angle D of the horizontal orientation of the pan/tilt head_hAnd a vertically oriented viewing angle D_vThe method comprises the following steps:

assuming that the motor of the tripod head rotates one circle and walks STP1 steps totally, when the horizontal motor of the tripod head walks A1 steps, A1 is less than STP1, and the horizontal direction visual angle D of the tripod head_h= A1/STP1 × 360 °, A1 is calculated from 0 after the pan head rotates more than one turn, and the angle of view of the pan head vertical orientation is D_v=A2/STP2×Angle_VMaxA2 is the current walking step number of the vertical motor, STP2 is the total walking step number of the vertical motor, Angle_VMaxThe maximum angle of walking is vertical to the motor.

5. The positioning monitoring method according to claim 1, wherein calculating the vertical distance L between the subject and the pan/tilt head under the same horizontal plane by a binocular ranging method comprises:

assuming that a point P is a shot object, PL is an imaging point of the shot object on an image plane of a thermal imaging core, PR is an imaging point of the shot object on an image plane of a visible light core, L1 is a thermal imaging image plane width, L2 is a visible light imaging image plane width, OL is an optical center of the thermal imaging core, OR is an optical center of the visible light core, b is a distance between the optical center of the thermal imaging core OL and an optical center of the visible light core OR, namely OLOR = b, an edge distance between PL and the image plane of the thermal imaging core is XL, an edge distance between PR and the image plane of the visible light core is XR, focal lengths of the thermal imaging core and the visible light core are both f, PLPR is a line between the point PL and the point PR, and Z is a straight line distance between the length of the shot object and a pan-tilt head:

PLPR/(Z-f) = OLOR/Z, where PLPR = b- (XL- (L1/2)) - ((L2/2) -XR), then L is:

6. The positioning monitoring method according to claim 1, wherein the mapping of the accurate geographical position of the subject is: let P point be the object, P point longitude and latitude be P (Xp, Yp), Xp = X_A+L×cos (D_h)，Yp=Y_A+L×sin(D_h)。

7. The location monitoring method of claim 4, wherein the predetermined temperature threshold ranges from 30-40 degrees.

8. A positioning monitoring device, comprising: the device comprises a holder double-bin module and a monitoring platform which are connected through a network, wherein the monitoring platform is provided with a GIS map, the holder double-bin module comprises a control module and a laser light supplementing lamp, a zooming visible light camera, a fixed-focus thermal imaging core, a Beidou module, a nine-axis inertial sensor, a holder horizontal motor and a holder vertical motor which are electrically connected with the control module, and the device executes the positioning monitoring method according to any one of claims 1 to 7.

9. The positioning monitoring device of claim 8, wherein the control module comprises an MCU, a CPU and an ISP which are electrically connected, and the control module is connected with the monitoring platform through the CPU.

10. The positioning monitoring device according to claim 8, wherein the Beidou module is connected with the control module through a serial port.

11. The positioning monitoring device of claim 8, wherein the nine-axis inertial sensor is coupled to the control module via a serial port.

12. The positioning monitoring device according to claim 8, wherein the control module is connected to the laser fill-in light through IO control.

13. The position monitoring device of claim 8, wherein the control module interacts YUV data with the zoom visible camera.

14. The positioning monitoring device according to claim 8, wherein the control module is connected to the fixed focus thermal imaging engine through an LVDS line.

15. The positioning monitoring device according to claim 8, wherein the pan/tilt horizontal motor is configured to control the pan/tilt to move in a horizontal direction.

16. The positioning monitoring device of claim 8, wherein the pan/tilt/vertical motor is configured to control the pan/tilt/vertical movement.

Technical Field

The invention relates to the technical field of monitoring, in particular to a positioning monitoring device.

Background

The traditional thermal imaging cloud platform is generally placed at a height-control point, generally on the top of a mountain or a super high-rise building, is monitored at 360 degrees, has a large range, and the orientation of a lens is not related to a geodetic coordinate system, so that people or objects in a monitored image cannot be identified and distinguished, and shot objects cannot be identified. Early warning cannot be achieved in advance, and investigation can be assisted afterwards.

Disclosure of Invention

The invention aims to solve the technical problem of providing a positioning monitoring device, which improves the imaging mechanism of the traditional thermal imaging holder, adds a Beidou and nine-axis inertial sensor and an integrated deep learning algorithm identification module, and calculates and obtains the accurate geographic coordinates of a shot object by the method, thereby greatly improving the alarm efficiency and reducing the property loss as much as possible.

To solve the foregoing technical problem, in one aspect, an embodiment of the present invention provides a positioning monitoring method, including:

main control board acquires visual angle D of horizontal orientation of holder_hAnd a vertically oriented viewing angle D_v；

The main control board identifies the identity of a shot object through a built-in detection module;

the main control board zooms the focal length of the visible light machine core to a preset focal length, and the distance L of a vertical line of a shot object and the holder under the same horizontal plane is calculated through a binocular ranging method;

the main control board obtains the current coordinate (X) of the holder through the Beidou module connected with the main control board_A,Y_A）；

Visual angle D of horizontal orientation of holder by main control board_hThe vertical distance L between the shot object and the holder under the same horizontal plane, and the current coordinate (X) of the holder_A,Y_A) Uploading the geographic position of the shot object to a monitoring platform, and drawing the geographic position of the shot object by the monitoring platform;

the main control board identifies the identity of the shot object through a built-in detection module and comprises the following steps:

the visible light movement carries out color imaging on the collected shot object, simultaneously, the image output after the color imaging is carried out is sent to a deep learning algorithm module of a main control board CPU, the algorithm module distinguishes the shot object and intercepts pictures from the output image, the intercepted pictures are compared with a shot object database stored in a local flash, and the identity of the shot object is confirmed.

Preferably, the horizontal orientation visual angle D of the holder is acquired_hAnd a vertically oriented viewing angle D_vThe method comprises the following steps: according to the data of the nine-axis inertial sensor, the holder obtains a north positive point and a horizontal reference point, and the initial horizontal visual angle of the holder is set at the north positive point.

Preferably, according to the nine-axis inertial sensor data, before the pan-tilt obtaining the north positive point and the horizontal reference point, the method further includes: and (4) powering on the cradle head for self-checking.

Preferably, the main control board recognizing the identity of the subject through the built-in detection module includes: after finding a shot object with the temperature within a preset temperature threshold range in advance by the thermal imaging core, starting the visible light core and the laser light supplement lamp to carry out black-and-white imaging on the shot object, sending a black-and-white image to the CPU deep learning algorithm module after passing through the ISP, distinguishing the shot object by the algorithm module, intercepting a picture from an output image, comparing the intercepted picture with a shot object database stored in local flash, and confirming the identity of the shot object.

Preferably, when the pan/tilt head moves, the view angle D of the pan/tilt head horizontal orientation is obtained_hAnd a vertically oriented viewing angle D_vThe method comprises the following steps: assuming that the motor of the tripod head rotates one circle and walks STP1 steps totally, when the horizontal motor of the tripod head walks A1 steps, A1 is less than STP1, and the horizontal direction visual angle D of the tripod head_h= A1/STP1 × 360 °, A1 is calculated from 0 after the pan head rotates more than one turn, and the angle of view of the pan head vertical orientation is D_v=A2/STP2× Angle_VMaxA2 is the current walking step number of the vertical motor, STP2 is the total walking step number of the vertical motor, Angle_VMaxThe maximum angle of walking is vertical to the motor.

Preferably, the calculating the vertical distance L of the subject to the pan/tilt head under the same horizontal plane by the binocular ranging method includes: assuming that a point P is a shot object, PL is an imaging point of the shot object on an image plane of a thermal imaging core, PR is an imaging point of the shot object on an image plane of a visible light core, L1 is a thermal imaging image plane width, L2 is a visible light imaging image plane width, OL is an optical center of the thermal imaging core, OR is an optical center of the visible light core, b is a distance between the optical center of the thermal imaging core OL and an optical center of the visible light core OR, namely OLOR = b, an edge distance between PL and the image plane of the thermal imaging core is XL, an edge distance between PR and the image plane of the visible light core is XR, focal lengths of the thermal imaging core and the visible light core are both f, PLPR is a line between the point PL and the point PR, and Z is a straight line distance between the length of the shot object and a pan-tilt head:

PLPR/(Z-f) = OLOR/Z, where PLPR = b- (XL- (L1/2)) - ((L2/2) -XR), then L is:

wherein

。

Preferably, the exact geographical location of the subject is plotted as: let P point be the object, P point longitude and latitude be P (Xp, Yp), Xp = X_A+L×cos(D_h)，Yp=Y_A+L×sin(D_h)。

In another aspect, an embodiment of the present invention provides a positioning monitoring apparatus, including: the device comprises a tripod head double-bin module and a monitoring platform which are connected through a network, wherein the monitoring platform is provided with a GIS map, the tripod head double-bin module comprises a control module and a laser light supplementing lamp, a zooming visible light camera, a fixed-focus thermal imaging core, a Beidou module, a nine-axis inertial sensor, a tripod head horizontal motor and a tripod head vertical motor which are electrically connected with the control module, and the device executes the positioning monitoring method.

Preferably, the control module comprises an MCU, a CPU and an ISP which are electrically connected, and the control module is connected with the monitoring platform through the CPU.

Preferably, the Beidou module is connected with the control module through a serial port.

Preferably, the nine-axis inertial sensor is connected with the control module through a serial port.

Preferably, the control module is connected with the laser light supplement lamp through IO control.

Preferably, the control module interacts YUV data with the zoom visible light camera.

Preferably, the control module is connected with the fixed-focus thermal imaging movement through an LVDS line.

Preferably, the horizontal motor of the pan/tilt head is used for controlling the pan/tilt head to move in the horizontal direction.

Preferably, the vertical motor of the pan/tilt head is used for controlling the pan/tilt head to move in the vertical direction.

Compared with the prior art, the technical scheme has the following advantages: the traditional thermal imaging holder is improved in camera system, the Beidou and nine-axis inertial sensors are added, the deep learning algorithm identification module is integrated, and the accurate geographic coordinates of the shot object are calculated and obtained by the method, so that the alarm efficiency is greatly improved, and the property loss is reduced as much as possible.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.

Fig. 1 is a schematic view of binocular ranging.

Fig. 2 is a geometrical diagram of the distance between the measured person and the device.

FIG. 3 is a logic block diagram of the positioning monitoring device of the present invention.

Detailed description of the preferred embodiments.

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.