CN213123337U

CN213123337U - Traffic detection device

Info

Publication number: CN213123337U
Application number: CN202021428794.9U
Authority: CN
Inventors: 王一民; 章庆
Original assignee: Nanjing Hurys Intelligent Technology Co Ltd
Current assignee: Nanjing Hurys Intelligent Technology Co Ltd
Priority date: 2020-07-20
Filing date: 2020-07-20
Publication date: 2021-05-04
Anticipated expiration: 2030-07-20

Abstract

The utility model provides a traffic detection device, including sensor module, storage module, communication module, clock module, main control unit respectively with sensor module storage module communication module the clock module links to each other, sensor module comprises millimeter wave radar sensor and video sensor. The utility model has the advantages that: the utility model discloses put these two perception front ends of millimeter wave radar sensor and video sensor in same equipment, alleviateed the degree of difficulty of installation and debugging, reduced the maintenance cost.

Description

Traffic detection device

Technical Field

The utility model relates to the field of electronic technology, especially, relate to a traffic detection device.

Background

Most of the existing traffic detection systems adopt video sensors, and a single video detection mode has low accuracy on detection effect, large time delay of image processing, and the accuracy is easily influenced by environments such as rain, fog and the like. And other types of sensors, such as millimeter wave radar, geomagnetic, laser radar and the like, are added to the components in the system afterwards, and the advantages of different sensors are utilized to perform multi-sensor data fusion, so that the detection performance of the system is greatly improved. The millimeter wave radar sensor can detect the position and speed information of a target in real time, the data processing capacity reaches 20 times per second, the environmental suitability is strong, the sensor can work all day long, and the defect that the sensor cannot be visualized is overcome. The video sensor can process image information, if the image is analyzed and calculated, a long time is needed for transcoding, real-time response cannot be achieved, and the environmental adaptability is not high.

By utilizing the advantages of the two sensors, the millimeter wave radar sensor and the video sensor can be used as detection front ends to perform data fusion processing. In the current system, the millimeter wave radar sensor and the video sensor need to be associated with the coordinate systems of the two sensors when information fusion is performed due to different installation positions of the millimeter wave radar sensor and the video sensor, the coordinate association of the two sensors is related to the relative positions of the two sensors, and if one sensor slightly moves, the coordinate association needs to be re-associated. Because two sensors often receive the shake in use, the mounted position has the deviation after a period of time, leads to the unfixed of distance and angle, needs regularly to carry out the coordinate again and matches, so the installation and debugging degree of difficulty is big, often needs to maintain.

SUMMERY OF THE UTILITY MODEL

To the problem that prior art structure installation and debugging is complicated and work efficiency is low, the utility model provides a traffic detection device.

The utility model provides a traffic detection device, including sensor module, storage module, communication module, clock module, main control unit respectively with sensor module storage module communication module the clock module links to each other, sensor module comprises millimeter wave radar sensor and video sensor.

As the utility model discloses a further improvement, this traffic detection device still includes controller LAN interface, image interface, the road surface target information that millimeter wave radar sensor will gather passes through controller LAN interface connection main control unit, video sensor passes through image interface connection with the road surface image of gathering main control unit.

As a further improvement of the present invention, the main controller includes an ARM microprocessor and an embedded neural network processor, and the embedded neural network processor is responsible for processing image data, identifying the type of the target, and superimposing the target information collected by the millimeter wave radar sensor in the video image; the ARM microprocessor is responsible for counting information of all traffic flows and identifying traffic events; the main controller fuses data information received in real time from the millimeter wave radar sensor and the data information detected by the video sensor, and outputs complete information of the same target to the system platform.

As a further improvement of the present invention, the storage module includes an embedded multimedia storage device and an SD card, the embedded multimedia storage device is used for storing an operating system, and the SD card is used for storing a traffic flow database and traffic event information.

As a further improvement of the present invention, the clock module is connected to the main controller through an I2C bus, and the clock module is used for recording time.

As a further improvement of the utility model, communication module includes USB interface, RS232 interface, RS485 interface and RJ45 interface, main control unit passes through communication module receives and dispatches traffic data to system platform.

As a further improvement of the present invention, the traffic detection device further comprises a power module, wherein the power module is connected to the main controller, and the power module connected to the main controller supplies power to the millimeter wave radar sensor; the controller area network comprises a controller and a transceiver connected with the controller, the millimeter wave radar sensor transmits collected road surface target information to the controller through the transceiver, and the controller converts the road surface target information into an SPI signal and transmits the SPI signal to the main controller.

As a further improvement of the present invention, the transceiver of the controller area network employs tja1050 chip, and the controller of the controller area network employs mcp2515 chip.

As a further improvement of the utility model, the image interface adopts the mipi csi-2 interface, and the clock module adopts the ISL1208 chip.

The utility model has the advantages that: the utility model discloses put these two perception front ends of millimeter wave radar sensor and video sensor in same equipment, alleviateed the degree of difficulty of installation and debugging, reduced the maintenance cost.

Drawings

FIG. 1 is a schematic block diagram of the present invention;

FIG. 2 is a schematic diagram of the interface between the millimeter wave radar sensor and the main controller;

fig. 3 is a schematic diagram of the interface between the video sensor and the main controller according to the present invention;

FIG. 4 is a circuit diagram of the clock module of the present invention;

fig. 5 is a schematic diagram of the millimeter wave radar sensor connected to the main controller through the controller area network interface.

Detailed Description

As shown in fig. 1, the utility model discloses a traffic detection device, including sensor module 20, storage module 30, communication module 50, clock module 40, main control unit 10 respectively with sensor module 20 storage module 30 communication module 50 clock module 40 links to each other, sensor module 20 comprises millimeter wave radar sensor 21 and video sensor 22, and millimeter wave radar sensor 21 and video sensor 22 are located a front end equipment.

The traffic detection device further comprises a controller area network interface and an image interface, the millimeter wave radar sensor 21 connects the collected road surface target information with the main controller 10 through the controller area network interface, and the video sensor 22 connects the collected road surface image with the main controller 10 through the image interface.

The storage module 30 comprises an embedded multimedia storage device 31 and an SD card 32, wherein the embedded multimedia storage device 31 is used for storing an operating system, and the SD card 32 is used for storing a traffic flow database and traffic event information.

The clock module 40 adopts an ISL1208 chip, the clock module 40 is connected with the main controller 10 through an I2C bus, the clock module 40 is used for recording time, when the equipment is not connected with a power supply, a button battery in the equipment supplies power to the clock module 40, so that the clock module 40 can still normally work, and when the equipment is powered on, the equipment time is ensured to be consistent with the current Beijing time. The ISL1208 is a low-power consumption RTC chip, the power supply range is 2.7V-5.5V, clock data can be stored in a user SRAM and read through an I2C bus, the accuracy of a system clock can be kept within a 0.2ppm range by linking a crystal oscillator of 32.768K outside the chip, and under the condition that a clock circuit is powered off and cannot work, the ISL1208 can provide about 400nA current through an external silver oxide battery to ensure that the time can be corrected when the RTC clock is powered off.

The communication module 50 includes a USB interface, an RS232 interface, an RS485 interface, and an RJ45 interface, and the main controller 10 transmits and receives traffic data to and from the system platform 60 through the communication module 50. The usb interface is used for programming programs and can also be used for upgrading programs through RS232 and RJ45, the RS485 interface is used for interacting data with a traffic signal machine, the RJ45 interface is a 100/1000M network interface, and video streams, pictures, radar real-time data, traffic flow information and traffic event information are output outwards through the network interface. And the RS485 interface is used for butting a bayonet camera and an intersection traffic control signal machine.

The traffic detection device also comprises a power supply module, wherein the power supply module is connected with the main controller 10, and the power supply module connected to the main controller 10 supplies power to the millimeter wave radar sensor 21; the controller area network comprises a controller and a transceiver connected with the controller, the millimeter wave radar sensor 21 transmits collected road surface target information to the controller through the transceiver, and the controller converts the road surface target information into an SPI signal and transmits the SPI signal to the main controller 10.

The transceiver of the controller area network adopts tja1050 chip, and the controller of the controller area network adopts mcp2515 chip.

The image interface adopts a mobile industry processor interface. The image interface adopts a mipi csi-2 interface. The video sensor 22 is connected with the main controller 10 through a MIPI CSI-2 interface, a MIPI CSI-2 plug-in terminal provides data and power supply, the CSI-2 is a second version of MIPI CSI, mainly comprises an application layer, a protocol layer and a physical layer, and supports 4-channel data transmission to the maximum extent, and the single-wire transmission speed is up to 1 Gb/s.

Millimeter wave radar sensor 21 and video sensor 22 are located a front end check out test set, have reduced installation and debugging work, and video sensor 22 is connected with main control unit through mipi interface, makes more clear and the memory capacity of pixel bigger, and power module makes the more stable work of circuit through increasing the function of power down protection.

The millimeter wave radar sensor 21 connects the collected information of the road vehicle to the main controller through a controller area network interface (CAN interface for short). As shown in FIG. 2, master controller 10 provides a 3-way SPI interface, and SPI-to-CAN uses a bus interface in which SPI2 is present. As shown in fig. 5, since the SPI2 bus level from the master controller 10(3519 core board) is 1.8V and the voltage of the chip used by us is 3.3V, a large voltage difference is present, which easily detects illegal voltages in level discrimination, the level conversion chips added with 1.8V and 3.3V between the mcp2515 chip and the master controller 10(3519 core board) facilitate level conversion. The converted SPI is 3.3V, the level meets the level requirement of an I/O of an mcp2515 chip, and the converted SPI is converted into a CAN _ TTL signal and transmitted to a CAN bus chip of TJA1042 from a physical interface of the CAN. The level conversion chip is convenient for people to convert the voltage difference into level and is used for power supply and power failure protection of each chip and each sensor in the equipment.

The video sensor 22 connects the collected road surface image to the main controller 10 through an image interface. The image interface adopts a mipi csi-2 interface. The video sensor 22 adopts an image interface, the video sensor 22 realizes the acquisition of video image data by a main control chip through a MIPI CSI-2 interface, and the CSI-2 is an MIPI CSI second version and mainly comprises an application layer, a protocol layer and a physical layer, and the maximum support is realized for 4-channel data transmission, and the single-wire transmission speed is up to 1 Gb/s. As shown in fig. 3, the main controller 10(3519 core board) provides 3 MIPI differential signals, and the product only uses one MIPI. MIPI0 comprises clock line and data line, MIPI _ RX0_ CK0_ P and MIPI _ RX0_ CK0_ N constitute MIPI0 clock differential pair. MIPI _ RX0_ D0_ P, MIPI _ RX0_ D0_ N, MIPI _ RX0_ D1_ P, MIPI _ RX0_ D1_ N, MIPI _ RX0_ D2_ P, MIPI _ RX0_ D2_ N, MIPI _ RX0_ D3_ P and MIPI _ RX0_ D3_ N form a data differential pair of MIPI 0. The MIPI0 differential signals are connected to the SENSOR through FPC flex cable terminals.

The main controller 10 includes an ARM microprocessor and an embedded neural Network Processor (NPU). The embedded neural Network Processor (NPU) is responsible for processing image data, identifying the type of the target, and superimposing the target information acquired by the millimeter wave radar sensor 21 in the video image. The ARM microprocessor is responsible for counting information of all traffic flows and identifying traffic events. The main controller 10 fuses the data information received in real time from the millimeter wave radar sensor 21 and the data information detected by the video sensor 22, and outputs the complete information of the same target to the system platform 60.

The memory module 30 is connected to the main controller 10, and the memory module 30 includes an embedded multimedia storage device 31(EMMC) and an SD card 32. The EMMC is used to store the operating system kernel and the file system. The SD card 32 is used to store traffic flow databases, traffic event information, pictures, and videos. And after the network is disconnected and then recovered, transmitting the data which is disconnected before to a background through the network.

The utility model has the advantages that: the utility model discloses put these two perception front ends of millimeter wave radar sensor and video sensor in same equipment, alleviateed the degree of difficulty of installation and debugging, reduced the maintenance cost. The radar sensor and the video sensor transmit signals with the main controller through the controller local area network interface and the image interface respectively, so that the stability and the reliability of the signals are guaranteed, the calculated amount of the system is reduced, the response time of the system is shortened, and the detection precision is improved. The video sensor adopts a mipi interface, so that the resolution of the picture is higher and the storage space of the picture is larger compared with the traditional USB interface; and a level conversion chip is added, so that signals can be transmitted more flexibly.

The foregoing is a more detailed description of the present invention, taken in conjunction with the specific preferred embodiments thereof, and it is not intended that the invention be limited to the specific embodiments shown and described. To the utility model belongs to the technical field of ordinary technical personnel, do not deviate from the utility model discloses under the prerequisite of design, can also make a plurality of simple deductions or replacement, all should regard as belonging to the utility model discloses a protection scope.

Claims

1. A traffic detection device characterized by: the device comprises a sensor module, a storage module, a communication module, a clock module and a main controller, wherein the main controller is respectively connected with the sensor module, the storage module, the communication module and the clock module, and the sensor module consists of a millimeter wave radar sensor and a video sensor; the clock module is connected with the main controller through an I2C bus, and the clock module is used for recording time.

2. The traffic detection device according to claim 1, characterized in that: the traffic detection device further comprises a controller local area network interface and an image interface, the millimeter wave radar sensor is used for connecting the collected road surface target information with the main controller through the controller local area network interface, and the video sensor is used for connecting the collected road surface image with the main controller through the image interface.

3. The traffic detection device according to claim 1, characterized in that: the main controller comprises an ARM microprocessor and an embedded neural network processor, the embedded neural network processor is responsible for processing image data, identifying the type of a target and superposing target information acquired by the millimeter wave radar sensor in a video image; the ARM microprocessor is responsible for counting information of all traffic flows and identifying traffic events; the main controller fuses data information received in real time from the millimeter wave radar sensor and the data information detected by the video sensor, and outputs complete information of the same target to the system platform.

4. The traffic detection device according to claim 1, characterized in that: the storage module comprises an embedded multimedia storage device and an SD card, wherein the embedded multimedia storage device is used for storing an operating system, and the SD card is used for storing a traffic flow database and traffic event information.

5. The traffic detection device according to claim 1, characterized in that: the communication module comprises a USB interface, an RS232 interface, an RS485 interface and an RJ45 interface, and the main controller receives and transmits traffic data to the system platform through the communication module.

6. The traffic detection device according to claim 2, characterized in that: the traffic detection device also comprises a power supply module, wherein the power supply module is connected with the main controller and supplies power to the millimeter wave radar sensor; the controller area network comprises a controller and a transceiver connected with the controller, the millimeter wave radar sensor transmits collected road surface target information to the controller through the transceiver, and the controller converts the road surface target information into an SPI signal and transmits the SPI signal to the main controller.

7. The traffic detection device of claim 6, wherein: the transceiver of the controller area network adopts tja1050 chip, and the controller of the controller area network adopts mcp2515 chip.

8. The traffic detection device according to claim 2, characterized in that: the image interface adopts a mipi csi-2 interface, and the clock module adopts an ISL1208 chip.