CN217505691U - Portable vehicle-mounted road disease detection equipment - Google Patents
Portable vehicle-mounted road disease detection equipment Download PDFInfo
- Publication number
- CN217505691U CN217505691U CN202221584739.8U CN202221584739U CN217505691U CN 217505691 U CN217505691 U CN 217505691U CN 202221584739 U CN202221584739 U CN 202221584739U CN 217505691 U CN217505691 U CN 217505691U
- Authority
- CN
- China
- Prior art keywords
- terminal host
- module
- power supply
- vehicle
- image
- 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.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The application discloses portable vehicle-mounted road disease detection equipment, which comprises a terminal host, a camera lens, a light supplement lamp array, an antenna, a power supply assembly and a magnetic suction bracket; the camera lens is fixedly arranged on one side of the front surface of the terminal host, and is used for collecting road ground pictures and transmitting the collected pictures to the terminal host; the antenna is arranged at the top of the terminal host and is connected with a communication positioning module in the terminal host to be in communication connection with external equipment; the power supply assembly is arranged on one side of the back surface of the terminal host and is connected with an in-vehicle power supply through a cigarette lighter plug to supply power to the equipment; the magnetic support is arranged at the bottom of the terminal host, the upper end of the support arm is connected with the terminal host, and the lower end of the support arm is connected with a magnetic fixing part fixed on the detection vehicle. The utility model discloses an image sensor and degree of depth study network identification model, supplementary GNSS locating information detects and fixes a position the road disease in real time, improves and patrols and examines efficiency, reduces artificial careless omission and the hidden danger that causes of participating in.
Description
Technical Field
The utility model relates to a road inspection field, in particular to portable on-vehicle road disease check out test set.
Background
Road disease detection plays an important role in road maintenance and repair, and currently, a manual inspection mode is mainly adopted, namely, an inspector drives a road administration maintenance inspection vehicle to carry out naked eye observation on the road surface of a governed road. When a disease condition occurs, the inspection personnel need to get off and take a picture and report the picture by using the hand-held terminal. But the polling personnel are easy to be tired and easily careless when observing on the vehicle for a long time; and the getting-off photographing has traffic hidden trouble and influences the normal operation of traffic.
In order to improve the inspection efficiency and reduce the careless omission and hidden danger caused by human participation, domestic and foreign enterprises and institutions also carry out the development work of various vehicle-mounted automatic pavement detection instruments. The inspection vehicle realizes the detection of the road by integrating various sensors such as three-dimensional laser, ground penetrating radar, a camera, a high-precision navigation terminal and the like. Various sensor data are mainly collected, stored and analyzed by a terminal (computer) in the vehicle and reported to a remote server. The system needs to modify vehicles (including systems of power supply, storage, navigation and the like), has high cost (about dozens to millions of special vehicles on the market), is mainly applied to road detection before large, medium and small road repairs, and is difficult to popularize in daily maintenance inspection.
In recent years, with the popularization of rear-mounted vehicle-mounted equipment such as a driver monitoring system and a vehicle data recorder, some enterprises also try to use the video acquisition equipment to perform maintenance and inspection on roads. However, the equipment is arranged in a vehicle, the visual field of a camera of the equipment is mainly focused on the right front of a road surface instead of being directly aligned to the road surface according to standard requirements, so that the measurement distortion is large and the precision is not high; in addition, because the camera is arranged at the position of the windshield, the image of the camera is easily affected by dirt on the windshield, reflection in the vehicle, reflection and the like, and the sampling precision required by the standard cannot be achieved.
After the vehicle-mounted terminal collects data of various sensors, two modes of cloud analysis or local analysis are generally adopted. The traditional cloud analysis has low computing capacity on the vehicle-mounted terminal, the terminal only needs to simply compress data and then stores and returns the data, and the cloud server performs disease analysis. But the requirements on cloud computing capacity, storage space, network communication flow and bandwidth are high, and the real-time performance is poor under the conditions of weak networks and network disconnection. The local analysis mode generally requires that a vehicle-mounted terminal has strong computing power, and particularly when a disease identification algorithm based on deep learning (artificial intelligent network model) is operated, the terminal needs to be provided with a special image analysis processor such as a GPU/NPU/VPU. Although the local analysis mode has higher purchase cost of the terminal, the operation and maintenance costs such as network communication, cloud processing and the like are greatly saved, and the local analysis mode is a mainstream analysis mode in the future.
The main reason in the prior art is that a precise artificial intelligence model cannot be trained due to the lack of massive sample pictures collected under various environments, road conditions and roads of different grades. Most of the existing training sample sets are shot by non-special equipment such as a vehicle event data recorder and a street view collector, and the existing training sample sets lack coverage on the road conditions of low-grade roads such as vast county roads and rural roads.
SUMMERY OF THE UTILITY MODEL
Based on this, the embodiment of the application provides a portable vehicle-mounted road disease detection device, can install fast and arrange on all kinds of vehicles such as public transit, rent, rubbish clearing car, road inspection car, reform transform ordinary vehicle into professional road disease inspection car with low costs, enlarge effectively and patrol and examine scope and region, make full use of vehicle resource, satisfied daily demand of patrolling and examining still provide very big data supplement and support for road disease sample storehouse.
The application provides a portable on-vehicle road disease check out test set, this equipment includes: the terminal comprises a terminal host, a camera lens, a light supplement lamp array, an antenna, a power supply assembly and a magnetic suction bracket;
the camera lens is fixedly arranged on one side of the front surface of the terminal host and is used for acquiring road ground pictures and transmitting the acquired pictures to the image module in the terminal host; the light supplement lamp arrays are arranged on the surfaces of the terminal host machines on the two sides of the camera lens;
the antenna is arranged at the top of the terminal host, is connected with a communication positioning module in the terminal host and is used for communication connection between the terminal host and external equipment;
the power supply assembly is arranged on one side of the back face of the terminal host and is used for being connected with an in-vehicle power supply through a cigarette lighter plug in the power supply assembly and supplying power to equipment;
the magnetic attraction support is arranged at the bottom of the terminal host and comprises a support arm and a magnetic attraction fixing part, the upper end of the support arm is connected with the terminal host, and the lower end of the support arm is connected with the magnetic attraction fixing part fixed on the detection vehicle.
Optionally, the magnetic support specifically includes support arms disposed on two sides of the bottom of the terminal host, and the terminal host is movably connected to the support arms on two sides so that the terminal host can rotate to the front side/back side.
Optionally, a waterproof shell is further arranged outside the device, wherein one side of the waterproof shell is made of a transparent material and used for enabling the internal camera lens and the light supplement lamp array to generate light source interaction with the outside; the other side of the waterproof shell is provided with a power supply wire hole; and the top of the waterproof shell is provided with an antenna cover made of plastic.
Optionally, the terminal host includes an image module, a computing module, a power module, a communication positioning module and a storage module;
the image module comprises an image sensor, wherein the image sensor is a global shutter sensor;
the computing module comprises a video analysis acceleration chip, a central processing unit and a memory;
the communication positioning module comprises a GNSS positioning module, a mobile network communication module and a WIFI module.
Optionally, a deep learning network recognition model trained in advance is stored in the video analysis acceleration chip, and the deep learning network recognition model is used for compressing, decompressing, image quality enhancing, image preprocessing, target detecting and recognizing the acquired original image.
Optionally, the light supplement lamp array is a white light LED array.
Optionally, the magnetic attraction fixing part comprises a neodymium iron boron strong magnet sucker.
The technical scheme provided by the embodiment of the application comprises a terminal host, a camera lens, a light supplement lamp array, an antenna, a power supply assembly and a magnetic absorption support; the camera lens is fixedly arranged on one side of the front surface of the terminal host and is used for collecting road ground pictures and transmitting the collected pictures to the image module in the terminal host; the surface of the terminal host at two sides of the camera lens is provided with a light supplement lamp array; the antenna is arranged at the top of the terminal host, is connected with a communication positioning module in the terminal host and is used for communication connection between the terminal host and external equipment; the power supply assembly is arranged on one side of the back surface of the terminal host and is used for being connected with an in-vehicle power supply through a cigarette lighter plug in the power supply assembly and supplying power to equipment; the magnetic attraction support is arranged at the bottom of the terminal host and comprises a support arm and a magnetic attraction fixing part, the upper end of the support arm is connected with the terminal host, and the lower end of the support arm is connected with the magnetic attraction fixing part fixed on the detection vehicle. The utility model discloses an image sensor and degree of depth study network identification model, supplementary GNSS locating information detects and fixes a position the road disease in real time, improves and patrols and examines efficiency, reduces artificial careless omission and the hidden danger that causes of participating in.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary and that other implementation drawings may be derived from the provided drawings by those of ordinary skill in the art without inventive effort.
Fig. 1 is a structural diagram of a portable vehicle-mounted road disease detection device provided in an embodiment of the present application;
fig. 2 is a schematic diagram of a terminal host module in a portable vehicle-mounted road damage detection device according to an embodiment of the present application;
fig. 3 is a schematic flow chart of software in a terminal host of the portable vehicle-mounted road disease detection device according to the embodiment of the present application;
fig. 4 is a flowchart of a portable vehicle-mounted road disease detection method provided in the embodiment of the present application;
reference numerals are as follows: the method comprises the following steps of 1-a terminal host, 2-a camera lens, 3-a light supplement lamp array, 4-an antenna, 5-a power supply assembly and 6-a magnetic attraction support.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In the description of the present invention, the terms "comprises," "comprising," "has," "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements specifically listed, but may include other steps or elements not expressly listed that are inherent to such process, method, article, or apparatus, or that add steps or elements based on further optimization concepts of the present invention.
Please refer to fig. 1, which shows a structural diagram of a portable vehicle-mounted road damage detecting device provided in an embodiment of the present application, the device includes: terminal host computer 1, camera lens 2, light filling lamp array 3, antenna 4, power supply module 5, magnetism support 6 of inhaling.
The camera lens 2 is fixedly arranged on one side of the front surface of the terminal host 1 and is used for collecting road ground pictures and transmitting the collected pictures to the image module in the terminal host 1; wherein, the terminal host 1 surface of camera lens 2 both sides is provided with light filling lamp array 3.
The antenna 4 is arranged on the top of the terminal host 1, connected with a communication positioning module in the terminal host 1, and used for communication connection between the terminal host 1 and external equipment.
The power supply unit 5 is provided on the rear surface side of the terminal main unit 1, and is connected to an in-vehicle power supply through a cigarette lighter plug in the power supply unit 5 to supply power to the device.
The magnetic support 6 is arranged at the bottom of the terminal host 1 and comprises a support arm and a magnetic fixing part, the upper end of the support arm is connected with the terminal host 1, and the lower end of the support arm is connected with the magnetic fixing part fixed on the detection vehicle. Specifically, the magnetic support 6 in the embodiment of the present application specifically includes support arms disposed on two sides of the bottom of the terminal host 1, and the terminal host 1 is movably connected to the support arms on two sides so that the terminal host 1 can rotate to the front side/back side.
In the embodiment of the present application, as shown in fig. 2, the electronic circuit portion of the terminal host in the present application is mainly composed of an image module, a computing module, a power module, a communication and positioning module, and a storage module;
the computing module generally comprises a central processing unit CPU and a memory as main carriers for software operation and algorithm flow control. In addition, because the existing popular video and image analysis methods are all convolution models based on deep learning, a special video analysis acceleration chip is integrated into a calculation module to serve as a coprocessor, and the algorithm is optimized and accelerated. The acceleration chip is also called GPU (graphics processing unit), VPU (visual processing unit) or NPU (neural network processing unit), and its main purpose is to compress, decompress, enhance image quality, pre-process image, detect and identify target, etc. for the original image collected by the image sensor.
The image module mainly utilizes an image sensor (CMOS or CCD) to collect road and ground pictures through a lens. The image sensor is generally divided into a rolling shutter sensor or a global shutter sensor, for high-speed running vehicle acquisition, the global shutter sensor is adopted, and the smear phenomenon caused by too slow shutter can be greatly reduced when the sampling frequency is higher than 90 fps. In addition, in order to meet the requirements of image acquisition in areas with dark light, such as culverts, tunnels, bridge openings, roads under elevated buildings and the like, the image module utilizes the white light LED array as a light source to supplement light.
Communication and orientation module mainly include the GNSS location module of big dipper, GPS as the representative, and mobile network communication module and WIFI local network communication module of 4G 5G as the representative. The GNSS positioning module mainly acquires the current geographic coordinates, the speed, the orientation and the current time of the vehicle. Mobile network communications provide a data channel between the device and an external server for the device to report data, video streams, receive server commands, and the like. The WIFI module provides the ability of local access of equipment, lets the last operating personnel of car pass through access devices such as computer, cell-phone, previews the video analysis picture, and the adjustment camera lens angle looks over equipment running state.
The power module can convert a 12-24V power supply provided by a power supply of the cigarette lighter on the vehicle into a low-voltage power supply required by each module. The storage module provides persistent storage capability, and can be generally formed by devices such as a large-capacity SD card and an SSD solid state disk, and the like, and stores original video or picture streams, GNSS positioning data, identification and analysis key frame pictures and data, equipment running logs and the like.
In an alternative embodiment of the present application, as shown in fig. 3, the software running inside the device is composed of an operating system layer, a data processing layer and an interface service layer.
The operating system layer is mainly responsible for the overall operation of the equipment embedded system and provides basic functions of network communication, file storage, equipment management, task scheduling and the like. Common vehicle-mounted end operating systems include Linux, FreeRTOS, uC/OS and the like.
The data processing layer is the core for realizing the functions of the equipment, and the algorithm flow is as follows: the image data acquisition module acquires image sensor data, decompresses and transcodes the data, outputs the data to the image preprocessing module, and performs preprocessing such as image quality enhancement, jitter removal, image slicing and the like on the image. And then, carrying out target detection or example segmentation operation through a deep neural network model to obtain a detection target of each picture. Each detected disease target may appear in a plurality of frames of pictures which are continuous in front and back, so that image target post-processing is needed to track and remove the duplicate of the same target, so as to avoid repeated reporting. In addition, data fusion processing is carried out on coordinate data acquired by GNSS and target data, and finally structured information such as geographic coordinates, geometric dimensions and the like of each target is obtained.
The interface service layer defines 3 standard interfaces, and can be connected to any server supporting the interfaces without additional customized development. The video streaming service can adopt streaming media services such as RTSP (real time streaming protocol) and the like, the file downloading service can adopt FTP (file transfer protocol) service, and external software can access video streaming, original video and pictures, key frame pictures and logs of the equipment through the standard services when needed. No network traffic charges are incurred without access.
The data reporting function of the interface service layer adopts a standard message queue client, such as MQTT. The external server can receive the data reported by the equipment only by downloading and installing the message queue service software. The report message format comprises equipment coordinates, speed, azimuth, acquisition time, target type, target key frame picture and confidence.
In an alternative embodiment of the present application, the exterior of the device is further provided with a waterproof housing, and in order to reduce interference of the windshield to the shooting effect of the image sensor, the device needs to be deployed outside the installation vehicle. The aforementioned electronic circuit portion needs to be fixed in a case having a waterproof function. The front of the waterproof shell is made of transparent materials, so that the internal lens and the light supplement lamp array circuit can be conveniently penetrated out. An antenna cover made of plastic is arranged right above the shell, and a WIFI, GNSS and mobile network antenna are embedded in the antenna cover. The power cord is led out from the back of the shell and is connected to the in-vehicle socket through a cigarette lighter plug for supplying power. The side surface of the whole shell is provided with a bracket hole, and the shell can rotate up and down to adjust the angle of the lens. The neodymium iron boron strong magnet sucker is arranged below the support, so that the whole equipment can be easily adsorbed and arranged on an engine cover, a vehicle roof or a trunk cover of a vehicle.
As shown in fig. 4, an embodiment of the present application further provides a portable vehicle-mounted road disease detection method. The method is applied to the detection equipment and specifically comprises the following steps:
adsorbing the detection equipment at a target position of a target vehicle through a magnetic fixing part of a magnetic support, wherein the target position comprises a hood, a roof or a trunk lid of the target vehicle;
connecting a cigarette lighter plug of the detection equipment with an in-vehicle power supply to supply power to the detection equipment;
adjusting the angle of a camera lens in the detection equipment through a support arm of the magnetic support; acquiring image data through a camera lens, and sending the acquired image data to a terminal host;
processing the acquired image data through a terminal host to obtain a detected disease target, and performing data fusion processing on the coordinate data acquired through the GNSS and the disease target; and reporting the processed data.
In an optional embodiment of the present application, processing the acquired image data by the terminal host specifically includes: acquiring image data, decompressing and transcoding the image data, outputting the image data to an image preprocessing module, and performing preprocessing such as image quality enhancement, jitter removal and image slicing on the image data; carrying out target detection through a deep neural network model to obtain a disease target in each picture; and for each detected disease target, tracking and removing the duplicate of the same target after obtaining the image target.
In an optional embodiment of the present application, reporting the processed data includes: with a standard message queue client, the message protocol of the message queue client may include MQTT.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the claims. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (7)
1. A portable vehicle-mounted road disease detection device, characterized in that the device comprises: the terminal comprises a terminal host, a camera lens, a light supplement lamp array, an antenna, a power supply assembly and a magnetic suction bracket;
the camera lens is fixedly arranged on one side of the front surface of the terminal host and is used for acquiring road ground pictures and transmitting the acquired pictures to the image module in the terminal host; the light supplement lamp arrays are arranged on the surfaces of the terminal host machines on the two sides of the camera lens;
the antenna is arranged at the top of the terminal host, is connected with a communication positioning module in the terminal host and is used for communication connection between the terminal host and external equipment;
the power supply assembly is arranged on one side of the back face of the terminal host and is used for being connected with an in-vehicle power supply through a cigarette lighter plug in the power supply assembly and supplying power to equipment;
the magnetic attraction support is arranged at the bottom of the terminal host and comprises a support arm and a magnetic attraction fixing part, the upper end of the support arm is connected with the terminal host, and the lower end of the support arm is connected with the magnetic attraction fixing part fixed on the detection vehicle.
2. The device of claim 1, wherein the magnetic support comprises support arms disposed at two sides of a bottom of the terminal host, and the terminal host is movably connected to the support arms at two sides so that the terminal host can rotate towards a front side/a back side.
3. The device according to claim 1, wherein a waterproof housing is further arranged outside the device, wherein one side of the waterproof housing is made of a transparent material and used for enabling the internal camera lens and the light supplement lamp array to generate light source interaction with the outside; the other side of the waterproof shell is provided with a power supply wire hole; and the top of the waterproof shell is provided with an antenna cover made of plastic.
4. The device according to claim 1, wherein the terminal host comprises an image module, a computing module, a power module, a communication positioning module and a storage module;
the image module comprises an image sensor, wherein the image sensor is a global shutter sensor;
the computing module comprises a video analysis acceleration chip, a central processing unit and a memory;
the communication positioning module comprises a GNSS positioning module, a mobile network communication module and a WIFI module.
5. The device according to claim 4, wherein a pre-trained deep learning network recognition model is saved in the video analysis acceleration chip, and the deep learning network recognition model is used for compressing, decompressing, enhancing image quality, preprocessing image, detecting and recognizing target of the acquired original image.
6. The apparatus of claim 1, wherein the fill light array is a white light LED array.
7. The apparatus of claim 1, wherein the magnetically attractive fixture includes a neodymium iron boron ferromagnetic chuck.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202221584739.8U CN217505691U (en) | 2022-06-23 | 2022-06-23 | Portable vehicle-mounted road disease detection equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202221584739.8U CN217505691U (en) | 2022-06-23 | 2022-06-23 | Portable vehicle-mounted road disease detection equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN217505691U true CN217505691U (en) | 2022-09-27 |
Family
ID=83340431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202221584739.8U Active CN217505691U (en) | 2022-06-23 | 2022-06-23 | Portable vehicle-mounted road disease detection equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN217505691U (en) |
-
2022
- 2022-06-23 CN CN202221584739.8U patent/CN217505691U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108833833B (en) | Intelligent networking-oriented automobile scene image data sensing and cooperative processing system | |
| CN108109385B (en) | System and method for identifying and judging dangerous behaviors of power transmission line anti-external damage vehicle | |
| CN100419813C (en) | Omnibearing visual sensor based road monitoring apparatus | |
| CN102110376B (en) | Roadside parking space detection device based on computer vision | |
| CA3124173C (en) | System and method for detecting and transmitting incidents of interest of a roadway to a remote server | |
| US20220020230A1 (en) | System and method for interactively reporting of roadway incidents on an ai device | |
| CN106682592B (en) | Image automatic identification system and method based on neural network method | |
| CN102426801A (en) | Automatic parking lot berth management method and system based on visual analysis | |
| CN108318506A (en) | A kind of pipeline intelligent detection method and detecting system | |
| CN105141924A (en) | Wireless image monitoring system based on 4G technology | |
| CN105120237A (en) | Wireless image monitoring method based on 4G technology | |
| CN101052124A (en) | Night-vision device for motor vehicle and ship | |
| CN109239099A (en) | Road surface breakage real-time detecting system and its detection method under multi-machine collaborative environment | |
| CN101833117A (en) | Intelligent vehicle safety vision detection device and motion target tracking method | |
| CN102708603A (en) | GIS (Geographic Information System)-based vehicle-mounted recorder for monitoring vehicle | |
| CN103640595A (en) | Automatic detecting system and damage recognition method for railway protecting fences | |
| CN116545122B (en) | Power transmission line external damage prevention monitoring device and external damage prevention monitoring method | |
| CN115144407A (en) | Portable vehicle-mounted road disease detection device and detection method | |
| CN107819998A (en) | A kind of panorama Camcording system and method based on vehicle-mounted integral | |
| CN217505691U (en) | Portable vehicle-mounted road disease detection equipment | |
| CN202257940U (en) | License plate identification video server | |
| CN219574949U (en) | Intelligent traffic perception integrated device based on binocular depth fusion of thunder and sound | |
| CN114565597B (en) | Night road pedestrian detection method based on YOLO v3-tiny-DB and transfer learning | |
| CN114592411B (en) | Carrier parasitic type intelligent inspection method for highway damage | |
| CN217331227U (en) | Strain insulator string wind-induced vibration on-line monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |