WO2024087290A1 - 一种道路标牌及安防设施缺失的检测方法、介质及系统 - Google Patents

一种道路标牌及安防设施缺失的检测方法、介质及系统 Download PDF

Info

Publication number
WO2024087290A1
WO2024087290A1 PCT/CN2022/134386 CN2022134386W WO2024087290A1 WO 2024087290 A1 WO2024087290 A1 WO 2024087290A1 CN 2022134386 W CN2022134386 W CN 2022134386W WO 2024087290 A1 WO2024087290 A1 WO 2024087290A1
Authority
WO
WIPO (PCT)
Prior art keywords
target detection
target
detection object
sequence
type
Prior art date
Application number
PCT/CN2022/134386
Other languages
English (en)
French (fr)
Inventor
张海
孙浩宇
潘宗俊
弋晓明
王宇强
龚长鑫
曹建坤
王亚欣
Original Assignee
中公高科养护科技股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中公高科养护科技股份有限公司 filed Critical 中公高科养护科技股份有限公司
Publication of WO2024087290A1 publication Critical patent/WO2024087290A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Definitions

  • the present invention relates to the technical field of road detection, and in particular to a method, medium and system for detecting the missing of road signs and security facilities.
  • the embodiments of the present invention provide a method, medium and system for detecting the missing of road signs and security facilities, so as to solve the problem of low efficiency caused by manual detection of whether road signs and security facilities are missing in the prior art.
  • a method for detecting missing road signs and security facilities comprising:
  • a database of road target detection objects wherein the types of the target detection objects include: signs and security facilities, and the database includes: a standard sequence of the geographical location of each target detection object and the category of each target detection object;
  • the first sequence of each of the target detection objects is modified to obtain a second sequence of each of the target detection objects
  • each element in the standard sequence, the first sequence and the second sequence is 0 or 1
  • each element corresponds to each geographical location, and each element is arranged in order of geographical location. If the value of the element is 0, it means that the geographical location does not have the target detection object, and if the value of the element is 1, it indicates that the geographical location has the target detection object.
  • a computer-readable storage medium on which computer program instructions are stored; when the computer program instructions are executed by a processor, the method for detecting missing road signs and security facilities as described in the embodiment of the first aspect above is implemented.
  • a system for detecting missing road signs and security facilities comprising: a computer-readable storage medium as described in the above-mentioned embodiment of the second aspect.
  • the embodiments of the present invention can realize automatic detection of missing signs and security facilities, and can perform mutual inspection of signs and security facilities, reduce manual intervention, and improve detection and identification efficiency.
  • Fig. 1 shows a flow chart of a method for detecting missing road signs and security facilities according to a preferred embodiment of the present invention
  • FIG2 shows a flow chart of a method for detecting missing road signs and security facilities according to another preferred embodiment of the present invention
  • FIG3 shows a schematic diagram of a backtracking algorithm model according to an embodiment of the present invention
  • FIG4 schematically shows a block diagram of a computing and processing device for executing the method according to the present invention
  • FIG. 5 schematically shows a storage unit for holding or carrying a program code for implementing the method according to the present invention.
  • the embodiment of the present invention discloses a method for detecting the missing of road signs and security facilities. As shown in FIG1 , the method comprises the following steps:
  • Step S101 Establish a database of road target detection objects.
  • a database of target detection objects on the road can be established.
  • the function of data query and matching can be provided for the retrospective detection in subsequent steps.
  • the types of target detection objects include: signs and security facilities.
  • the types of signs include: warning signs, prohibition signs, and instruction signs.
  • security facilities include: crash barriers, speed bumps, and the like.
  • the database includes: a standard sequence of the geographical location of each target detection object and a category of each target detection object.
  • each element in the standard sequence is 0 or 1, and each element corresponds to each geographical location.
  • the geographical location can be a stake number or GPS data.
  • Each element is arranged in order of geographical location.
  • the route and direction of the road can be recorded in the database, and the elements of different geographical locations are arranged in sequence according to the route and direction.
  • the sequence number of the element can be represented by an index.
  • the first corresponding index is 0, the second corresponding index is 1, the third corresponding index is 2, and so on. If the element is 0, it means that the geographical location does not have the target detection object, and if the element is 1, it indicates that the geographical location has the target detection object.
  • the stake numbers of the road are 1 to 5, and the target detection object is at stake number 4, then the standard sequence is 00010.
  • Step S102 During the driving process of the detection vehicle, each time a preset distance is driven, an image of the road in front of the detection vehicle is collected by a camera installed on the detection vehicle.
  • the camera is usually installed on the top of the inspection vehicle.
  • the preset distance can be determined according to the actual situation. For example, the preset distance is 10m, which means that when the inspection vehicle is driving on the road, it takes an image every 10m.
  • Step S103 Identify each target object in all the acquired images, and record the position recognition result and type recognition result of each target object to obtain a first sequence of each target object consisting of the position recognition results.
  • the image recognition technology can adopt existing technologies, for example, using computer vision recognition technology to build a suitable deep neural network model, and using random data in the front image database to train and optimize the model to identify the target detection object and its type and geographical location.
  • ⁇ Deep Learning for Large-Scale Traffic-Sign Detection and Recognition> Domen Tabernik and Danijel Skocaj or, ⁇ MR-CNN: A Multi-Scale Region-Based Convolutional Neural Network for Small Traffic Sign Recognition> ZHIGANG LIU, JUAN DU, FENG TIAN and JIAZHENG WEN
  • the mentioned technologies are used for corresponding image recognition.
  • the geographical location in the image can be obtained by obtaining the stake number or GPS data, or the corresponding geographical location can be obtained by transforming the image coordinate system and the road coordinate system according to the existing technology.
  • the representation of the first sequence is consistent with the target sequence, and will not be repeated here.
  • the road has stake numbers 1 to 5, and the target object is identified at stake number 4, then the first sequence is 00010.
  • Step S104 According to the type recognition result, the first sequence of each target detection object is modified to obtain the second sequence of each target detection object.
  • the camera lens has different focal lengths, different viewing angles and different blind spots.
  • different lanes will also lead to different blind spots. Therefore, the continuous markings may not actually be accurate geographic locations (pile numbers or GPS). Therefore, this step is used to calibrate the geographic location.
  • PT represents the number of shift bits.
  • c represents the distance between the center line of the lane where the detection vehicle is traveling and the slope or edge line
  • ⁇ represents the viewing angle of the camera
  • H represents the image acquisition frequency, which is equivalent to the preset distance/time.
  • the viewing angle of the camera is related to the actual parameters of the device, as shown in Table 1. When applied, the viewing angle is selected from Table 1 according to the actual parameters of the camera.
  • Security facilities may be continuous targets or non-continuous targets.
  • speed bumps in security facilities are non-continuous targets
  • crash barriers in security facilities are continuous targets.
  • the distinction between continuous targets and non-continuous targets described in the embodiment of the present invention is as follows: since the image of the road is collected once every preset distance, when the length of the target detection object exceeds the preset distance, such a target detection object is a continuous target; conversely, when the length of the target detection object is less than the preset distance, such a target detection object is a non-continuous target.
  • the length of the target detection object should be understood as the length along the direction of extension of the road.
  • this step includes the following two situations:
  • the target object is a non-continuous target, add the index of the first element with a value of 0 after the elements with consecutive values of 1 in the first sequence of the target object to the number of shift bits to obtain a transformable index.
  • Index0 0 represents the index of the first element with a value of 0 after the elements with consecutive values of 1, and the convertible index is Index0 0 +P T .
  • the first sequence of the target detection object is 011110000000
  • the indexes of the elements with consecutive values of 1 in the first sequence of the target object are added with the number of shift bits to obtain a transformable index.
  • Index1 0 to Index1 n represent the indices of elements whose values are consecutively 1, then the convertible indices are Index1 0 + PT to Index1 n + PT .
  • the first sequence of the target detection object is 011110000000
  • the indexes of the elements with consecutive values of 1 are 1 to 4
  • the calculated number of shift bits is 2
  • the convertible indexes are 1+2 to 4+2, that is, 3 to 6.
  • the representation of the second sequence is consistent with the target sequence and will not be repeated here.
  • the target detection object is a non-continuous target
  • the first sequence of the target detection object is 011110000000
  • the calculated number of shift bits is 2
  • the second sequence is 000000010000.
  • the target detection object is a continuous target
  • the first sequence of the target detection object is 011110000000
  • the calculated number of shift bits is 2
  • the second sequence is 000111100000.
  • Step S105 For each target detection object, the second sequence of the target detection object is compared with the standard sequence of the target detection object in the database to determine whether the target detection object is missing.
  • the target detection object is not missing; otherwise, it is determined that the target detection object is missing.
  • the method of the embodiment of the present invention further includes the following steps:
  • This step is the same as the previous step and will not be repeated here.
  • a target index range is obtained from the second sequence of each target detection object.
  • the target index range is the first target index range
  • the lower limit of the first target index range is the difference between the index of the element with a value of 1 in the second sequence of the target detection object and the preset parameter
  • the upper limit of the first target index range is the sum of the index of the element with a value of 1 in the second sequence of the target detection object and the preset parameter.
  • the preset parameters can be set according to the relevant provisions of the target detection object in the relevant national standards or local standards.
  • highway security facilities are set according to the relevant provisions of highway security facilities
  • warning signs are set according to the relevant provisions of warning signs.
  • Index0 0 +P T represents the index of the element with a value of 1 in the second sequence
  • the first target index range is [Index0 0 +P T -z, Index0 0 +P T +z], where z represents a preset parameter, and the preset parameter is a positive number.
  • the target index range is the second target index range
  • the lower limit of the second target index range is the index of the first element in the second sequence of the target detection object that has a continuous value of 1
  • the upper limit of the second target index range is the index of the last element in the second sequence of the target detection object that has a continuous value of 1.
  • the second target index range is [Index1 0 +P T ,Index1 n +P T ].
  • the embodiment of the present invention can also perform mutual inspection of whether the sign and security facilities are missing based on the backtracking algorithm model shown in FIG3. Based on this principle, as shown in FIG2, after step S105, the method of the embodiment of the present invention further includes:
  • Step S106 If the target detection object is not missing, obtain a second sequence of another target detection object of a second type that matches the first type of the target detection object.
  • warning signs generally, only the areas near warning signs will be equipped with security facilities. Conversely, there will be warning signs near security facilities.
  • the second category is a security facility; or, if the first category is a security facility, then the second category is a warning sign among signs. That is, only when the target detection object is one of these two categories, will the second sequence of target detection objects of the corresponding category be obtained for mutual inspection.
  • Step S107 Compare the target index range of the first type of target detection object with the target index ranges of other target detection objects of the second type to obtain a result of whether the area where the first type of target detection object is located lacks other target detection objects of the second type.
  • the target index range of the target detection object of the first type has an intersection with the target index range of other target detection objects of the second type, it is determined that the area where the target detection object of the first type is located has other target detection objects of the second type; if the target index range of the target detection object of the first type has no intersection with the target index range of other target detection objects of the second type, it is determined that the area where the target detection object of the first type is located lacks other target detection objects of the second type.
  • Index0 0,1 + PT represents the index of the warning sign in the second sequence
  • [Index1 0 + PT , Index1 n + PT ] represents the index of the continuous security facility in the second sequence
  • Index0 0,2 + PT represents the index of the non-continuous security facility in the second sequence
  • z1 represents the preset parameter corresponding to the warning sign
  • z2 represents the preset parameter corresponding to the non-continuous security facility.
  • the target detection object is a warning sign, and its target index range is [Index0 0,1 +P T -z 1 ,Index0 0,1 +P T +z 1 ].
  • the second type of target detection object is a security facility, and it is a continuous target, and its target index range is [Index1 0 +P T ,Index1 n +P T ]. Then, it is determined whether [Index1 0 +P T ,Index1 n +P T ] belongs to or partially belongs to [Index0 0,1 +P T -z 1 ,Index0 0,1 +P T +z 1 ]. If so, there are security facilities in the area where the warning sign is located, that is, the security facilities are not missing; otherwise, the security facilities are missing.
  • the target detection object is a warning sign, and its target index range is [Index0 0,1 +P T1 -z 1 ,Index0 0,1 +P T1 +z 1 ].
  • the second type of target detection object is a security facility, and it is a non-continuous target, and its target index range is [Index0 0,2 +P T -z 2 ,Index0 0,2 +P T +z 2 ]. Then, it is determined whether [Index0 0,2 +P T -z 2 ,Index0 0,2 +P T +z 2 ] belongs to or partially belongs to [Index0 0,1 +P T1 -z 1 ,Index0 0,1 +P T1 +z 1 ]. If so, there are security facilities in the area where the warning sign is located, that is, the security facilities are not missing; otherwise, the security facilities are missing.
  • the target detection object is a security facility and is a non-continuous target
  • its target index range is [Index0 0,2 +P T -z 2 ,Index0 0,2 +P T +z 2 ]
  • the second type of target detection object is a warning sign
  • its target index range is [Index0 0,1 +P T -z 1 ,Index0 0,1 +P T +z 1 ]
  • the target detection object is a security facility and is a continuous target
  • its target index range is [Index1 0 + PT , Index1 n + PT ]
  • the second type of target detection object is a warning sign
  • its target index range is [Index0 0,1 + PT -z 1 , Index0 0,1 + PT +z 1 ]
  • each target detection object and its corresponding target search range the target detection object that matches it and its corresponding target search range can be used to construct a retrospective decision card.
  • the retrospective decision card includes: the target detection object and its position, the target detection object that matches it and its position, as shown in Table 2.
  • the retrospective decision card mechanism can be activated to find the corresponding guardrail from the retrospective decision card to determine whether the guardrail that matches the warning sign is normal.
  • the retrospective decision card may also include status information of the target test object and the target test object that matches it, that is, missing or not missing.
  • An embodiment of the present invention further discloses a computer-readable storage medium having computer program instructions stored thereon; when the computer program instructions are executed by a processor, the method for detecting missing road signs and security facilities as described in the above embodiment is implemented.
  • the embodiment of the present invention further discloses a road sign and security facility missing detection system, comprising: a computer-readable storage medium as described in the above embodiment.
  • the embodiments of the present invention can realize automatic detection of missing signs and security facilities, and can perform mutual inspection of signs and security facilities, thereby reducing manual intervention and improving detection and identification efficiency.
  • the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.
  • the various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the computing processing device according to an embodiment of the present invention.
  • DSP digital signal processor
  • the present invention can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein.
  • Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.
  • FIG. 4 shows a computing processing device that can implement the method according to the present invention.
  • the computing processing device traditionally includes a processor 1010 and a computer program product or a computer-readable medium in the form of a memory 1020.
  • the memory 1020 can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM.
  • the memory 1020 has a storage space 1030 for a program code 1031 for executing any method step in the above method.
  • the storage space 1030 for the program code can include individual program codes 1031 for implementing the various steps in the above method respectively.
  • These program codes can be read from or written to one or more computer program products.
  • These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. Such computer program products are generally portable or fixed storage units as described with reference to FIG. 5.
  • the storage unit can have storage segments, storage spaces, etc. arranged similarly to the memory 1020 in the computing processing device of FIG. 4.
  • the program code can be compressed, for example, in an appropriate form.
  • the storage unit includes computer readable code 1031', i.e., code that can be read by a processor such as 1010, which, when executed by a computing processing device, causes the computing processing device to perform the various steps in the method described above.
  • the terms “installed”, “connected”, and “connected” should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components.
  • installed should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components.
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are merely schematic.
  • the division of the units is only a logical function division. There may be other division methods in actual implementation.
  • multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
  • Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor.
  • the computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.
  • references herein to "one embodiment,” “embodiment,” or “one or more embodiments” mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present invention.
  • examples of the term “in one embodiment” do not necessarily all refer to the same embodiment.
  • any reference signs placed between brackets shall not be construed as limiting the claims.
  • the word “comprising” does not exclude the presence of elements or steps not listed in the claims.
  • the word “a” or “an” preceding an element does not exclude the presence of a plurality of such elements.
  • the invention may be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware.
  • the use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Alarm Systems (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种道路标牌及安防设施缺失的检测方法、介质及系统，包括：建立道路目标检测物的数据库（S101）；在检测车行驶过程中，每行驶预设距离，通过检测车上安装的摄像头采集一幅检测车前方的道路的图像（S102）；在采集的所有图像中识别每一目标检测物，并记录每一目标检测物的位置识别结果和种类识别结果，得到由位置识别结果组成的每一目标检测物的第一序列（S103）；根据种类识别结果，对每一目标检测物的第一序列进行修正，得到每一目标检测物的第二序列（S104）；对于每一目标检测物，将该目标检测物的第二序列与数据库中的该目标检测物的标准序列进行比较，确定该目标检测物是否缺失（S105）。可自动实现标牌、安防设施的缺失检测，减少人工干预，提高检测识别效率。

Description

一种道路标牌及安防设施缺失的检测方法、介质及系统
本申请要求在2022年10月26日提交中国专利局、申请号为202211318065.1发明名称为“一种道路标牌及安防设施缺失的检测方法、介质及系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及道路检测技术领域，尤其涉及一种道路标牌及安防设施缺失的检测方法、介质及系统。
背景技术
基于建养并重的交通建设方针，提出了公路全资产管理理念，各养护管理单位对路面安全防护设施及标志标牌检测更为重视。为应对养护单位的管理需求，现阶段均采用检测车前方摄像头以采集图像进行逐帧识别比对。虽然目前已经实现了基于计算机视觉的检测，加快了第一次全面检测对公路设施的标定，但后续的标志标牌分类、位置信息及缺失检测仍然需要大量人工比对标记工作，不能实现自动缺失标定和检测，在很大程度上限制了咨询服务进度。此外，现行技术并未能实现安防工程及警示标牌的互检。
发明内容
本发明实施例提供一种道路标牌及安防设施缺失的检测方法、介质及系统，以解决现有技术通过人工检测道路标牌及安防设施是否缺失导致效率低的问题。
第一方面，提供一种道路标牌及安防设施缺失的检测方法，包括：
建立道路目标检测物的数据库，其中，所述目标检测物的种类包括：标牌和安防设施，所述数据库包括：每一目标检测物的地理位置的标准序列和每一目标检测物的类别；
在检测车行驶过程中，每行驶预设距离，通过所述检测车上安装的摄像头采集一幅所述检测车前方的道路的图像；
在采集的所有所述图像中识别每一所述目标检测物，并记录每一所述目标检测物的位置识别结果和种类识别结果，得到由所述位置识别结果组成的每一所述目标检测物的第一序列；
根据所述种类识别结果，对每一所述目标检测物的第一序列进行修正，得到每一所述目标检测物的第二序列；
对于每一所述目标检测物，将该目标检测物的第二序列与所述数据库中的该目标检测物的标准序列进行比较，确定该目标检测物是否缺失；
其中，所述标准序列、所述第一序列和所述第二序列中的每一元素的取值为0或1，每一元素对应每一地理位置，每一元素按地理位置顺序排列，若该元素的取值为0则表示该地理位置不具有该目标检测物，若该元素的取值为1则表明该地理位置具有该目标检测物。
第二方面，提供一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序指令；所述计算机程序指令被处理器执行时实现如上述第一方面实施例所述的道路标牌及安防设施缺失的检测方法。
第三方面，提供一种道路标牌及安防设施缺失的检测系统，包括：如上述第二方面实施例所述的计算机可读存储介质。
这样，本发明实施例，可实现标牌、安防设施缺失的自动检测，并可进行标牌、安防设施的互检，减少人工干预，提高检测识别效率。
上述说明仅是本发明技术方案的概述，为了能够更清楚了解本发明的技术手段，而可依照说明书的内容予以实施，并且为了让本发明的上述和其它目的、特征和优点能够更明显易懂，以下特举本发明的具体实施方式。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1示出了本发明一优选实施例的道路标牌及安防设施缺失的检测 方法的流程图；
图2示出了本发明另一优选实施例的道路标牌及安防设施缺失的检测方法的流程图；
图3示出了本发明实施例的回溯算法模型示意图；
图4示意性地示出了用于执行根据本发明的方法的计算处理设备的框图；
图5示意性地示出了用于保持或者携带实现根据本发明的方法的程序代码的存储单元。
具体实施例
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明实施例公开了一种道路标牌及安防设施缺失的检测方法。如图1所示，该方法包括如下的步骤：
步骤S101：建立道路目标检测物的数据库。
对于每一条道路可建立一个该道路上的目标检测物的数据库，通过建立数据库，结构化存储相应信息，可对后续步骤的回溯检测提供数据查询匹配的功能。
具体的，目标检测物的种类包括：标牌和安防设施。进一步的，标牌的种类包括：警示标牌、禁令标牌、指示标牌。进一步的，安防设施包括：防撞栏、减速带等等。
具体的，数据库包括：每一目标检测物的地理位置的标准序列和每一目标检测物的类别。
其中，标准序列中的每一元素的取值为0或1，每一元素对应每一地理位置。地理位置可以是桩号或者GPS数据。每一元素按地理位置顺序排列。例如，数据库中可记录道路的路线、方向，按照该路线及方向依 次排列不同地理位置的元素。元素的序号可通过索引表示。本发明实施例中，一个序列中，排序第一对应索引为0，排序第二对应索引为1，排序第三对应索引为2，……，以此类推。若该元素为0则表示该地理位置不具有该目标检测物，若该元素为1则表明该地理位置具有该目标检测物。例如，该道路的桩号为1～5，在桩号4处具有该目标检测物，则标准序列为00010。
步骤S102：在检测车行驶过程中，每行驶预设距离，通过检测车上安装的摄像头采集一幅检测车前方的道路的图像。
摄像头一般安装于检测车的顶部。预设距离可根据实际情况确定。例如，预设距离为10m，即检测车在该条道路上行驶时，每行驶10m拍摄一次图像。
步骤S103：在采集的所有图像中识别每一目标检测物，并记录每一目标检测物的位置识别结果和种类识别结果，得到由位置识别结果组成的每一目标检测物的第一序列。
具体的，图像识别技术可采用现有技术，例如，利用计算机视觉识别技术构建适用的深度神经网络模型，并利用前方图像数据库中随机数据对模型进行训练优化，以识别目标检测物及其种类和地理位置。例如，通过<Deep Learning for Large-Scale Traffic-Sign Detection and Recognition>Domen Tabernik and Danijel Skocaj，或者，<MR-CNN:A Multi-Scale Region-Based Convolutional Neural Network for Small Traffic Sign Recognition>ZHIGANG LIU,JUAN DU,FENG TIAN and JIAZHENG WEN，提及的技术进行相应的图像识别。获取图像中的地理位置，可以通过获取桩号或者GPS数据实现，或者，通过现有技术的图像坐标系和道路坐标系变换得到相应的地理位置。
第一序列的表征和目标序列一致，在此不再赘述。例如，该道路的桩号为1～5，在桩号4处识别出该目标检测物，则第一序列为00010。
步骤S104：根据种类识别结果，对每一目标检测物的第一序列进行修正，得到每一目标检测物的第二序列。
通常情况下，摄像头的镜头由于焦距不同，可视角度及视觉盲区面 积不同。此外，检测车行驶在不同的车道也会导致不同的视觉盲区。因此，在连续标记处，事实上可能并非准确的地理位置(桩号或者GPS)。因此，通过本步骤对地理位置进行校正。
具体的，该步骤的过程如下：
(1)对于每一目标检测物，采用
Figure PCTCN2022134386-appb-000001
计算该目标检测物的第一序列的平移位数。
其中，P T表示平移位数。
Figure PCTCN2022134386-appb-000002
c表示检测车行驶的车道中心线距边坡或边线的距离，θ表示摄像头的可视角度，H表示图像采集频率，相当于预设距离/次。
其中，摄像头的可视角度与设备实际参数有关，具体如表1所示。应用时，根据摄像头的实际参数，从表1中选择可视角度。
表1焦距及可视角度对照表
焦距 1/3 CCD可视角度 1/4 CCD可视角度
2.8mm 89.9° 75.6°
4mm 69.9° 57°
6mm 50° 39.8°
8mm 38.5° 30.4°
12mm 26.2° 20.5°
(2)根据每一目标检测物的种类识别结果，得到每一目标检测物是否为连续型目标的结果。
一般来说，标牌无论具体是哪种类型的标牌，都为非连续型目标。安防设施可能是连续型目标，也可能是非连续型目标。例如，安防设施中的减速带是非连续型目标，安防设施中的防撞栏是连续型目标。本发明实施例所述的连续型目标和非连续型目标的区分标准为：由于每行驶预设距离采集一次道路的图像，因此，当目标检测物的长度超过预设距 离时，这样的目标检测物为连续型目标；反之，当目标检测物的长度小于预设距离时，这样的目标检测物为非连续型目标。目标检测物的长度应理解为沿着道路延伸方向的长度。
(3)根据每一目标检测物是否为连续型目标的结果，基于平移位数，得到每一目标检测物的第一序列中的可变换的索引。
具体的，该步骤包括如下两种情况：
①若目标检测物为非连续型目标，则将目标检测物的第一序列中的连续取值为1的元素后的首位取值为0的元素的索引加上平移位数，得到可变换的索引。
以Index0 0表示连续取值为1的元素后的首位取值为0的元素的索引，则可变换的索引为Index0 0+P T。
例如，目标检测物的第一序列为011110000000，连续取值为1的元素后的首位取值为0的元素的索引为5，计算得到的平移位数为2，则可变换的索引为5+2＝7。
②若目标检测物为连续型目标，则将目标检测物的第一序列中的连续取值为1的元素的索引分别加上平移位数，得到可变换的索引。
以Index1 0～Index1 n表示连续取值为1的元素的索引，则可变换的索引为Index1 0+P T～Index1 n+P T。
例如，目标检测物的第一序列为011110000000，连续取值为1的元素的索引为1～4，计算得到的平移位数为2，则可变换的索引为1+2～4+2，即3～6。
(4)将每一目标检测物的第一序列中原始的连续取值为1的元素均更新取值为0，并将每一目标检测物的第一序列中的可变换的索引对应的元素更新取值为1，得到每一目标检测物的第二序列。
第二序列的表征和目标序列一致，在此不再赘述。
例如，目标检测物为非连续型目标，目标检测物的第一序列为011110000000，计算得到的平移位数为2，则得到第二序列为000000010000。
例如，目标检测物为连续型目标，目标检测物的第一序列为 011110000000，计算得到的平移位数为2，则得到第二序列为000111100000。
步骤S105：对于每一目标检测物，将该目标检测物的第二序列与数据库中的该目标检测物的标准序列进行比较，确定该目标检测物是否缺失。
具体的，若该目标检测物的第二序列与该目标检测物的标准序列完全相同，则确定该目标检测物未缺失，否则，确定该目标检测物缺失。
优选的，本发明实施例的方法还包括如下的步骤：
(1)根据每一目标检测物的种类识别结果，得到每一目标检测物是否为连续型目标的结果。
该步骤与前文相同的步骤一致，在此不再赘述。
(2)根据每一目标检测物是否为连续型目标的结果，从每一目标检测物的第二序列中获取目标索引范围。
具体的，根据是否为连续型目标，有如下两种情况：
①若该目标检测物为非连续型目标，则目标索引范围为第一目标索引范围，第一目标索引范围的下限为该目标检测物的第二序列中的取值为1的元素的索引与预设参数的差，第一目标索引范围的上限为该目标检测物的第二序列中的取值为1的元素的索引与预设参数的和。
预设参数可根据相关的国家标准或地方标准中对于目标检测物的相关规定进行取值。例如，公路安防设施按照公路安防设施的相关规定取值，警示标牌按照警示标牌的相关规定取值。
以Index0 0+P T表示第二序列中的取值为1的元素的索引，则第一目标索引范围为[Index0 0+P T-z,Index0 0+P T+z]，其中，z表示预设参数，预设参数为正数。
②若该目标检测物为连续型目标，则目标索引范围为第二目标索引范围，第二目标索引范围的下限为该目标检测物的第二序列中的连续取值为1的首个元素的索引，第二目标索引范围的上限为该目标检测物的第二序列中的连续取值为1的最后一个元素的索引。
即第二目标索引范围为[Index1 0+P T,Index1 n+P T]。
优选的，本发明实施例还可以基于图3所示的回溯算法模型进行标牌和安防设施是否缺失的互检，基于这一原理，如图2所示，步骤S105之后，本发明实施例的方法还包括：
步骤S106：若该目标检测物没有缺失，则获取与该目标检测物的第一种类配合的第二种类的其它目标检测物的第二序列。
标牌的三个种类中，一般的，只有警示标牌附近区域会配合设置安防设施，反之，安防设施附近会有警示标牌。
因此，第一种类为标牌中的警示标牌，则第二种类为安防设施；或者，第一种类为安防设施，则第二种类为标牌中的警示标牌，即只有目标检测物是这两个种类时，才会去获取与其配合的种类的目标检测物的第二序列，以进行互检。
步骤S107：将该第一种类的目标检测物的目标索引范围与第二种类的其它目标检测物的目标索引范围进行比较，得到该第一种类的目标检测物所在区域是否缺失第二种类的其它目标检测物的结果。
具体的，若该第一种类的目标检测物的目标索引范围与第二种类的其它目标检测物的目标索引范围具有交集，则确定该第一种类的目标检测物所在区域具有第二种类的其它目标检测物；若该第一种类的目标检测物的目标索引范围与第二种类的其它目标检测物的目标索引范围不具有交集，则确定该第一种类的目标检测物所在区域缺失第二种类的其它目标检测物。
由于警示标牌是非连续型目标，安防设施包括连续型目标和非连续型目标，以Index0 0,1+P T表示警示标牌在第二序列中的索引，以[Index1 0+P T,Index1 n+P T]表示连续型的安防设施在第二序列中的索引，以Index0 0,2+P T表示非连续型的安防设施在第二序列中的索引，以z1表示警示标牌对应的预设参数，以z2表示非连续型的安防设施对应的预设参数，则该步骤具体可具有如下的几种情况：
(1)该目标检测物为警示标牌，其目标索引范围为[Index0 0,1+P T-z 1,Index0 0,1+P T+z 1]，第二种类的目标检测物为安防设施，且为连续型目标，则其目标索引范围为[Index1 0+P T,Index1 n+P T]，则判断 [Index1 0+P T,Index1 n+P T]是否属于或部分属于[Index0 0,1+P T-z 1,Index0 0,1+P T+z 1]，若是，则警示标牌所在区域具有安防设施，即安防设施未缺失；反之，安防设施缺失。
(2)该目标检测物为警示标牌，其目标索引范围为[Index0 0,1+P T1-z 1,Index0 0,1+P T1+z 1]，第二种类的目标检测物为安防设施，且为非连续型目标，则其目标索引范围为[Index0 0,2+P T-z 2,Index0 0,2+P T+z 2]，则判断[Index0 0,2+P T-z 2,Index0 0,2+P T+z 2]是否属于或部分属于[Index0 0,1+P T1-z 1,Index0 0,1+P T1+z 1]，若是，则警示标牌所在区域具有安防设施，即安防设施未缺失；反之，安防设施缺失。
(3)该目标检测物为安防设施，且为非连续型目标，则其目标索引范围为[Index0 0,2+P T-z 2,Index0 0,2+P T+z 2]，第二种类的目标检测物为警示标牌，其目标索引范围为[Index0 0,1+P T-z 1,Index0 0,1+P T+z 1]，则判断[Index0 0,1+P T-z 1,Index0 0,1+P T+z 1]是否属于或部分属于[Index0 0,2+P T-z 2,Index0 0,2+P T+z 2]，若是，则安防设施所在区域具有警示标牌，即警示标牌未缺失；反之，警示标牌缺失。
(4)该目标检测物为安防设施，且为连续型目标，则其目标索引范围为[Index1 0+P T,Index1 n+P T]，第二种类的目标检测物为警示标牌，其目标索引范围为[Index0 0,1+P T-z 1,Index0 0,1+P T+z 1]，则判断[Index0 0,1+P T-z 1,Index0 0,1+P T+z 1]是否属于或部分属于[Index1 0+P T,Index1 n+P T]，若是，则安防设施所在区域具有警示标牌，即警示标牌未缺失；反之，警示标牌缺失。
具体应用时，结合国家相关标准，可将各目标检测物及对应的目标检索范围，与其配合的目标检测物及对应的目标检索范围，构建回溯决策卡，回溯决策卡包括：目标检测物及其位置，与其配合的目标检测物及其位置，如表2所示。
表2回溯决策卡
Figure PCTCN2022134386-appb-000003
例如，应用时，标牌为警示标牌，同时，警示标牌为连续急弯警示，此时，可启动回溯决策卡机制，从回溯决策卡找到与其配合的防撞栏，判断与警示标牌配合的防撞栏是否正常。
此外，根据检测结果，该回溯决策卡还可以包括目标检测物及与其配合的目标检测物的状态信息，即缺失或未缺失。
本发明实施例还公开了一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序指令；所述计算机程序指令被处理器执行时实现如上述实施例所述的道路标牌及安防设施缺失的检测方法。
本发明实施例还公开了一种道路标牌及安防设施缺失的检测系统，包括：如上述实施例所述的计算机可读存储介质。
综上，本发明实施例，可实现标牌、安防设施缺失的自动检测，并可进行标牌、安防设施的互检，减少人工干预，提高检测识别效率。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
本发明的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本发明实施例的计算处理设备中的一些或者全部部件的一些或者全部功能。本发明还可以实现为用于执行这里所描述的方法的一部 分或者全部的设备或者装置程序(例如，计算机程序和计算机程序产品)。这样的实现本发明的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
例如，图4示出了可以实现根据本发明的方法的计算处理设备。该计算处理设备传统上包括处理器1010和以存储器1020形式的计算机程序产品或者计算机可读介质。存储器1020可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。存储器1020具有用于执行上述方法中的任何方法步骤的程序代码1031的存储空间1030。例如，用于程序代码的存储空间1030可以包括分别用于实现上面的方法中的各种步骤的各个程序代码1031。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。这些计算机程序产品包括诸如硬盘，紧致盘(CD)、存储卡或者软盘之类的程序代码载体。这样的计算机程序产品通常为如参考图5所述的便携式或者固定存储单元。该存储单元可以具有与图4的计算处理设备中的存储器1020类似布置的存储段、存储空间等。程序代码可以例如以适当形式进行压缩。通常，存储单元包括计算机可读代码1031’，即可以由例如诸如1010之类的处理器读取的代码，这些代码当由计算处理设备运行时，导致该计算处理设备执行上面所描述的方法中的各个步骤。
另外，在本发明实施例的描述中，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本发明中的具体含义。
在本发明的描述中，需要说明的是，术语“中心”、“上”、“下”、“左”、“右”、“竖直”、“水平”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本发明和简化描述，而不是 指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本发明的限制。此外，术语“第一”、“第二”、“第三”仅用于描述目的，而不能理解为指示或暗示相对重要性。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存 储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上所述实施例，仅为本发明的具体实施方式，用以说明本发明的技术方案，而非对其限制，本发明的保护范围并不局限于此，尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化，或者对其中部分技术特征进行等同替换；而这些修改、变化或者替换，并不使相应技术方案的本质脱离本发明实施例技术方案的精神和范围，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应所述以权利要求的保护范围为准。
本文中所称的“一个实施例”、“实施例”或者“一个或者多个实施例”意味着，结合实施例描述的特定特征、结构或者特性包括在本发明的至少一个实施例中。此外，请注意，这里“在一个实施例中”的词语例子不一定全指同一个实施例。
在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本发明的实施例可以在没有这些具体细节的情况下被实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包含”不排除存在未列在权利要求中的元件或步骤。位于元件之前的单词“一”或“一个”不排除存在多个这样的元件。本发明可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替 换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (11)

  1. 一种道路标牌及安防设施缺失的检测方法，其特征在于，包括：
    建立道路目标检测物的数据库，其中，所述目标检测物的种类包括：标牌和安防设施，所述数据库包括：每一目标检测物的地理位置的标准序列和每一目标检测物的类别；
    在检测车行驶过程中，每行驶预设距离，通过所述检测车上安装的摄像头采集一幅所述检测车前方的道路的图像；
    在采集的所有所述图像中识别每一所述目标检测物，并记录每一所述目标检测物的位置识别结果和种类识别结果，得到由所述位置识别结果组成的每一所述目标检测物的第一序列；
    根据所述种类识别结果，对每一所述目标检测物的第一序列进行修正，得到每一所述目标检测物的第二序列；
    对于每一所述目标检测物，将该目标检测物的第二序列与所述数据库中的该目标检测物的标准序列进行比较，确定该目标检测物是否缺失；
    其中，所述标准序列、所述第一序列和所述第二序列中的每一元素的取值为0或1，每一元素对应每一地理位置，每一元素按地理位置顺序排列，若该元素的取值为0则表示该地理位置不具有该目标检测物，若该元素的取值为1则表明该地理位置具有该目标检测物。
  2. 根据权利要求1所述的道路标牌及安防设施缺失的检测方法，其特征在于，所述得到每一所述目标检测物的第二序列的步骤，包括：
    对于每一所述目标检测物，采用
    Figure PCTCN2022134386-appb-100001
    计算该目标检测物的第一序列的平移位数，其中，P T表示平移位数，
    Figure PCTCN2022134386-appb-100002
    c表示检测车行驶的车道中心线距边坡或边线的距离，θ表示摄像头的可视角度，H表示图像采集频率，所述图像采集频率为所述预设距离/次；
    根据每一所述目标检测物的种类识别结果，得到每一所述目标检测物是否为连续型目标的结果；
    根据每一所述目标检测物是否为连续型目标的结果，基于平移位数，得到每一所述目标检测物的第一序列中的可变换的索引；
    将每一所述目标检测物的第一序列中原始的连续取值为1的元素均更新取值为0，并将每一所述目标检测物的第一序列中的可变换的索引对应的元素更新取值为1，得到每一所述目标检测物的第二序列；
    其中，所述索引表示元素的序号。
  3. 根据权利要求2所述的道路标牌及安防设施缺失的检测方法，其特征在于，所述得到每一所述目标检测物的第一序列中的可变换的索引的步骤，包括：
    若所述目标检测物为非连续型目标，则将所述目标检测物的第一序列中的连续取值为1的元素后的首位取值为0的元素的索引加上平移位数，得到所述可变换的索引。
  4. 根据权利要求2所述的道路标牌及安防设施缺失的检测方法，其特征在于，所述得到每一所述目标检测物的第一序列中的可变换的索引的步骤，包括：
    若所述目标检测物为连续型目标，则将所述目标检测物的第一序列中的连续取值为1的元素的索引分别加上平移位数，得到所述可变换的索引。
  5. 根据权利要求1所述的道路标牌及安防设施缺失的检测方法，其特征在于，所述确定该目标检测物是否缺失的步骤，包括：
    若该目标检测物的第二序列与该目标检测物的标准序列完全相同，则确定该目标检测物未缺失，否则，确定该目标检测物缺失。
  6. 根据权利要求1所述的道路标牌及安防设施缺失的检测方法，其特征在于，还包括：
    根据每一所述目标检测物的种类识别结果，得到每一所述目标检测物是否为连续型目标的结果；
    根据每一所述目标检测物是否为连续型目标的结果，从每一所述目标检测物的第二序列中获取目标索引范围；
    其中，若该目标检测物为非连续型目标，则所述目标索引范围为第一目标索引范围，所述第一目标索引范围的下限为该目标检测物的第二序列中的取值为1的元素的索引与预设参数的差，所述第一目标索引范围的上限为该目标检测物的第二序列中的取值为1的元素的索引与预设参数的和；
    其中，若该目标检测物为连续型目标，则所述目标索引范围为第二目标索引范围，所述第二目标索引范围的下限为该目标检测物的第二序列中的连续取值为1的首个元素的索引，所述第二目标索引范围的上限为该目标检测物的第二序列中的连续取值为1的最后一个元素的索引；
    其中，所述索引表示元素的序号。
  7. 根据权利要求6所述的道路标牌及安防设施缺失的检测方法，其特征在于，所述确定该目标检测物是否缺失的步骤之后，所述方法还包括：
    若该目标检测物没有缺失，则获取与该目标检测物的第一种类配合的第二种类的其它目标检测物的第二序列，其中，所述第一种类为标牌中的警示标牌，所述第二种类为安防设施，或者，所述第一种类为安防设施，所述第二种类为标牌中的警示标牌；
    将该第一种类的目标检测物的目标索引范围与第二种类的其它目标检测物的目标索引范围进行比较，得到该第一种类的目标检测物所在区域是否缺失第二种类的其它目标检测物的结果。
  8. 根据权利要求7所述的道路标牌及安防设施缺失的检测方法，其特征在于，所述得到该第一种类的目标检测物所在区域是否缺失第二种类的其它目标检测物的结果的步骤，包括：
    若该第一种类的目标检测物的目标索引范围与第二种类的其它目标检测物的目标索引范围具有交集，则确定该第一种类的目标检测物所在区域具有第二种类的其它目标检测物；
    若该第一种类的目标检测物的目标索引范围与第二种类的其它目标检测物的目标索引范围不具有交集，则确定该第一种类的目标检测物所在区域缺失第二种类的其它目标检测物。
  9. 一种计算机可读存储介质，其特征在于：所述计算机可读存储介质上存储有计算机程序指令；所述计算机程序指令被处理器执行时实现如权利 要求1～8中任一项所述的道路标牌及安防设施缺失的检测方法。
  10. 一种道路标牌及安防设施缺失的检测系统，其特征在于，包括：如权利要求9所述的计算机可读存储介质。
  11. 一种计算处理设备，其特征在于，包括：
    存储器，其中存储有计算机可读代码；
    一个或多个处理器，当所述计算机可读代码被所述一个或多个处理器执行时，所述计算处理设备执行如权利要求1-8中任一项所述的语音处理方法。
PCT/CN2022/134386 2022-10-26 2022-11-25 一种道路标牌及安防设施缺失的检测方法、介质及系统 WO2024087290A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211318065.1 2022-10-26
CN202211318065.1A CN115909263A (zh) 2022-10-26 2022-10-26 一种道路标牌及安防设施缺失的检测方法、介质及系统

Publications (1)

Publication Number Publication Date
WO2024087290A1 true WO2024087290A1 (zh) 2024-05-02

Family

ID=86475175

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/134386 WO2024087290A1 (zh) 2022-10-26 2022-11-25 一种道路标牌及安防设施缺失的检测方法、介质及系统

Country Status (2)

Country Link
CN (1) CN115909263A (zh)
WO (1) WO2024087290A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140052422A (ko) * 2012-10-24 2014-05-07 현대모비스 주식회사 차량용 교통 안내 표지판 인식 장치 및 이를 이용한 경로 안내 방법
CN108108703A (zh) * 2017-12-27 2018-06-01 天津英创汇智汽车技术有限公司 减速带缺失检测方法、装置及电子设备
CN108198419A (zh) * 2018-01-04 2018-06-22 山东华夏高科信息股份有限公司 一种智能道路交通安全隐患排查系统
CN113343782A (zh) * 2021-05-18 2021-09-03 东南大学 一种基于无人机遥感的高速公路标志标牌检测方法
CN114022862A (zh) * 2021-09-30 2022-02-08 南宁小欧技术开发有限公司 一种交通标牌被遮挡的智能化检测方法及系统
CN114973646A (zh) * 2022-03-14 2022-08-30 北京市商汤科技开发有限公司 道路检测方法、装置、系统及服务器

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140052422A (ko) * 2012-10-24 2014-05-07 현대모비스 주식회사 차량용 교통 안내 표지판 인식 장치 및 이를 이용한 경로 안내 방법
CN108108703A (zh) * 2017-12-27 2018-06-01 天津英创汇智汽车技术有限公司 减速带缺失检测方法、装置及电子设备
CN108198419A (zh) * 2018-01-04 2018-06-22 山东华夏高科信息股份有限公司 一种智能道路交通安全隐患排查系统
CN113343782A (zh) * 2021-05-18 2021-09-03 东南大学 一种基于无人机遥感的高速公路标志标牌检测方法
CN114022862A (zh) * 2021-09-30 2022-02-08 南宁小欧技术开发有限公司 一种交通标牌被遮挡的智能化检测方法及系统
CN114973646A (zh) * 2022-03-14 2022-08-30 北京市商汤科技开发有限公司 道路检测方法、装置、系统及服务器

Also Published As

Publication number Publication date
CN115909263A (zh) 2023-04-04

Similar Documents

Publication Publication Date Title
US10950124B2 (en) License plate recognition
CN103824452B (zh) 一种轻量级的基于全景视觉的违章停车检测装置
CN108073923B (zh) 一种车牌校正方法及装置
CN115717894B (zh) 一种基于gps和普通导航地图的车辆高精度定位方法
CN110688902B (zh) 一种检测停车位内车辆区域的方法及装置
CN111369801B (zh) 车辆识别方法、装置、设备和存储介质
CN109448387B (zh) 基于轨迹的违规行驶判定方法
JP2011113440A (ja) ナンバープレート認識プログラムおよびナンバープレート認識装置
CN113011331B (zh) 机动车是否礼让行人的检测方法、装置、电子设备及介质
CN110647886A (zh) 兴趣点标注方法、装置、计算机设备和存储介质
CN112432650A (zh) 高精地图数据的获取方法、车辆控制方法以及设备
CN111400533A (zh) 图像筛选方法、装置、电子设备和存储介质
CN111369824B (zh) 一种基于图像识别定位的引导泊车方法及系统
CN113505638A (zh) 车流量的监测方法、监测装置及计算机可读存储介质
CN113205692A (zh) 一种路侧停车泊位异常变动的自动识别方法
Sunny et al. Image based automatic traffic surveillance system through number-plate identification and accident detection
WO2024087290A1 (zh) 一种道路标牌及安防设施缺失的检测方法、介质及系统
CN112418081B (zh) 一种空地联合快速勘察交通事故的方法及系统
Priambada et al. Levensthein distance as a post-process to improve the performance of ocr in written road signs
US20160358462A1 (en) Method and system for vehicle data integration
CN114693722B (zh) 一种车辆行驶行为检测方法、检测装置及检测设备
CN113743316A (zh) 基于目标检测的车辆加塞行为识别方法、系统及装置
CN113408514A (zh) 一种基于深度学习检测路侧停车场泊位的方法及装置
CN111488771B (zh) Ocr挂接方法、装置与设备
Chang et al. Vehicle detection approach adjusting road curves to estimate local traffic density under real driving conditions