WO2017193679A1 - 自动检测单车是否倒地的方法 - Google Patents

自动检测单车是否倒地的方法 Download PDF

Info

Publication number
WO2017193679A1
WO2017193679A1 PCT/CN2017/075814 CN2017075814W WO2017193679A1 WO 2017193679 A1 WO2017193679 A1 WO 2017193679A1 CN 2017075814 W CN2017075814 W CN 2017075814W WO 2017193679 A1 WO2017193679 A1 WO 2017193679A1
Authority
WO
WIPO (PCT)
Prior art keywords
bicycle
identification code
code image
image
ground
Prior art date
Application number
PCT/CN2017/075814
Other languages
English (en)
French (fr)
Inventor
黄安武
Original Assignee
黄安武
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 黄安武 filed Critical 黄安武
Priority to CN201780001008.1A priority Critical patent/CN107851326A/zh
Publication of WO2017193679A1 publication Critical patent/WO2017193679A1/zh

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01N—GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR MACHINES OR ENGINES IN GENERAL; GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR INTERNAL COMBUSTION ENGINES
    • F01N11/00—Monitoring or diagnostic devices for exhaust-gas treatment apparatus, e.g. for catalytic activity
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01N—GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR MACHINES OR ENGINES IN GENERAL; GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR INTERNAL COMBUSTION ENGINES
    • F01N3/00—Exhaust or silencing apparatus having means for purifying, rendering innocuous, or otherwise treating exhaust
    • F01N3/08—Exhaust or silencing apparatus having means for purifying, rendering innocuous, or otherwise treating exhaust for rendering innocuous
    • F01N3/0807—Exhaust or silencing apparatus having means for purifying, rendering innocuous, or otherwise treating exhaust for rendering innocuous by using absorbents or adsorbents
    • F01N3/0828—Exhaust or silencing apparatus having means for purifying, rendering innocuous, or otherwise treating exhaust for rendering innocuous by using absorbents or adsorbents characterised by the absorbed or adsorbed substances
    • F01N3/0857—Carbon oxides
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01N—GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR MACHINES OR ENGINES IN GENERAL; GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR INTERNAL COMBUSTION ENGINES
    • F01N3/00—Exhaust or silencing apparatus having means for purifying, rendering innocuous, or otherwise treating exhaust
    • F01N3/08—Exhaust or silencing apparatus having means for purifying, rendering innocuous, or otherwise treating exhaust for rendering innocuous
    • F01N3/10—Exhaust or silencing apparatus having means for purifying, rendering innocuous, or otherwise treating exhaust for rendering innocuous by thermal or catalytic conversion of noxious components of exhaust
    • F01N3/18—Exhaust or silencing apparatus having means for purifying, rendering innocuous, or otherwise treating exhaust for rendering innocuous by thermal or catalytic conversion of noxious components of exhaust characterised by methods of operation; Control
    • F01N3/20—Exhaust or silencing apparatus having means for purifying, rendering innocuous, or otherwise treating exhaust for rendering innocuous by thermal or catalytic conversion of noxious components of exhaust characterised by methods of operation; Control specially adapted for catalytic conversion ; Methods of operation or control of catalytic converters
    • F01N3/2086—Activating the catalyst by light, photo-catalysts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01D—SEPARATION
    • B01D2252/00—Absorbents, i.e. solvents and liquid materials for gas absorption
    • B01D2252/20—Organic absorbents
    • B01D2252/205—Other organic compounds not covered by B01D2252/00 - B01D2252/20494
    • B01D2252/2053—Other nitrogen compounds
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01N—GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR MACHINES OR ENGINES IN GENERAL; GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR INTERNAL COMBUSTION ENGINES
    • F01N2560/00—Exhaust systems with means for detecting or measuring exhaust gas components or characteristics
    • F01N2560/02—Exhaust systems with means for detecting or measuring exhaust gas components or characteristics the means being an exhaust gas sensor
    • F01N2560/022—Exhaust systems with means for detecting or measuring exhaust gas components or characteristics the means being an exhaust gas sensor for measuring or detecting CO or CO2
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
    • Y02A50/20—Air quality improvement or preservation, e.g. vehicle emission control or emission reduction by using catalytic converters
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Definitions

  • the present invention relates to the field of bicycle field and computer vision processing, and more particularly to a method for automatically detecting whether a bicycle has fallen to the ground.
  • the present invention provides a method for automatically detecting whether a bicycle has fallen to the ground, and can improve the efficiency of detecting whether a bicycle is thrown onto the ground.
  • a method for automatically detecting whether a bicycle has fallen to the ground according to the present invention comprises the following steps:
  • the bicycle identification code image respectively attached to the handlebar and the seatbar of the bicycle is extracted from the video image;
  • the output is displayed to inform the corresponding staff that there is a need to deal with the bicycle falling to the ground.
  • the process of calculating the deflection angle of the bicycle according to the offset angle and the offset direction comprises: calculating the rotation coefficient according to the offset angle ⁇ and the offset direction (f x , f y , f z ) H, and calculating a deflection angle ⁇ of the bicycle corresponding to the reference angle according to the rotation coefficient H; using the following formula:
  • I is a 3x3 unit matrix
  • the method further includes the steps of:
  • the process of detecting whether a bicycle exists in a video image comprises:
  • the bicycle identification code includes direction information.
  • the bicycle identification code includes four sub-identification codes, and the four sub-identification codes are respectively located at four corners; and the extracted bicycle identification code image is performed with a pre-stored original identification code image.
  • the process of comparing and determining the offset angle and the offset direction of the bicycle identification code image relative to the original identification code image includes:
  • the weighted average is used as an offset angle and an offset direction of the bicycle identification code image with respect to the original identification code image.
  • the method for automatically detecting whether the bicycle has fallen to the ground is that a bicycle identification code is attached to the handlebar and the seat rod of the bicycle in advance, and then the bicycle recognition is obtained through the surveillance cameras everywhere.
  • the code image and calculate the offset angle and the offset direction of the bicycle identification code image, thereby calculating the deflection angle of the bicycle, thereby identifying whether the bicycle is down to the ground, and if so, automatically outputting the alarm prompt information to the corresponding staff for reminding.
  • the solution of the present invention is completely implemented by a software algorithm, and does not need to add additional hardware sensors, avoids the blind search of manual detection, and can find and remind the first time where there is a bicycle falling to the ground and realize the cost. Low, easy to maintain, greatly improving the detection efficiency.
  • FIG. 1 is a schematic flow chart of a method for automatically detecting whether a bicycle has fallen to the ground provided by the present invention.
  • a schematic flowchart of a preferred embodiment of a method for automatically detecting whether a bicycle has fallen to the ground according to the present invention includes the following steps:
  • Step S1 Obtain a video image captured by the surveillance camera in real time, and detect whether there is a bicycle in the video image.
  • the process of detecting whether a bicycle exists in a video image may specifically include the following steps:
  • the structure and shape of the bicycle are represented in advance by using the geometric model or structure of the bicycle, and the correspondence between the model and the image is established by extracting the object features of the bicycle, and then the bicycle recognition is performed by the geometric method.
  • step S2 if the difference in step S1 is that there is a bicycle, the bicycle identification code images respectively attached to the handlebars and the seatbars of the bicycle are extracted from the video image, and then the process proceeds to step S3.
  • a bicycle identification code is attached to the handlebar and the seatbar of the bicycle in advance, and the bicycle identification code is It is specially made. Similar to the form of QR code, each manufacturer can make its own bicycle identification code according to specific needs. The most basic requirement is to add direction information to the bicycle identification code, so that the original can be obtained. The direction of the identification code so that the direction of the original identification code can be called for subsequent comparisons. In addition to this, it is also possible to add information unique to each manufacturer in the bicycle identification code to distinguish it. At present, there are some similar identification codes in the field of computer vision computing, which are not described in the present invention.
  • Step S3 comparing the extracted bicycle identification code image with the pre-stored original identification code image, determining an offset angle and an offset direction of the bicycle identification code image with respect to the original identification code image, and then proceeding to step S4. .
  • step S4 the deflection angle of the bicycle is calculated according to the offset angle and the offset direction, and then proceeds to step S5.
  • the process of calculating the deflection angle of the bicycle according to the offset angle and the offset direction in this step may specifically include: according to the offset angle ⁇ and the offset direction (f x , f y , f z ) calculating the rotation coefficient H, and calculating the deflection angle ⁇ of the bicycle corresponding to the reference angle according to the rotation coefficient H; the following formula can be adopted:
  • v f (0, 0, 1) is the reference vector.
  • step S5 it is determined whether the deflection angle of the bicycle exceeds a set angle threshold. If yes, it is determined that the bicycle has fallen to the ground, and the local GPS positioning information of the surveillance camera can be automatically invoked at this time.
  • the surveillance camera has a limited monitoring range and can be photographed by a surveillance camera to indicate that the bicycle is in a certain area near the surveillance camera. Therefore, the local GPS positioning information of the surveillance camera is defaulted to the approximate position of the inverted bicycle, and the The local GPS positioning information is edited into the first alarm prompt information for output display, to notify the corresponding staff that the bicycle has to be disposed of.
  • the efficiency is higher, the downhill bicycle can be found and notified at the first time; in addition, compared with the scheme of adding a hardware sensor on the bicycle to detect whether the bicycle is fell to the ground, On the one hand, it will not increase the hardware cost of bicycles, and the maintenance cost is lower than that of hardware sensors. On the other hand, in terms of the accuracy of detection, the scheme can achieve an accuracy of more than 99%. Compared with hardware sensor solutions, it has advantages.
  • the method for automatically detecting whether a bicycle has fallen to the ground, after extracting the bicycle identification code image, and comparing the bicycle identification code image with the original identification code image may further include the following steps:
  • the distance between the first key feature point and the second key feature point calculated in the above embodiment is not satisfied.
  • the preset distance threshold indicates that there is a fault in the bicycle identification code, such as loss or damage.
  • an alarm prompt is issued to notify the corresponding staff to replace the bicycle identification code.
  • the bicycle identification code may include four sub-identification codes, and the four sub-identification codes are respectively located on four corners of the bicycle identification code; then, the bicycle identification that will be extracted in step S3 at this time.
  • the process of comparing the code image with the pre-stored original identification code image and determining the offset angle and the offset direction of the bicycle identification code image relative to the original identification code image may specifically include the following steps:
  • Step S31 performing image segmentation processing on the bicycle identification code image to obtain four corner images of the bicycle identification code image
  • Step S32 performing binarization processing on the four corner images, and extracting sub-identification code images having predetermined feature points among the four corner images;
  • Step S33 comparing each sub-identification code image into the identification code database and comparing with the pre-stored original identification code image, respectively calculating an offset angle and an offset direction of each sub-ID image relative to the original identification code image;
  • Step S34 performing outlier calculation on the calculated offset angle and offset direction of each sub-ID image, excluding the outlier value, and calculating the weight of the offset angle and the offset direction of the remaining sub-ID images.
  • An average value is used as an offset angle and an offset direction of the bicycle identification code image with respect to the original identification code image.
  • the method for automatically detecting whether the bicycle has fallen to the ground is that the bicycle identification code is attached to the handlebar and the seat rod of the bicycle in advance, and the offset angle and offset of the bicycle identification code image are calculated.
  • the direction is used to calculate the deflection angle of the bicycle. Since the bicycle identification code is used to detect whether the bicycle has fallen to the ground, and since the feature points in the bicycle identification code image are obvious and easy to identify, the efficiency of detecting the bicycle to the ground can be greatly improved. The computational complexity is reduced and the accuracy of the detection is significantly improved.

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Combustion & Propulsion (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Toxicology (AREA)
  • Exhaust Gas Treatment By Means Of Catalyst (AREA)
  • Treating Waste Gases (AREA)
  • Exhaust Gas After Treatment (AREA)
  • Image Analysis (AREA)

Abstract

一种自动检测单车是否倒地的方法，包括：获取监控摄像头实时拍摄到的视频图像，并检测该视频图像中是否存在单车（S1）；若存在单车，则从视频图像中提取分别贴在单车的车把和坐杆上的单车识别码图像（S2）；将提取到的单车识别码图像与预先存储的原始识别码图像进行对比，确定提取到的单车识别码图像相对于原始识别码图像的偏移角度和偏移方向（S3）；根据偏移角度和偏移方向计算单车的偏转角度（S4）；判断单车的偏转角度是否超过设定角度阈值，若是，则判定为单车已经倒地，此时自动获取本地GPS定位信息，并将本地GPS定位信息编辑到第一告警提示信息中进行输出显示，以通知相应的工作人员有单车倒地需要处理（S5）。该方法能提高单车倒地检测的效率。

Description

自动检测单车是否倒地的方法 技术领域
本发明涉及自行车领域和计算机视觉处理领域，尤其涉及一种自动检测单车是否倒地的方法。
背景技术
近来，大城市中“随停随走”的共享单车(或称“公共自行车”)非常受欢迎。随之而来的共享单车乱停乱放的问题不断出现，甚至有些共享单车被人使用完之后随意丢弃在地面上，倒在地面上的共享单车很容易弄脏，这样后面的人即使看到这辆弄脏的共享单车也不会有人愿意使用，从而极大影响了市容和行人的出行。
为了解决这个问题，有些共享单车运营机构不得不雇佣专门的工作人员来进行维护和整治，通过工作人员分工负责一片区域并采用定期巡逻的方式来寻找和发现这些乱丢并倒在地面上的共享单车。但是采用这种人工检测的方法，其效率非常低，往往不能及时发现哪里有被乱丢倒在地面上的共享单车。
发明内容
本发明提出一种自动检测单车是否倒地的方法，能够提高检测单车是否被乱丢倒在地面上的效率。
本发明的一种自动检测单车是否倒地的方法，包括如下步骤：
获取监控摄像头实时拍摄到的视频图像，并检测该视频图像中是否存在单车；
若存在单车，则从视频图像中提取分别贴在单车的车把和坐杆上的单车识别码图像；
将提取到的单车识别码图像与预先存储的原始识别码图像进行对比，确定 所述单车识别码图像相对于所述原始识别码图像的偏移角度和偏移方向；
根据所述偏移角度和偏移方向计算单车的偏转角度；
判断所述单车的偏转角度是否超过设定角度阈值，若是，则判定为单车已经倒地，此时自动获取本地GPS定位信息，并将所述本地GPS定位信息编辑到第一告警提示信息中进行输出显示，以通知相应的工作人员有单车倒地需要处理。
在其中一个实施例中，根据所述偏移角度和偏移方向计算单车的偏转角度的过程包括：根据所述偏移角度α和偏移方向(fx,fy,fz)计算旋转系数H，并根据所述旋转系数H计算单车相当于基准角度的偏转角度β；采用如下公式：
Figure PCTCN2017075814-appb-000001
式中，I是3x3的单位矩阵，
Figure PCTCN2017075814-appb-000002
在其中一个实施例中，在提取单车识别码图像之后、将单车识别码图像与原始识别码图像进行对比之前，还包括步骤：
从所述车把上贴着的单车识别码图像中提取出第一关键特征点；以及从所述坐杆上贴着的单车识别码图像中提取出第二关键特征点；
计算所述第一关键特征点和第二关键特征点之间的距离；
判断所述距离是否在预设的距离阈值内，若否，则输出第二告警提示信息，以提示相应的工作人员所述单车识别码出现故障。
在其中一个实施例中，所述检测视频图像中是否存在单车的过程包括：
将所述视频图像输入到预先建立的单车模型中进行匹配，提取所述视频图像中的物体特征进行相似度计算；
当相似度计算的结果超过设定特征阈值时，判定为检测到视频图像中存在单车，并提取出与所述物体特征相近的纹理进行保存。
在其中一个实施例中，所述单车识别码中包括方向信息。
在其中一个实施例中，所述单车识别码中包括4个子识别码，该4个子识别码分别位于四个边角；所述将提取到的单车识别码图像与预先存储的原始识别码图像进行对比、确定单车识别码图像相对于所述原始识别码图像的偏移角度和偏移方向的过程包括：
对所述单车识别码图像进行图像分割处理，获得单车识别码图像的四个边角图像；
将所述四个边角图像进行二值化处理，提取四个边角图像中具有预定特征点的子识别码图像；
将各子识别码图像输入识别码数据库中与预先存储的原始识别码图像进行对比，分别计算每个子识别码图像相对于所述原始识别码图像的偏移角度和偏移方向；
对计算出来的每个子识别码图像的偏移角度和偏移方向进行离群计算，剔除离群点数值，并对剩下的子识别码图像的偏移角度和偏移方向计算加权平均值，将所述加权平均值作为所述单车识别码图像相对于所述原始识别码图像的偏移角度和偏移方向。
从以上方案可以看出，本发明的一种自动检测单车是否倒地的方法，预先在单车的车把和坐杆上贴有单车识别码，然后通过遍布各处的监控摄像头来获取到单车识别码图像，并计算单车识别码图像的偏移角度和偏移方向，进而计算单车的偏转角度，以此识别出单车是否倒地，如果是则自动输出告警提示信息到相应的工作人员进行提醒。相比于现有的技术，本发明的方案完全采用软件算法实现，不需要增加额外的硬件传感器，避免了人工检测的盲目性查找，能第一时间发现并提醒哪里有单车倒地，实现成本低，维护方便，极大提高了检测效率。
附图说明
图1是本发明提供的一种自动检测单车是否倒地的方法流程示意图。
具体实施方式
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，所描述的实施例仅仅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。
如图1所示，为本发明提供的一种自动检测单车是否倒地的方法一个优选的实施例的流程示意图，包括如下步骤：
步骤S1，获取监控摄像头实时拍摄到的视频图像，并检测该视频图像中是否存在单车。
目前，监控摄像头遍布市区各处，尤其是大城市中监控摄像头的应用更加广泛。但是传统的监控摄像头主要用来拍摄视频并进行存档，以便事后可进行追溯；由于缺少智能的算法，传统的监控摄像头对于突发状况的处理并不是很理想。采用本发明提供的算法，可以有效提升传统监控摄像头的智能程度，让传统的监控摄像头发挥出更大的作用。
作为一个较好的实施例，所述检测视频图像中是否存在单车的过程具体可以包括如下步骤：
将所述视频图像输入到预先建立的单车模型中进行匹配，提取所述视频图像中的物体特征进行相似度计算；
当相似度计算的结果超过设定特征阈值时，判定为检测到视频图像中存在单车，并提取出与所述物体特征相近的纹理进行保存。
本发明中，事先利用单车的几何模型或结构来表示单车的结构和形状，并通过提取单车的物体特征，在模型和图像之间建立起对应关系，然后通过几何方法来进行单车识别。
步骤S2，若步骤S1的差别是存在单车，则从视频图像中提取分别贴在单车的车把和坐杆上的单车识别码图像，然后进入步骤S3。
本发明中，预先在单车的车把和坐杆上贴有单车识别码，且该单车识别码 是特殊制作而成的，类似于二维码的形态，各厂商可以根据具体需求制作属于自己的单车识别码，最基本的要求是需要在单车识别码中添加方向信息，这样就可以获取到原始识别码的方向，以便后续对比时可以调用该原始识别码的方向。除此之外还可以在单车识别码添加各厂商独有的信息等以便进行区分。目前在计算机视觉计算领域已经有一些类似的识别码的应用，本发明中不作过多描述。
步骤S3，将提取到的单车识别码图像与预先存储的原始识别码图像进行对比，确定所述单车识别码图像相对于所述原始识别码图像的偏移角度和偏移方向，然后进入步骤S4。
由于单车识别码中的特征点较为明显，较易识别，因此对这些特征点进行识别的难度较低，相对于实物识别来讲，进行图像对比和计算的运算量成几何级数降低，可以有效提高运算效率，节省计算机的资源。
步骤S4，根据所述偏移角度和偏移方向计算单车的偏转角度，然后进入步骤S5。
在其中一个实施例中，本步骤中根据所述偏移角度和偏移方向计算单车的偏转角度的过程具体可以包括如下：根据所述偏移角度α和偏移方向(fx,fy,fz)计算旋转系数H，并根据所述旋转系数H计算单车相当于基准角度的偏转角度β；可以采用如下公式：
Figure PCTCN2017075814-appb-000003
式中，I是3x3的单位矩阵，
Figure PCTCN2017075814-appb-000004
vf＝(0，0，1)为参考向量。
步骤S5，判断所述单车的偏转角度是否超过设定角度阈值，若是，则判定为单车已经倒地，此时可以自动调用监控摄像头的本地GPS定位信息，由于监 控摄像头的监控范围有限，能被某一监控摄像头拍摄到说明倒地单车就在该监控摄像头附近一定区域，因此把监控摄像头的本地GPS定位信息默认为倒地单车的大致位置，并将所述本地GPS定位信息编辑到第一告警提示信息中进行输出显示，以通知相应的工作人员有单车倒地需要处理。
采用本发明的方案，首先相比于人工检测的效率更高，能第一时间发现倒地单车并进行通知；此外，相比于在单车上增加硬件传感器以检测单车是否倒地的方案来说，一方面不会增加单车的硬件成本，而且后期维护成本相比于硬件传感器的方案来说也更低；另一方面，从检测的准确性来讲，本方案能达到99％以上的准确率，相比硬件传感器的方案更具有优势。
作为一个较好的实施例，本发明的一种自动检测单车是否倒地的方法，在提取单车识别码图像之后、将单车识别码图像与原始识别码图像进行对比之前，还可以包括如下步骤：
从所述车把上贴着的单车识别码图像中提取出第一关键特征点；以及从所述坐杆上贴着的单车识别码图像中提取出第二关键特征点；
计算所述第一关键特征点和第二关键特征点之间的距离；
判断所述距离是否在预设的距离阈值内，若否，则输出第二告警提示信息，以提示相应的工作人员所述单车识别码出现故障。
因为考虑到单车识别码可能会被人为损坏的情况出现，为了确保本发明方案计算的准确性，当上述实施中中计算出来的第一关键特征点和第二关键特征点之间的距离不满足预设的距离阈值时，说明有可能单车识别码出现了故障，例如丢失或损坏了等，此时进行告警提示，通知相应的工作人员更换单车识别码。
在其中一个实施例中，所述单车识别码中可以包括4个子识别码，且该4个子识别码分别位于单车识别码的四个边角上；则此时步骤S3中将提取到的单车识别码图像与预先存储的原始识别码图像进行对比、确定单车识别码图像相对于所述原始识别码图像的偏移角度和偏移方向的过程具体可以包括如下步骤：
步骤S31，对所述单车识别码图像进行图像分割处理，获得单车识别码图像的四个边角图像；
步骤S32，将所述四个边角图像进行二值化处理，提取四个边角图像中具有预定特征点的子识别码图像；
步骤S33，将各子识别码图像输入识别码数据库中与预先存储的原始识别码图像进行对比，分别计算每个子识别码图像相对于所述原始识别码图像的偏移角度和偏移方向；
步骤S34，对计算出来的每个子识别码图像的偏移角度和偏移方向进行离群计算，剔除离群点数值，并对剩下的子识别码图像的偏移角度和偏移方向计算加权平均值，将所述加权平均值作为所述单车识别码图像相对于所述原始识别码图像的偏移角度和偏移方向。
通过以上方案可以看出，本发明的一种自动检测单车是否倒地的方法，预先在单车的车把和坐杆上贴有单车识别码，通过计算单车识别码图像的偏移角度和偏移方向来计算单车的偏转角度，由于借助了单车识别码来检测单车是否倒地，且由于单车识别码图像中的特征点较为明显，容易识别，因此能够极大提高对单车倒地检测的效率，降低了计算复杂度，检测的准确度也得到显著提升。

Claims (5)

  1. 一种自动检测单车是否倒地的方法，其特征在于，包括如下步骤：
    获取监控摄像头实时拍摄到的视频图像，并检测该视频图像中是否存在单车；
    若存在单车，则从视频图像中提取分别贴在单车的车把和坐杆上的单车识别码图像；
    将提取到的单车识别码图像与预先存储的原始识别码图像进行对比，确定所述单车识别码图像相对于所述原始识别码图像的偏移角度和偏移方向；
    根据所述偏移角度和偏移方向计算单车的偏转角度，具体为：根据所述偏移角度α和偏移方向(fx,fy,fz)计算旋转系数H，并根据所述旋转系数H计算单车相当于基准角度的偏转角度β；采用如下公式：
    Figure PCTCN2017075814-appb-100001
    式中，I是3x3的单位矩阵，
    Figure PCTCN2017075814-appb-100002
    vf＝(0，0，1)；
    判断所述单车的偏转角度是否超过设定角度阈值，若是，则判定为单车已经倒地，此时自动获取本地GPS定位信息，并将所述本地GPS定位信息编辑到第一告警提示信息中进行输出显示，以通知相应的工作人员有单车倒地需要处理。
  2. 根据权利要求1所述的自动检测单车是否倒地的方法，其特征在于，在提取单车识别码图像之后、将单车识别码图像与原始识别码图像进行对比之前，还包括步骤：
    从所述车把上贴着的单车识别码图像中提取出第一关键特征点；以及从所述坐杆上贴着的单车识别码图像中提取出第二关键特征点；
    计算所述第一关键特征点和第二关键特征点之间的距离；
    判断所述距离是否在预设的距离阈值内，若否，则输出第二告警提示信息，以提示相应的工作人员所述单车识别码出现故障。
  3. 根据权利要求1或2所述的自动检测单车是否倒地的方法，其特征在于，所述检测视频图像中是否存在单车的过程包括：
    将所述视频图像输入到预先建立的单车模型中进行匹配，提取所述视频图像中的物体特征进行相似度计算；
    当相似度计算的结果超过设定特征阈值时，判定为检测到视频图像中存在单车，并提取出与所述物体特征相近的纹理进行保存。
  4. 根据权利要求3所述的自动检测单车是否倒地的方法，其特征在于，所述单车识别码中包括方向信息。
  5. 根据权利要求4所述的自动检测单车是否倒地的方法，其特征在于，所述单车识别码中包括4个子识别码，该4个子识别码分别位于四个边角；
    所述将提取到的单车识别码图像与预先存储的原始识别码图像进行对比、确定单车识别码图像相对于所述原始识别码图像的偏移角度和偏移方向的过程包括：
    对所述单车识别码图像进行图像分割处理，获得单车识别码图像的四个边角图像；
    将所述四个边角图像进行二值化处理，提取四个边角图像中具有预定特征点的子识别码图像；
    将各子识别码图像输入识别码数据库中与预先存储的原始识别码图像进行对比，分别计算每个子识别码图像相对于所述原始识别码图像的偏移角度和偏移方向；
    对计算出来的每个子识别码图像的偏移角度和偏移方向进行离群计算，剔除离群点数值，并对剩下的子识别码图像的偏移角度和偏移方向计算加权平均值，将所述加权平均值作为所述单车识别码图像相对于所述原始识别码图像的偏移角度和偏移方向。
PCT/CN2017/075814 2016-05-09 2017-03-07 自动检测单车是否倒地的方法 WO2017193679A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201780001008.1A CN107851326A (zh) 2016-05-09 2017-03-07 自动检测单车是否倒地的方法

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610301154.3 2016-05-09
CN201610301154.3A CN106014570A (zh) 2016-05-09 2016-05-09 处理汽车尾气中一氧化碳的方法及系统

Publications (1)

Publication Number Publication Date
WO2017193679A1 true WO2017193679A1 (zh) 2017-11-16

Family

ID=57098823

Family Applications (2)

Application Number Title Priority Date Filing Date
PCT/CN2017/074035 WO2017193663A1 (zh) 2016-05-09 2017-02-19 处理汽车尾气中一氧化碳的方法
PCT/CN2017/075814 WO2017193679A1 (zh) 2016-05-09 2017-03-07 自动检测单车是否倒地的方法

Family Applications Before (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/074035 WO2017193663A1 (zh) 2016-05-09 2017-02-19 处理汽车尾气中一氧化碳的方法

Country Status (2)

Country Link
CN (2) CN106014570A (zh)
WO (2) WO2017193663A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106014569A (zh) * 2016-05-09 2016-10-12 饶川辉 汽车尾气中的一氧化碳处理方法及系统
CN105840284A (zh) * 2016-05-09 2016-08-10 黄安武 处理尾气中一氧化碳的方法及系统
CN106014570A (zh) * 2016-05-09 2016-10-12 黄安武 处理汽车尾气中一氧化碳的方法及系统
CN109147200A (zh) * 2018-07-24 2019-01-04 李公健 识别车辆方位与道路的角度和距离是否正确的管理系统
CN110927330B (zh) * 2019-05-05 2022-03-25 唐山师范学院 一种基于obd数据采集的柴油货车尾气排放分析装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007269223A (ja) * 2006-03-31 2007-10-18 Nissin Kogyo Co Ltd 自動２輪車用システム
CN103134425A (zh) * 2011-11-30 2013-06-05 佳能株式会社 信息处理装置及信息处理方法
CN103996019A (zh) * 2014-02-24 2014-08-20 香港应用科技研究院有限公司 用于检测和跟踪一个物体上多个部位的系统和方法
CN204895677U (zh) * 2015-07-14 2015-12-23 于洪涛 一种电动自行车的倾倒报警装置
CN106447733A (zh) * 2016-09-28 2017-02-22 北京理工大学 颈椎活动度及活动轴线位置的确定方法、系统及装置

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5922640A (en) * 1996-02-29 1999-07-13 Mitsubishi Gas Chemical Company, Inc. Adsorbent for carbon monoxide
JP2002048711A (ja) * 2000-08-03 2002-02-15 Mitsubishi Heavy Ind Ltd レーザー計測装置
JP3726884B2 (ja) * 2001-04-25 2005-12-14 学校法人日本大学 慣性計測装置を用いた姿勢推定装置及び方法並びにプログラム
JP4227991B2 (ja) * 2005-12-28 2009-02-18 トヨタ自動車株式会社 排ガス分析装置および排ガス分析方法
CN101179706B (zh) * 2006-11-07 2010-04-07 国立阳明大学 远程居家监视系统及其方法
CN102646316B (zh) * 2012-04-28 2013-09-18 中国人民解放军国防科学技术大学 基于哨位的综合安防监控方法及系统
DE102014201271A1 (de) * 2014-01-24 2015-07-30 Robert Bosch Gmbh Verfahren und Steuergerät zum Erkennen einer Veränderung eines relativen Gierwinkels innerhalb eines Stereo-Video-Systems für ein Fahrzeug
CN104239851B (zh) * 2014-07-25 2018-05-01 重庆科技学院 基于行为分析的智能小区巡检系统及其控制方法
CN104751097B (zh) * 2015-03-30 2018-05-11 深圳市道通科技股份有限公司 一种车辆识别码的检测处理方法及装置
CN104794463B (zh) * 2015-05-11 2018-12-14 华东理工大学 基于Kinect实现室内人体跌倒检测的系统及方法
CN104833358B (zh) * 2015-05-13 2018-11-20 上海交通大学 基于罗德里格斯参数的星敏感器几何线性姿态确定方法
CN105354540A (zh) * 2015-10-22 2016-02-24 上海鼎松物联网科技有限公司 基于视频分析实现人员倒地行为检测的方法
CN105319178B (zh) * 2015-10-27 2018-05-04 中国科学院合肥物质科学研究院 机动车尾气co和co2浓度实时检测系统及其控制方法
CN105840284A (zh) * 2016-05-09 2016-08-10 黄安武 处理尾气中一氧化碳的方法及系统
CN106014570A (zh) * 2016-05-09 2016-10-12 黄安武 处理汽车尾气中一氧化碳的方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007269223A (ja) * 2006-03-31 2007-10-18 Nissin Kogyo Co Ltd 自動２輪車用システム
CN103134425A (zh) * 2011-11-30 2013-06-05 佳能株式会社 信息处理装置及信息处理方法
CN103996019A (zh) * 2014-02-24 2014-08-20 香港应用科技研究院有限公司 用于检测和跟踪一个物体上多个部位的系统和方法
CN204895677U (zh) * 2015-07-14 2015-12-23 于洪涛 一种电动自行车的倾倒报警装置
CN106447733A (zh) * 2016-09-28 2017-02-22 北京理工大学 颈椎活动度及活动轴线位置的确定方法、系统及装置

Also Published As

Publication number Publication date
CN106014570A (zh) 2016-10-12
WO2017193663A1 (zh) 2017-11-16
CN107851326A (zh) 2018-03-27

Similar Documents

Publication Publication Date Title
WO2017193679A1 (zh) 自动检测单车是否倒地的方法
WO2017193701A1 (zh) 共享单车的倒地检测方法
US7916944B2 (en) System and method for feature level foreground segmentation
CN104751491B (zh) 一种人群跟踪及人流量统计方法及装置
US9754160B2 (en) Method and device for detecting gathering of objects based on stereo vision as well as non-transitory computer-readable medium
JP6904346B2 (ja) 画像処理装置、画像処理システム、および画像処理方法、並びにプログラム
CN108399627B (zh) 视频帧间目标运动估计方法、装置和实现装置
US20110280478A1 (en) Object monitoring system and method
JP5106302B2 (ja) 移動物体追跡装置
US20200013148A1 (en) System and Method for Detecting Motion Anomalies in Video
JP2008286725A (ja) 人物検出装置および方法
JP6226368B2 (ja) 車両監視装置、および車両監視方法
JP6803525B2 (ja) 顔検出装置およびこれを備えた顔検出システムならびに顔検出方法
TWI493510B (zh) 跌倒偵測方法
US20110280442A1 (en) Object monitoring system and method
WO2023273010A1 (zh) 高空抛物检测方法和装置、设备，及计算机存储介质
Verma et al. Analysis of moving object detection and tracking in video surveillance system
JP2002342762A (ja) 物体追跡方法
Wang Research and implementation of intrusion detection algorithm in video surveillance
KR20200060868A (ko) 객체 탐지 및 자동 추적이 가능한 다시점 영상 감시 시스템
US20210089818A1 (en) Deposit detection device and deposit detection method
JP6527183B2 (ja) 放置物検出装置
JP5142416B2 (ja) 物体検出装置
Fei et al. Drowning detection based on background subtraction
CN107067411B (zh) 一种结合密集特征的Mean-shift跟踪方法

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17795297

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 17795297

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 24/05/2019)

122 Ep: pct application non-entry in european phase

Ref document number: 17795297

Country of ref document: EP

Kind code of ref document: A1