技术领域technical field
本发明涉及车辆定位技术领域，尤其涉及一种车辆重定位的方法及装置。The invention relates to the technical field of vehicle positioning, in particular to a method and device for vehicle repositioning.
背景技术Background technique
车联网系统是近年兴起的一种以提高交通效率和交通安全为主要目的的网络与应用系统，车辆定位技术是其中的关键技术，获取精确位置对于提高智能车辆的安全性和实现自主驾驶都具有重要意义。The Internet of Vehicles system is a network and application system that has emerged in recent years with the main purpose of improving traffic efficiency and traffic safety. Vehicle positioning technology is one of the key technologies. Acquiring accurate positions is important for improving the safety of intelligent vehicles and realizing autonomous driving. important meaning.
目前，汽车用于高精度导航与定位的地图主要分为两类，一类为激光点云为主的地图(激光雷达地图)，一类为矢量信息为主的地图(高精度矢量地图)。当车辆借助高精度地图的行驶过程中，因为某些原因突然丢失自身位置时，需要快速准确地在高精度地图中恢复自身的定位(称为重定位)，以保障车辆(特别是导航系统)的正常运行。现有技术中，主要技术有基于激光点云匹配的重定位方法和基于图像点特征信息的重定位方法。其中，基于激光点云匹配的方法依赖于GPS、IMU、里程计等辅助信息给出较为精准的初始搜索位置，在缺少辅助信息时(如隧道、高楼等)，重定位的运算量非常大，无法快速完成。基于图像点特征的信息鲁棒性较差。At present, the maps used by automobiles for high-precision navigation and positioning are mainly divided into two categories, one is the map based on laser point cloud (lidar map), and the other is the map based on vector information (high-precision vector map). When the vehicle suddenly loses its position due to some reasons while driving with the aid of a high-precision map, it is necessary to quickly and accurately restore its own position in the high-precision map (called relocation) to ensure the vehicle (especially the navigation system) of normal operation. In the prior art, the main technologies include a relocation method based on laser point cloud matching and a relocation method based on image point feature information. Among them, the method based on laser point cloud matching relies on auxiliary information such as GPS, IMU, and odometer to give a more accurate initial search position. When there is a lack of auxiliary information (such as tunnels, high-rise buildings, etc.), the amount of calculation for relocation is very large. Can't do it quickly. Information based on image point features is less robust.
因此，如何减少重定位过程中的计算量，且提高计算的鲁棒性是本领域技术人员亟待解决的问题。Therefore, how to reduce the amount of calculation in the relocation process and improve the robustness of the calculation is an urgent problem to be solved by those skilled in the art.
发明内容Contents of the invention
本发明提供一种车辆重定位的方法及装置，以减少重定位过程中的计算量，且提高计算的鲁棒性。The invention provides a method and device for vehicle relocation to reduce the calculation amount in the relocation process and improve the robustness of the calculation.
本发明实施例提供一种车辆重定位的方法，包括：An embodiment of the present invention provides a method for vehicle relocation, including:
获取待定位车辆的环境图像；Obtain the environment image of the vehicle to be positioned;
提取所述环境图像中的预设特征信息；所述预设特征信息包括几何特征信息和/或语义特征信息；Extracting preset feature information in the environment image; the preset feature information includes geometric feature information and/or semantic feature information;
根据所述预设特征信息构建所述环境图像对应的视觉特征；Constructing visual features corresponding to the environmental image according to the preset feature information;
将所述视觉特征与预设视觉特征进行匹配，以确定所述待定位车辆所在的位置；其中，所述预设视觉特征为地图数据中的视觉特征。Matching the visual features with preset visual features to determine the location of the vehicle to be positioned; wherein the preset visual features are visual features in map data.
在本发明一实施例中，所述根据所述预设特征信息构建所述环境图像对应的视觉特征，包括：In an embodiment of the present invention, the constructing the visual features corresponding to the environmental image according to the preset feature information includes:
确定所述预设特征信息对应的描述子；determining a descriptor corresponding to the preset feature information;
确定所述描述子对应的词袋模型中的单词；其中，每一个所述单词对应一个或多个所述描述子；Determining the words in the bag-of-words model corresponding to the descriptor; wherein, each of the words corresponds to one or more of the descriptors;
根据与每一个所述单词匹配的描述子的个数构建所述环境图像对应的视觉特征。A visual feature corresponding to the environment image is constructed according to the number of descriptors matched with each word.
在本发明一实施例中，所述根据所述预设特征信息构建所述环境图像对应的视觉特征之前，还包括：In an embodiment of the present invention, before constructing the visual features corresponding to the environmental image according to the preset feature information, it further includes:
将所述环境图像划分为多个子区域；dividing the environment image into a plurality of sub-regions;
所述根据所述预设特征信息构建所述环境图像对应的视觉特征，包括：The constructing the visual features corresponding to the environmental image according to the preset feature information includes:
确定每一个子区域中预设特征信息对应的特征向量；determining a feature vector corresponding to preset feature information in each sub-region;
将每一个所述子区域对应的特征向量按照分布位置进行向量组合，构建所述环境图像对应的视觉特征。Combining the feature vectors corresponding to each of the sub-regions according to the distribution position to construct the visual features corresponding to the environment image.
在本发明一实施例中，所述将所述环境图像划分为多个子区域之前，还包括：In an embodiment of the present invention, before dividing the environment image into multiple sub-regions, it further includes:
确定所述环境图像中的消隐点；determining vanishing points in the environment image;
所述将所述环境图像划分为多个子区域，包括：The said environment image is divided into a plurality of sub-regions, including:
根据所述消隐点将所述环境图像划分为所述多个子区域。The environment image is divided into the plurality of sub-regions according to the blanking points.
在本发明一实施例中，所述环境图像包括激光点云数据，所述提取所述环境图像中的预设特征信息，包括：In an embodiment of the present invention, the environmental image includes laser point cloud data, and the extraction of preset feature information in the environmental image includes:
提取所述环境图像中的特征信息；extracting feature information in the environment image;
根据预设规则在所述特征信息中选取所述预设特征信息；其中，所述预设规则为随机采样规则、法向量分布规则集均匀采样规则中的一种或多种的组合。The preset feature information is selected from the feature information according to a preset rule; wherein, the preset rule is a random sampling rule, a normal vector distribution rule set uniform sampling rule or a combination of one or more of them.
本发明实施例还提供一种车辆重定位的装置，包括：The embodiment of the present invention also provides a vehicle repositioning device, including:
获取单元，用于获取待定位车辆的环境图像；an acquisition unit, configured to acquire an environment image of the vehicle to be positioned;
提取单元，用于提取所述环境图像中的预设特征信息；所述预设特征信息包括几何特征信息和/或语义特征信息；An extraction unit, configured to extract preset feature information in the environment image; the preset feature information includes geometric feature information and/or semantic feature information;
构建单元，用于根据所述预设特征信息构建所述环境图像对应的视觉特征；A construction unit, configured to construct visual features corresponding to the environmental image according to the preset feature information;
确定单元，用于将所述视觉特征与预设视觉特征进行匹配，以确定所述待定位车辆所在的位置；其中，所述预设视觉特征为地图数据中的视觉特征。A determination unit, configured to match the visual features with preset visual features to determine the location of the vehicle to be positioned; wherein the preset visual features are visual features in map data.
在本发明一实施例中，所述构建单元，具体用于确定所述预设特征信息对应的描述子；确定所述描述子对应的词袋模型中的单词；其中，每一个所述单词对应一个或多个所述描述子；并根据与每一个所述单词匹配的描述子的个数构建所述环境图像对应的视觉特征。In an embodiment of the present invention, the construction unit is specifically configured to determine the descriptor corresponding to the preset feature information; determine the word in the bag-of-words model corresponding to the descriptor; wherein, each of the words corresponds to One or more descriptors; and constructing visual features corresponding to the environment image according to the number of descriptors matching each of the words.
在本发明一实施例中，该车辆重定位的装置还包括划分单元；In an embodiment of the present invention, the vehicle repositioning device further includes a dividing unit;
所述划分单元，用于将所述环境图像划分为多个子区域；The division unit is configured to divide the environment image into a plurality of sub-regions;
所述构建单元，具体用于确定每一个子区域中预设特征信息对应的特征向量；并将每一个所述子区域对应的特征向量按照分布位置进行向量组合，构建所述环境图像对应的视觉特征。The construction unit is specifically used to determine the feature vectors corresponding to the preset feature information in each sub-region; and combine the feature vectors corresponding to each of the sub-regions according to the distribution position to construct the visual image corresponding to the environmental image. feature.
在本发明一实施例中，所述确定单元，还用于确定所述环境图像中的消隐点；In an embodiment of the present invention, the determining unit is further configured to determine a vanishing point in the environment image;
所述划分单元，具体用于根据所述消隐点将所述环境图像划分为所述多个子区域。The dividing unit is specifically configured to divide the environment image into the plurality of sub-regions according to the blanking points.
在本发明一实施例中，所述环境图像包括激光点云数据；In an embodiment of the present invention, the environment image includes laser point cloud data;
所述提取单元，具体用于提取所述环境图像中的特征信息；并根据预设规则在所述特征信息中选取所述预设特征信息；其中，所述预设规则为随机采样规则、法向量分布规则集均匀采样规则中的一种或多种的组合。The extraction unit is specifically configured to extract feature information in the environmental image; and select the preset feature information from the feature information according to preset rules; wherein, the preset rules are random sampling rules, methods A combination of one or more uniform sampling rules in the vector distribution rule set.
本发明实施例提供的车辆位置重定位的方法及装置，通过获取待定位车辆的环境图像，并提取环境图像中的预设特征信息；再根据预设特征信息构建环境图像对应的视觉特征；之后，再将视觉特征与预设视觉特征进行匹配，从而确定待定位车辆所在的位置。由此可见，本发明实施例提供的车辆位置重定位的方法及装置，在确定待定位车辆所在位置时，是根据预先构建环境图像对应的视觉特征，并将该视觉特征与地图数据的预设视觉特征进行匹配，从而确定待定位车辆所在位置，不仅减少了重定位过程中的计算量，而且提高了计算的鲁棒性。The method and device for vehicle position relocation provided by the embodiments of the present invention obtain the environment image of the vehicle to be positioned, and extract the preset feature information in the environment image; then construct the corresponding visual features of the environment image according to the preset feature information; and then , and then match the visual features with the preset visual features to determine the location of the vehicle to be located. It can be seen that the vehicle position relocation method and device provided by the embodiments of the present invention, when determining the position of the vehicle to be positioned, is based on the visual features corresponding to the pre-built environment image, and combines the visual features with the preset map data. Visual features are matched to determine the location of the vehicle to be located, which not only reduces the amount of calculation in the relocation process, but also improves the robustness of the calculation.
附图说明Description of drawings
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure.
图1为本发明实施例提供的一种车辆重定位的方法的示意图；FIG. 1 is a schematic diagram of a vehicle relocation method provided by an embodiment of the present invention;
图2为本发明实施例提供的一种环境图像的示意图；FIG. 2 is a schematic diagram of an environment image provided by an embodiment of the present invention;
图3为本发明实施例提供的一种标注点特征的环境图像的示意图；FIG. 3 is a schematic diagram of an environment image marked with point features provided by an embodiment of the present invention;
图4为本发明实施例提供的一种标注线特征和圆特征的环境图像的示意图；Fig. 4 is a schematic diagram of an environment image marked with line features and circle features provided by an embodiment of the present invention;
图5为本发明实施例提供的一种标注语义特征的环境图像的示意图；FIG. 5 is a schematic diagram of an environmental image marked with semantic features provided by an embodiment of the present invention;
图6为本发明实施例提供的一种构建环境图像对应的视觉特征的示意图；FIG. 6 is a schematic diagram of visual features corresponding to a construction environment image provided by an embodiment of the present invention;
图7为本发明实施例提供的一种通过对应词袋模型中的单词构建环境图像对应的视觉特征的示意图；FIG. 7 is a schematic diagram of a visual feature corresponding to an environment image constructed by corresponding words in the bag-of-words model provided by an embodiment of the present invention;
图8为本发明实施例提供的另一种构建环境图像对应的视觉特征的示意图；FIG. 8 is a schematic diagram of another visual feature corresponding to a construction environment image provided by an embodiment of the present invention;
图9为本发明实施例提供的通过划分子区域构建环境图像对应的视觉特征的示意图；FIG. 9 is a schematic diagram of constructing visual features corresponding to an environment image by dividing sub-regions according to an embodiment of the present invention;
图10为本发明实施例提供的一种通过消隐点划分环境图像的示意图；Fig. 10 is a schematic diagram of dividing an environment image by blanking points according to an embodiment of the present invention;
图11为本发明实施例提供的另一种通过消隐点划分环境图像的示意图；FIG. 11 is another schematic diagram of dividing an environment image by blanking points according to an embodiment of the present invention;
图12为本发明实施例提供的再一种通过消隐点划分环境图像的示意图；Fig. 12 is another schematic diagram of dividing an environment image by blanking points provided by an embodiment of the present invention;
图13为本发明实施例提供的一种车辆重定位的装置的结构示意图；Fig. 13 is a schematic structural diagram of a vehicle repositioning device provided by an embodiment of the present invention;
图14为本发明实施例提供的另一种车辆重定位的装置的结构示意图。Fig. 14 is a schematic structural diagram of another vehicle relocation device provided by an embodiment of the present invention.
通过上述附图，已示出本公开明确的实施例，后文中将有更详细的描述。这些附图和文字描述并不是为了通过任何方式限制本公开构思的范围，而是通过参考特定实施例为本领域技术人员说明本公开的概念。By means of the above-mentioned drawings, certain embodiments of the present disclosure have been shown and will be described in more detail hereinafter. These drawings and written description are not intended to limit the scope of the disclosed concept in any way, but to illustrate the disclosed concept for those skilled in the art by referring to specific embodiments.
具体实施方式Detailed ways
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.
本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”“第四”等(如果存在)是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本发明的实施例例如能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects and not necessarily Describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of practice in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device comprising a sequence of steps or elements is not necessarily limited to the expressly listed instead, may include other steps or elements not explicitly listed or inherent to the process, method, product or apparatus.
下面以具体的实施例对本发明的技术方案以及本申请的技术方案如何解决上述技术问题进行详细说明。下面这几个具体的实施例可以相互结合，对于相同或相似的概念或过程在某些实施例中不再赘述。下面将结合附图，对本发明的实施例进行描述。The technical solution of the present invention and how the technical solution of the present application solves the above technical problems will be described in detail below with specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes will not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
图1为本发明实施例提供的一种车辆重定位的方法的示意图，该车辆重定位的方法可以由车辆重定位的装置执行，该车辆重定位的装置可以独立设置，也可以设置在车辆的处理器中，请参见图1所示，该车辆重定位的方法可以包括：Fig. 1 is a schematic diagram of a vehicle relocation method provided by an embodiment of the present invention. The vehicle relocation method can be executed by a vehicle relocation device. The vehicle relocation device can be set independently or in a vehicle In the processor, as shown in Figure 1, the method for vehicle relocation may include:
S101、获取待定位车辆的环境图像。S101. Acquire the environment image of the vehicle to be positioned.
其中，环境图像用于指示待定位车辆的周围环境情况。可选的，该环境图像还可以包括激光点云数据和GPS数据。其中，激光点云信息能够反映周围环境的真实三维几何信息和材质信息；GPS信息能够反映周围环境的经纬度信息。Wherein, the environment image is used to indicate the surrounding environment of the vehicle to be positioned. Optionally, the environment image may also include laser point cloud data and GPS data. Among them, laser point cloud information can reflect the real three-dimensional geometric information and material information of the surrounding environment; GPS information can reflect the latitude and longitude information of the surrounding environment.
在本发明实施例中，可以通过传感器获取待定位车辆的环境图像，也可以通过其他方式获取待定位车辆的环境图像。示例的，请参见图2所示，图2为本发明实施例提供的一种环境图像的示意图，该环境图像中可以包括车道线信息、路灯信息及交通灯信息等。In the embodiment of the present invention, the environment image of the vehicle to be positioned may be acquired by a sensor, or the environment image of the vehicle to be positioned may be acquired by other means. For an example, please refer to FIG. 2 . FIG. 2 is a schematic diagram of an environment image provided by an embodiment of the present invention. The environment image may include lane line information, street light information, traffic light information, and the like.
S102、提取环境图像中的预设特征信息。S102. Extract preset feature information in the environment image.
其中，预设特征信息可以包括几何特征信息和/或语义特征信息。Wherein, the preset feature information may include geometric feature information and/or semantic feature information.
需要说明的是，此处的几何特征信息可以包括点特征信息，当然，也可以包括线特征信息及圆特征信息。即在本发明实施例中，在提取环境图像中的预设特征信息时，可以只提取环境图像中的几何特征信息或语义特征信息中的一个，也可以同时提取环境图像中的几何特征信息和语义特征信息。详细来说，在提取环境图像中的预设特征信息时，可以只提取线特征信息和圆特征信息；也可以只提取语义特征信息；当然，也可以提取点特征信息、线特征信息及圆特征信息；也可以提取点特征信息和语义特征信息，也可以提取线特征信息、圆特征信息及语义特征信息，也可以同时提取点特征信息、线特征信息、圆特征信息及语义特征信息。It should be noted that the geometric feature information here may include point feature information, and of course, line feature information and circle feature information may also be included. That is, in the embodiment of the present invention, when extracting the preset feature information in the environment image, only one of the geometric feature information or the semantic feature information in the environment image can be extracted, and the geometric feature information and the semantic feature information in the environment image can also be extracted simultaneously. Semantic feature information. In detail, when extracting the preset feature information in the environment image, only line feature information and circle feature information can be extracted; only semantic feature information can be extracted; of course, point feature information, line feature information and circle feature information can also be extracted Information; point feature information and semantic feature information can also be extracted, line feature information, circle feature information and semantic feature information can also be extracted, and point feature information, line feature information, circle feature information and semantic feature information can also be extracted at the same time.
示例的，在本发明实施例中，点特征等灰度特征可以是SIFT特征、SURF特征、ORB特征等具有特征描述子的图像特征，也可以是特征点组合描述子的图像特征，比如FAST特征点及BRISK描述子。由于点特征等图像的灰度特征能够反映周围环境的纹理信息，且具有一定的不变性，因此，可以通过比较两幅不同图像中特征点的相似程度来衡量图像的相似度，进而衡量车辆位置的相似度。示例的，请参见图3所示，图3为本发明实施例提供的一种标注点特征的环境图像的示意图。Exemplarily, in the embodiment of the present invention, grayscale features such as point features can be image features with feature descriptors such as SIFT features, SURF features, ORB features, or image features of feature point combination descriptors, such as FAST features Point and BRISK descriptor. Since the grayscale features of images such as point features can reflect the texture information of the surrounding environment and have certain invariance, the similarity of the images can be measured by comparing the similarity of the feature points in two different images, and then the vehicle position can be measured similarity. For an example, please refer to FIG. 3 , which is a schematic diagram of an environment image marked with point features provided by an embodiment of the present invention.
图像的几何特征能够反映周围环境的几何投影信息。以该几何特征包括线特征和圆特征为例，几何线特征可通过Hough变换或者Line Segment Detector等方法获取。线特征的描述可以由Line Binary Descriptor(LBD)等方法计算。由于图像的几何特征能够反映周围环境的几何信息，例如车道线是斜向直线，交通灯的灯柱是竖直直线，建筑有斜向、竖直和水平直线等。由于几何线段具有一定的尺度(长度)，因此，在相似位置的图像中有相似的分布，几何特征的描述子同样可用来衡量图像的相似度，因此，可以通过比较两幅不同图像中几何特征来衡量车辆位置的相似度。示例的，请参见图4所示，图4为本发明实施例提供的一种标注线特征和圆特征的环境图像的示意图，结合图4可以看出，车道线信息可以标注为线特征，交通灯信息可以标注为圆特征。The geometric features of the image can reflect the geometric projection information of the surrounding environment. Taking the geometric features including line features and circle features as an example, the geometric line features can be obtained by methods such as Hough transform or Line Segment Detector. The description of line features can be calculated by methods such as Line Binary Descriptor (LBD). Because the geometric features of the image can reflect the geometric information of the surrounding environment, for example, the lane lines are oblique straight lines, the lampposts of traffic lights are vertical straight lines, and buildings have oblique, vertical and horizontal straight lines. Since the geometric line segment has a certain scale (length), there is a similar distribution in images of similar positions, and the descriptor of the geometric feature can also be used to measure the similarity of the image. Therefore, the geometric features in two different images can be compared to measure the similarity of vehicle locations. For an example, please refer to Figure 4, which is a schematic diagram of an environment image marked with line features and circle features provided by an embodiment of the present invention. It can be seen from Figure 4 that lane line information can be marked as line features, traffic Light information can be annotated as a circle feature.
图像的语义特征能够反映周围环境的真实含义信息，语义特征信息可以是车道线、道路标志牌、限速标志、路灯、交通灯、停止线等常见道路元素，也可以是停车场出入口、车位、加油站等与行车有关的局部信息。车辆在相似位置的图像必然包含极为相似的语义信息，因此，可以用来衡量车辆位置的相似度。请参见图5所示，图5为本发明实施例提供的一种标注语义特征的环境图像的示意图，结合图5可以看出，车道线信息可以标注为语义特征，交通灯信息可以标注为语义特征，路灯信息可以标注为语义特征。The semantic features of the image can reflect the real meaning information of the surrounding environment. The semantic feature information can be common road elements such as lane lines, road signs, speed limit signs, street lights, traffic lights, stop lines, etc., or parking lot entrances and exits, parking spaces, Local information related to driving, such as gas stations. Images of vehicles in similar locations must contain very similar semantic information, so they can be used to measure the similarity of vehicle locations. Please refer to Figure 5, which is a schematic diagram of an environmental image marked with semantic features provided by an embodiment of the present invention. It can be seen from Figure 5 that lane line information can be marked as semantic features, and traffic light information can be marked as semantic features features, street light information can be marked as semantic features.
可选的，当环境图像包括激光点云数据，提取环境图像中的预设特征信息可以通过以下可能的方式实现：Optionally, when the environment image includes laser point cloud data, the extraction of preset feature information in the environment image can be achieved in the following possible ways:
提取环境图像中的特征信息，并根据预设规则在特征信息中选取预设特征信息；其中，预设规则为随机采样规则、法向量分布规则集均匀采样规则中的一种或多种的组合。Extract feature information in the environment image, and select preset feature information from the feature information according to preset rules; wherein, the preset rule is a combination of one or more of random sampling rules, normal vector distribution rule set uniform sampling rules .
在提取到环境图像中的预设特征信息之后，就可以执行下述S103根据预设特征信息构建环境图像对应的视觉特征。After the preset feature information in the environment image is extracted, the following S103 may be executed to construct visual features corresponding to the environment image according to the preset feature information.
S103、根据预设特征信息构建环境图像对应的视觉特征。S103. Construct visual features corresponding to the environment image according to preset feature information.
可选的，在本发明实施例中，S103根据预设特征信息构建环境图像对应的视觉特征可以通过以下至少两种可能的方式实现，一种可能的方式是通过对应词袋模型中的单词构建环境图像对应的视觉特征；另一种可能的方式是通过划分子区域构建环境图像对应的视觉特征。下面，将详细描述这两种可能的实现方式。Optionally, in the embodiment of the present invention, S103 constructing the visual features corresponding to the environment image according to the preset feature information can be realized in the following at least two possible ways, one possible way is to construct words corresponding to the bag-of-words model The visual features corresponding to the environment image; another possible way is to construct the visual features corresponding to the environment image by dividing sub-regions. In the following, these two possible implementations will be described in detail.
在一种可能的实现方式中，可以通过对应词袋模型中的单词构建环境图像对应的视觉特征，请参见图6所示，图6为本发明实施例提供的一种构建环境图像对应的视觉特征的示意图。In a possible implementation, the visual features corresponding to the environment image can be constructed by corresponding to the words in the bag-of-words model. Please refer to FIG. A schematic diagram of the features.
S601、确定预设特征信息对应的描述子。S601. Determine a descriptor corresponding to preset feature information.
S602、确定描述子对应的词袋模型中的单词。S602. Determine the word in the bag-of-words model corresponding to the descriptor.
其中，每一个单词对应一个或多个描述子。Among them, each word corresponds to one or more descriptors.
需要说明的是，预设特征信息可以对应多个描述子，将多个描述子中每一个描述子对应到词袋模型中的单词，在对应时，会存在多个描述子对应到一个单词的情况，使得对应到的单词的数量小于描述子的个数。It should be noted that the preset feature information can correspond to multiple descriptors, and each of the multiple descriptors corresponds to a word in the bag-of-words model. When corresponding, there will be multiple descriptors corresponding to a word situation, so that the number of corresponding words is less than the number of descriptors.
S603、根据与每一个单词匹配的描述子的个数构建环境图像对应的视觉特征。S603. Construct visual features corresponding to the environment image according to the number of descriptors matching each word.
在将每一个描述子对应到词袋模型中的单词之后，就可以计算每一个单词对应的描述子的个数，从而根据与每一个单词匹配的描述子的个数生成特征向量，该特征向量即为环境图像对应的视觉特征。示例的，若提取到的预设特征对应500个描述子，其中，200个描述子对应词袋模型中的单词1，200个描述子对应词袋模型中的单词2，剩余的100个描述子对应词袋模型中的单词3，则可以得到与单词1匹配的描述子的个数为200，与单词2匹配的的描述子的个数为200，与单词3匹配的的描述子的个数为100，则根据与每一个单词匹配的描述子的个数生成特征向量(200，200，100)，该特征向量(200，200，100)即为环境图像对应的视觉特征，从而实现构建环境图像对应的视觉特征。示例的，请参见图7所示，图7为本发明实施例提供的一种通过对应词袋模型中的单词构建环境图像对应的视觉特征的示意图。After each descriptor is corresponding to a word in the bag-of-words model, the number of descriptors corresponding to each word can be calculated, so as to generate a feature vector according to the number of descriptors matching each word, the feature vector It is the visual feature corresponding to the environment image. For example, if the extracted preset features correspond to 500 descriptors, 200 descriptors correspond to word 1 in the bag-of-words model, 200 descriptors correspond to word 2 in the bag-of-words model, and the remaining 100 descriptors Corresponding to word 3 in the bag-of-words model, the number of descriptors matching word 1 is 200, the number of descriptors matching word 2 is 200, and the number of descriptors matching word 3 is is 100, the feature vector (200, 200, 100) is generated according to the number of descriptors matching each word, and the feature vector (200, 200, 100) is the visual feature corresponding to the environment image, so as to realize the construction of the environment The corresponding visual features of the image. For an example, please refer to FIG. 7 , which is a schematic diagram of constructing visual features corresponding to an environment image by corresponding words in the bag-of-words model provided by an embodiment of the present invention.
在另一种可能的实现方式中，可以通过划分子区域构建环境图像对应的视觉特征，请参见图8所示，图8为本发明实施例提供的另一种构建环境图像对应的视觉特征的示意图。In another possible implementation, the visual features corresponding to the environment image can be constructed by dividing sub-regions, as shown in FIG. schematic diagram.
S801、将环境图像划分为多个子区域。S801. Divide the environment image into multiple sub-regions.
S802、确定每一个子区域中预设特征信息对应的特征向量。S802. Determine a feature vector corresponding to preset feature information in each sub-region.
S803、将每一个子区域对应的特征向量按照分布位置进行向量组合，构建环境图像对应的视觉特征。S803. Combining the feature vectors corresponding to each sub-region according to the distribution positions, to construct the visual features corresponding to the environment image.
在该种方式中，在构建环境图像对应的视觉特征时，需要先将环境图像划分为多个子区域，并确定每一个子区域中预设特征信息对应的特征向量，之后，再将每一个子区域对应的特征向量按照分布位置进行向量组合，向量组合后得到的向量即为环境图像对应的视觉特征。示例的，若将环境图像分为4个子区域，第一个子区域对应的特征向量为a，第二个子区域对应的特征向量为b，第三个子区域对应的特征向量为c，第四个子区域对应的特征向量为d，若四个子区域的分布位置为第一子区域、第二子区域、第三子区域及第四子区域，则将每一个子区域对应的特征向量按照分布位置进行向量组合，得到的向量为(a，b，c，d)。请参见图9所示，图9为本发明实施例提供的通过划分子区域构建环境图像对应的视觉特征的示意图。结合图9可以看出，在构建环境图像对应的视觉特征时，是将环境图像划分为9个子区域，从而根据9个子区域中每一个子区域的对应的特征向量构建环境图像对应的视觉特征。In this way, when constructing the visual features corresponding to the environment image, it is necessary to divide the environment image into multiple sub-regions first, and determine the feature vector corresponding to the preset feature information in each sub-region, and then divide each sub-region The feature vectors corresponding to the regions are combined according to the distribution position, and the vector obtained after the vector combination is the visual feature corresponding to the environment image. For example, if the environment image is divided into 4 sub-areas, the feature vector corresponding to the first sub-area is a, the feature vector corresponding to the second sub-area is b, the feature vector corresponding to the third sub-area is c, and the feature vector corresponding to the fourth sub-area is The eigenvector corresponding to the area is d, if the distribution positions of the four sub-areas are the first sub-area, the second sub-area, the third sub-area and the fourth sub-area, then the eigenvector corresponding to each sub-area is calculated according to the distribution position Combining vectors, the resulting vector is (a, b, c, d). Please refer to FIG. 9 , which is a schematic diagram of constructing visual features corresponding to an environment image by dividing sub-regions according to an embodiment of the present invention. It can be seen from Fig. 9 that when constructing the visual features corresponding to the environmental image, the environmental image is divided into 9 sub-regions, and the corresponding visual features of the environmental image are constructed according to the corresponding feature vectors of each of the 9 sub-regions.
可选的，在上述通过划分子区域构建环境图像对应的视觉特征的方案中，可以通过消隐点将环境图像划分为多个子区域，因此，需要先确定环境图像中的消隐点。请参见图10-图12所示，图10为本发明实施例提供的一种通过消隐点划分环境图像的示意图，图11为本发明实施例提供的另一种通过消隐点划分环境图像的示意图，图12为本发明实施例提供的再一种通过消隐点划分环境图像的示意图，其中，图10、图11及图12分别从不同的空间点确定消隐点，从而根据该消隐点对环境图像进行划分。Optionally, in the above scheme of constructing visual features corresponding to the environment image by dividing sub-regions, the environment image may be divided into multiple sub-regions by using the blanking points, therefore, the blanking points in the environment image need to be determined first. Please refer to Figures 10-12. Figure 10 is a schematic diagram of dividing an environmental image by blanking points provided by an embodiment of the present invention. Fig. 12 is another schematic diagram of dividing an environment image by blanking points according to an embodiment of the present invention, wherein Fig. 10, Fig. 11 and Fig. 12 respectively determine the blanking points from different spatial points, so that according to the blanking points Hidden points segment the environment image.
需要说明的是，消隐点为真实世界中一组平行直线在图像中的交点。请参见图10-图12所示，消隐点为图10-图14中两条车道线的延长线(黑色虚线)的交点。消隐点是无穷远处地平线上的一点，所有的消隐点构成了地平线。因此，在图像中，消隐点可作为空间划分的参考点。特别地，在道路上，所有的车道线构成了一组平行线，它们对应于图像中同一个消隐点。消隐点在图像中的位置与摄像头的焦距、像元和真实世界中平行线的方向有关。由于车辆型号、摄像头安装位置和角度的差异，图像中的消隐点并不是一成不变的。图10和图11展示了车辆在行车过程中的两个不同位置采集的环境图像中的消隐点的示意图。图10和图12展示了不同车辆(如轿车和SUV)在行车过程中的两个不同位置采集的环境图像中的消隐点的示意图，基于消隐点划分的区域具有一定的平移不变性，从而增加了视觉特征比对的准确性。It should be noted that the blanking point is the intersection point of a group of parallel straight lines in the real world in the image. Please refer to Figures 10-12, the blanking point is the intersection of the extension lines (black dotted lines) of the two lane lines in Figures 10-14. A vanishing point is a point on the horizon at infinity, and all vanishing points make up the horizon. Therefore, in the image, the blanking point can be used as a reference point for space division. In particular, on roads, all lane lines form a set of parallel lines that correspond to the same vanishing point in the image. The position of the vanishing point in the image is related to the focal length of the camera, the pixel and the direction of the parallel lines in the real world. Due to differences in vehicle models, camera installation positions and angles, the vanishing point in the image is not invariant. Fig. 10 and Fig. 11 show schematic diagrams of vanishing points in environment images collected at two different positions during the driving process of the vehicle. Figure 10 and Figure 12 show the schematic diagrams of the blanking points in the environmental images collected by different vehicles (such as cars and SUVs) at two different positions during driving. The regions divided based on the blanking points have certain translation invariance. Therefore, the accuracy of visual feature comparison is increased.
S104、将视觉特征与预设视觉特征进行匹配，以确定待定位车辆所在的位置。S104. Match the visual features with preset visual features to determine the location of the vehicle to be positioned.
其中，预设视觉特征为地图数据中的视觉特征。Wherein, the preset visual feature is a visual feature in the map data.
在通过上述步骤构建好环境图像对应的视觉特征之后，就可以将构建好的视觉特征与预设视觉特征进行匹配，从而根据匹配结果确定待定位车辆所在的位置。After the visual features corresponding to the environment image are constructed through the above steps, the constructed visual features can be matched with the preset visual features, so as to determine the location of the vehicle to be positioned according to the matching result.
示例的，在本发明实施例中，可以预先获取地图数据中关键位置的预设视觉特征，并在分别获取到视觉特征和预设视觉特征之后，就可以将该视觉特征与预设视觉特征进行匹配，并根据匹配结果确定待定位车辆所在的位置。示例的，可以通过点云匹配、特征匹配和姿态优化匹配的方式对视觉特征进行匹配。As an example, in the embodiment of the present invention, the preset visual features of the key positions in the map data can be obtained in advance, and after the visual features and the preset visual features are respectively acquired, the visual features can be compared with the preset visual features. Match, and determine the location of the vehicle to be located according to the matching result. For example, visual features can be matched through point cloud matching, feature matching and pose optimization matching.
本发明实施例提供的车辆位置重定位的方法，通过获取待定位车辆的环境图像，并提取环境图像中的预设特征信息；再根据预设特征信息构建环境图像对应的视觉特征；之后，再将视觉特征与预设视觉特征进行匹配，从而确定待定位车辆所在的位置。由此可见，本发明实施例提供的车辆位置重定位的方法，在确定待定位车辆所在位置时，是根据预先构建环境图像对应的视觉特征，并将该视觉特征与地图数据的预设视觉特征进行匹配，从而确定待定位车辆所在位置，不仅减少了重定位过程中的计算量，而且提高了计算的鲁棒性。The vehicle position relocation method provided by the embodiment of the present invention obtains the environment image of the vehicle to be positioned, and extracts the preset feature information in the environment image; then constructs the corresponding visual features of the environment image according to the preset feature information; after that, Match the visual features with preset visual features to determine the location of the vehicle to be located. It can be seen that, the method for relocating the vehicle position provided by the embodiment of the present invention, when determining the position of the vehicle to be positioned, is based on the visual features corresponding to the pre-built environment image, and combines the visual features with the preset visual features of the map data Matching is performed to determine the location of the vehicle to be located, which not only reduces the amount of calculation in the relocation process, but also improves the robustness of the calculation.
图13为本发明实施例提供的一种车辆重定位的装置130的结构示意图，请参见图13所示，该车辆重定位的装置130可以包括：FIG. 13 is a schematic structural diagram of a vehicle relocation device 130 provided by an embodiment of the present invention. Please refer to FIG. 13. The vehicle relocation device 130 may include:
获取单元1301，用于获取待定位车辆的环境图像。The acquiring unit 1301 is configured to acquire the environment image of the vehicle to be positioned.
提取单元1302，用于提取环境图像中的预设特征信息；预设特征信息包括几何特征信息和/或语义特征信息。The extraction unit 1302 is configured to extract preset feature information in the environment image; the preset feature information includes geometric feature information and/or semantic feature information.
构建单元1303，用于根据预设特征信息构建环境图像对应的视觉特征。A construction unit 1303, configured to construct visual features corresponding to the environment image according to preset feature information.
确定单元1304，用于将视觉特征与预设视觉特征进行匹配，以确定待定位车辆所在的位置；其中，预设视觉特征为地图数据中的视觉特征。The determining unit 1304 is configured to match the visual features with preset visual features to determine the location of the vehicle to be positioned; wherein the preset visual features are visual features in map data.
可选的，构建单元1303，具体用于确定预设特征信息对应的描述子；确定描述子对应的词袋模型中的单词；其中，每一个单词对应一个或多个描述子；并根据与每一个单词匹配的描述子的个数构建环境图像对应的视觉特征。。Optionally, the construction unit 1303 is specifically configured to determine the descriptor corresponding to the preset feature information; determine the words in the bag-of-words model corresponding to the descriptor; wherein, each word corresponds to one or more descriptors; and according to each The number of descriptors matched by a word constructs the corresponding visual features of the environment image. .
可选的，该车辆重定位的装置130还可以包括划分单元1305，请参见图14所示，图14为本发明实施例提供的另一种车辆重定位的装置130的结构示意图。Optionally, the vehicle relocation device 130 may further include a division unit 1305, please refer to FIG. 14, which is a schematic structural diagram of another vehicle relocation device 130 provided by an embodiment of the present invention.
划分单元1305，用于将环境图像划分为多个子区域。A division unit 1305, configured to divide the environment image into multiple sub-regions.
构建单元1303，具体用于确定每一个子区域中预设特征信息对应的特征向量；并将每一个子区域对应的特征向量按照分布位置进行向量组合，构建环境图像对应的视觉特征。The construction unit 1303 is specifically configured to determine the feature vector corresponding to the preset feature information in each sub-region; and combine the feature vectors corresponding to each sub-region according to the distribution position to construct the visual feature corresponding to the environment image.
可选的，确定单元1304，还用于确定环境图像中的消隐点。Optionally, the determining unit 1304 is also configured to determine a vanishing point in the environment image.
划分单元1305，具体用于根据消隐点将环境图像划分为多个子区域。The division unit 1305 is specifically configured to divide the environment image into multiple sub-regions according to the blanking points.
可选的，环境图像包括激光点云数据。Optionally, the environment image includes laser point cloud data.
提取单元1302，具体用于提取环境图像中的特征信息；并根据预设规则在特征信息中选取预设特征信息；其中，预设规则为随机采样规则、法向量分布规则集均匀采样规则中的一种或多种的组合。The extraction unit 1302 is specifically used to extract feature information in the environment image; and select preset feature information from the feature information according to preset rules; wherein, the preset rules are random sampling rules, normal vector distribution rule set uniform sampling rules One or more combinations.
本发明实施例所示的车辆重定位的装置130，可以执行上述任一实施例所示的车辆重定位的方法的技术方案，其实现原理以及有益效果类似，此处不再进行赘述。The vehicle relocation device 130 shown in the embodiment of the present invention can implement the technical solution of the vehicle relocation method shown in any of the above-mentioned embodiments, and its implementation principles and beneficial effects are similar, and will not be repeated here.
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其它实施方案。本发明旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求书指出。Other embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. The present invention is intended to cover any modification, use or adaptation of the present disclosure, and these modifications, uses or adaptations follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not disclosed in the present disclosure . The specification and examples are to be considered exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求书来限制。It should be understood that the present disclosure is not limited to the precise constructions which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810157705.2ACN108416808B (en) | 2018-02-24 | 2018-02-24 | Method and device for vehicle relocation |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810157705.2ACN108416808B (en) | 2018-02-24 | 2018-02-24 | Method and device for vehicle relocation |
| Publication Number | Publication Date |
|---|---|
| CN108416808Atrue CN108416808A (en) | 2018-08-17 |
| CN108416808B CN108416808B (en) | 2022-03-08 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810157705.2AActiveCN108416808B (en) | 2018-02-24 | 2018-02-24 | Method and device for vehicle relocation |
| Country | Link |
|---|---|
| CN (1) | CN108416808B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255817A (en)* | 2018-09-14 | 2019-01-22 | 北京猎户星空科技有限公司 | A kind of the vision method for relocating and device of smart machine |
| CN110147705A (en)* | 2018-08-28 | 2019-08-20 | 北京初速度科技有限公司 | A kind of vehicle positioning method and electronic equipment of view-based access control model perception |
| CN110415297A (en)* | 2019-07-12 | 2019-11-05 | 北京三快在线科技有限公司 | Localization method, device and unmanned equipment |
| CN110568447A (en)* | 2019-07-29 | 2019-12-13 | 广东星舆科技有限公司 | Visual positioning method, device and computer readable medium |
| WO2020043081A1 (en)* | 2018-08-28 | 2020-03-05 | 北京三快在线科技有限公司 | Positioning technique |
| CN110967018A (en)* | 2019-11-25 | 2020-04-07 | 斑马网络技术有限公司 | Parking lot location method, device, electronic device and computer readable medium |
| CN111143489A (en)* | 2018-11-06 | 2020-05-12 | 北京嘀嘀无限科技发展有限公司 | Image-based positioning method and device, computer equipment and readable storage medium |
| WO2020098316A1 (en)* | 2018-11-12 | 2020-05-22 | 南京人工智能高等研究院有限公司 | Visual point cloud-based semantic vector map building method, device, and electronic apparatus |
| CN111322993A (en)* | 2018-12-13 | 2020-06-23 | 杭州海康机器人技术有限公司 | Visual positioning method and device |
| CN111508258A (en)* | 2020-04-17 | 2020-08-07 | 北京三快在线科技有限公司 | Positioning method and device |
| WO2020199565A1 (en)* | 2019-03-29 | 2020-10-08 | 魔门塔(苏州)科技有限公司 | Street lamp pole-based vehicle posture correction method and device |
| CN111860084A (en)* | 2019-04-30 | 2020-10-30 | 千寻位置网络有限公司 | Image feature matching and positioning method and device and positioning system |
| WO2021073403A1 (en)* | 2019-10-16 | 2021-04-22 | Ningbo Geely Automobile Research & Development Co., Ltd. | A vehicle parking finder support system, method and computer program product for determining if a vehicle is at a reference parking location |
| CN114545400A (en)* | 2022-04-27 | 2022-05-27 | 陕西欧卡电子智能科技有限公司 | Global repositioning method of water surface robot based on millimeter wave radar |
| CN116324886A (en)* | 2020-10-19 | 2023-06-23 | 罗伯特·博世有限公司 | Method and device for mapping a use environment for at least one mobile unit and for locating at least one mobile unit in a use environment, and location system for a use environment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6879341B1 (en)* | 1997-07-15 | 2005-04-12 | Silverbrook Research Pty Ltd | Digital camera system containing a VLIW vector processor |
| CN101364347A (en)* | 2008-09-17 | 2009-02-11 | 同济大学 | A video-based detection method for vehicle control delays at intersections |
| CN101862194A (en)* | 2010-06-17 | 2010-10-20 | 天津大学 | Imaginative Action EEG Identity Recognition Method Based on Fusion Feature |
| CN102053249A (en)* | 2009-10-30 | 2011-05-11 | 吴立新 | Underground space high-precision positioning method based on laser scanning and sequence encoded graphics |
| CN102054178A (en)* | 2011-01-20 | 2011-05-11 | 北京联合大学 | Chinese painting image identifying method based on local semantic concept |
| US20120263346A1 (en)* | 2011-04-13 | 2012-10-18 | International Business Machines Corporation | Video-based detection of multiple object types under varying poses |
| CN103473739A (en)* | 2013-08-15 | 2013-12-25 | 华中科技大学 | White blood cell image accurate segmentation method and system based on support vector machine |
| CN103810505A (en)* | 2014-02-19 | 2014-05-21 | 北京大学 | Vehicle identification method and system based on multilayer descriptors |
| CN103971124A (en)* | 2014-05-04 | 2014-08-06 | 杭州电子科技大学 | Multi-class motor imagery brain electrical signal classification method based on phase synchronization |
| CN104217444A (en)* | 2013-06-03 | 2014-12-17 | 支付宝（中国）网络技术有限公司 | Method and apparatus for locating card areas |
| CN104268876A (en)* | 2014-09-26 | 2015-01-07 | 大连理工大学 | Camera calibration method based on partitioning |
| CN105404887A (en)* | 2015-07-05 | 2016-03-16 | 中国计量学院 | White blood count five-classification method based on random forest |
| US20170024412A1 (en)* | 2015-07-17 | 2017-01-26 | Environmental Systems Research Institute (ESRI) | Geo-event processor |
| CN106569244A (en)* | 2016-11-04 | 2017-04-19 | 杭州联络互动信息科技股份有限公司 | Vehicle positioning method based on intelligent equipment and apparatus thereof |
| CN106896353A (en)* | 2017-03-21 | 2017-06-27 | 同济大学 | A kind of unmanned vehicle crossing detection method based on three-dimensional laser radar |
| CN106908775A (en)* | 2017-03-08 | 2017-06-30 | 同济大学 | A kind of unmanned vehicle real-time location method based on laser reflection intensity |
| CN106960179A (en)* | 2017-02-24 | 2017-07-18 | 北京交通大学 | Rail line Environmental security intelligent monitoring method and device |
| CN107451574A (en)* | 2017-08-09 | 2017-12-08 | 安徽大学 | A kind of method for estimating perceived based on class Haar visual signatures |
| CN107533630A (en)* | 2015-01-20 | 2018-01-02 | 索菲斯研究股份有限公司 | For the real time machine vision of remote sense and wagon control and put cloud analysis |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6879341B1 (en)* | 1997-07-15 | 2005-04-12 | Silverbrook Research Pty Ltd | Digital camera system containing a VLIW vector processor |
| CN101364347A (en)* | 2008-09-17 | 2009-02-11 | 同济大学 | A video-based detection method for vehicle control delays at intersections |
| CN102053249A (en)* | 2009-10-30 | 2011-05-11 | 吴立新 | Underground space high-precision positioning method based on laser scanning and sequence encoded graphics |
| CN101862194A (en)* | 2010-06-17 | 2010-10-20 | 天津大学 | Imaginative Action EEG Identity Recognition Method Based on Fusion Feature |
| CN102054178A (en)* | 2011-01-20 | 2011-05-11 | 北京联合大学 | Chinese painting image identifying method based on local semantic concept |
| US20120263346A1 (en)* | 2011-04-13 | 2012-10-18 | International Business Machines Corporation | Video-based detection of multiple object types under varying poses |
| CN104217444A (en)* | 2013-06-03 | 2014-12-17 | 支付宝（中国）网络技术有限公司 | Method and apparatus for locating card areas |
| CN103473739A (en)* | 2013-08-15 | 2013-12-25 | 华中科技大学 | White blood cell image accurate segmentation method and system based on support vector machine |
| CN103810505A (en)* | 2014-02-19 | 2014-05-21 | 北京大学 | Vehicle identification method and system based on multilayer descriptors |
| CN103971124A (en)* | 2014-05-04 | 2014-08-06 | 杭州电子科技大学 | Multi-class motor imagery brain electrical signal classification method based on phase synchronization |
| CN104268876A (en)* | 2014-09-26 | 2015-01-07 | 大连理工大学 | Camera calibration method based on partitioning |
| CN107533630A (en)* | 2015-01-20 | 2018-01-02 | 索菲斯研究股份有限公司 | For the real time machine vision of remote sense and wagon control and put cloud analysis |
| CN105404887A (en)* | 2015-07-05 | 2016-03-16 | 中国计量学院 | White blood count five-classification method based on random forest |
| US20170024412A1 (en)* | 2015-07-17 | 2017-01-26 | Environmental Systems Research Institute (ESRI) | Geo-event processor |
| CN106569244A (en)* | 2016-11-04 | 2017-04-19 | 杭州联络互动信息科技股份有限公司 | Vehicle positioning method based on intelligent equipment and apparatus thereof |
| CN106960179A (en)* | 2017-02-24 | 2017-07-18 | 北京交通大学 | Rail line Environmental security intelligent monitoring method and device |
| CN106908775A (en)* | 2017-03-08 | 2017-06-30 | 同济大学 | A kind of unmanned vehicle real-time location method based on laser reflection intensity |
| CN106896353A (en)* | 2017-03-21 | 2017-06-27 | 同济大学 | A kind of unmanned vehicle crossing detection method based on three-dimensional laser radar |
| CN107451574A (en)* | 2017-08-09 | 2017-12-08 | 安徽大学 | A kind of method for estimating perceived based on class Haar visual signatures |
| Title |
|---|
| M. RIDHWAN TAMJIS等: ""Automatic visual identification of correct matches in unmanned aerial vehicle images for visual-based attitude estimation"", 《 2015 IEEE INTERNATIONAL CONFERENCE ON EVOLVING AND ADAPTIVE INTELLIGENT SYSTEMS (EAIS)》* |
| WEI LIU等: ""A sequential mobile vehicle location method with visual features"", 《 2009 IEEE INTELLIGENT VEHICLES SYMPOSIUM》* |
| 李辉: ""基于多视觉词汇索引的车辆图像检索"", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147705A (en)* | 2018-08-28 | 2019-08-20 | 北京初速度科技有限公司 | A kind of vehicle positioning method and electronic equipment of view-based access control model perception |
| WO2020043081A1 (en)* | 2018-08-28 | 2020-03-05 | 北京三快在线科技有限公司 | Positioning technique |
| CN110147705B (en)* | 2018-08-28 | 2021-05-04 | 北京初速度科技有限公司 | Vehicle positioning method based on visual perception and electronic equipment |
| CN109255817A (en)* | 2018-09-14 | 2019-01-22 | 北京猎户星空科技有限公司 | A kind of the vision method for relocating and device of smart machine |
| CN111143489B (en)* | 2018-11-06 | 2024-01-09 | 北京嘀嘀无限科技发展有限公司 | Image-based positioning method and device, computer equipment and readable storage medium |
| CN111143489A (en)* | 2018-11-06 | 2020-05-12 | 北京嘀嘀无限科技发展有限公司 | Image-based positioning method and device, computer equipment and readable storage medium |
| WO2020098316A1 (en)* | 2018-11-12 | 2020-05-22 | 南京人工智能高等研究院有限公司 | Visual point cloud-based semantic vector map building method, device, and electronic apparatus |
| CN111322993B (en)* | 2018-12-13 | 2022-03-04 | 杭州海康机器人技术有限公司 | Visual positioning method and device |
| CN111322993A (en)* | 2018-12-13 | 2020-06-23 | 杭州海康机器人技术有限公司 | Visual positioning method and device |
| WO2020199565A1 (en)* | 2019-03-29 | 2020-10-08 | 魔门塔(苏州)科技有限公司 | Street lamp pole-based vehicle posture correction method and device |
| CN111860084A (en)* | 2019-04-30 | 2020-10-30 | 千寻位置网络有限公司 | Image feature matching and positioning method and device and positioning system |
| CN111860084B (en)* | 2019-04-30 | 2024-04-16 | 千寻位置网络有限公司 | Image feature matching and positioning method and device and positioning system |
| CN110415297B (en)* | 2019-07-12 | 2021-11-05 | 北京三快在线科技有限公司 | Positioning method and device and unmanned equipment |
| CN110415297A (en)* | 2019-07-12 | 2019-11-05 | 北京三快在线科技有限公司 | Localization method, device and unmanned equipment |
| CN110568447A (en)* | 2019-07-29 | 2019-12-13 | 广东星舆科技有限公司 | Visual positioning method, device and computer readable medium |
| WO2021073403A1 (en)* | 2019-10-16 | 2021-04-22 | Ningbo Geely Automobile Research & Development Co., Ltd. | A vehicle parking finder support system, method and computer program product for determining if a vehicle is at a reference parking location |
| US12211290B2 (en) | 2019-10-16 | 2025-01-28 | Ningbo Geely Automobile Research &Dev. Co., Ltd. | Vehicle parking finder support system, method and computer program product for determining if a vehicle is at a reference parking location |
| CN110967018A (en)* | 2019-11-25 | 2020-04-07 | 斑马网络技术有限公司 | Parking lot location method, device, electronic device and computer readable medium |
| CN110967018B (en)* | 2019-11-25 | 2024-04-12 | 斑马网络技术有限公司 | Parking lot positioning method, device, electronic device and computer readable medium |
| CN111508258A (en)* | 2020-04-17 | 2020-08-07 | 北京三快在线科技有限公司 | Positioning method and device |
| CN116324886A (en)* | 2020-10-19 | 2023-06-23 | 罗伯特·博世有限公司 | Method and device for mapping a use environment for at least one mobile unit and for locating at least one mobile unit in a use environment, and location system for a use environment |
| CN114545400A (en)* | 2022-04-27 | 2022-05-27 | 陕西欧卡电子智能科技有限公司 | Global repositioning method of water surface robot based on millimeter wave radar |
| Publication number | Publication date |
|---|---|
| CN108416808B (en) | 2022-03-08 |
| Publication | Publication Date | Title |
|---|---|---|
| CN108416808A (en) | Method and device for vehicle relocation | |
| US11094112B2 (en) | Intelligent capturing of a dynamic physical environment | |
| EP3660737B1 (en) | Method, apparatus, and system for providing image labeling for cross view alignment | |
| CN113034566B (en) | High-precision map construction method and device, electronic equipment and storage medium | |
| KR102815456B1 (en) | Learning data generation method for image processing, image processing method, and apparatus thereof | |
| US10331957B2 (en) | Method, apparatus, and system for vanishing point/horizon estimation using lane models | |
| EP3644013B1 (en) | Method, apparatus, and system for location correction based on feature point correspondence | |
| CN105512646B (en) | A kind of data processing method, device and terminal | |
| KR102218881B1 (en) | Method and system for determining position of vehicle | |
| EP3671623B1 (en) | Method, apparatus, and computer program product for generating an overhead view of an environment from a perspective image | |
| EP4202833A1 (en) | Method, apparatus, and system for pole extraction from a single image | |
| JP2020201649A (en) | Map generation device, map generation method and computer program for map generation | |
| US11024054B2 (en) | Method, apparatus, and system for estimating the quality of camera pose data using ground control points of known quality | |
| WO2020043081A1 (en) | Positioning technique | |
| US11055862B2 (en) | Method, apparatus, and system for generating feature correspondence between image views | |
| US10152635B2 (en) | Unsupervised online learning of overhanging structure detector for map generation | |
| US10515293B2 (en) | Method, apparatus, and system for providing skip areas for machine learning | |
| US10949707B2 (en) | Method, apparatus, and system for generating feature correspondence from camera geometry | |
| WO2020156923A2 (en) | Map and method for creating a map | |
| Yang et al. | Road intersection identification from crowdsourced big trace data using Mask‐RCNN | |
| CN116124173A (en) | Method and apparatus for navigating two or more users to meeting locations | |
| EP4202835A1 (en) | Method, apparatus, and system for pole extraction from optical imagery | |
| CN110827340B (en) | Map updating method, device and storage medium | |
| JP5435294B2 (en) | Image processing apparatus and image processing program | |
| US20240013554A1 (en) | Method, apparatus, and system for providing machine learning-based registration of imagery with different perspectives |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address | Address after:200000 Shanghai City Xuhui District Longyao Road No. 18 10th Floor 1001 Room Patentee after:Zebra Network Technology Co.,Ltd. Country or region after:China Address before:Building D1, 2nd Floor, No. 55 Huaihai West Road, Xuhui District, Shanghai Patentee before:ZEBRED NETWORK TECHNOLOGY Co.,Ltd. Country or region before:China |