CN112124303A - Parking space fusion method and system - Google Patents
Parking space fusion method and system Download PDFInfo
- Publication number
- CN112124303A CN112124303A CN202011029534.9A CN202011029534A CN112124303A CN 112124303 A CN112124303 A CN 112124303A CN 202011029534 A CN202011029534 A CN 202011029534A CN 112124303 A CN112124303 A CN 112124303A
- Authority
- CN
- China
- Prior art keywords
- space
- parking
- parking space
- line
- spaces
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
本发明公开了一种车位融合方法及系统，方法包括：获取车位种类、车位类型和所获取车位的位置信息，其中，车位种类包括空间车位或线车位，车位类型包括平行车位或垂直车位；判断车位内是否存在障碍物，若车位内不存在障碍物，并且当车位种类包括空间车位和线车位两种时，根据车位类型，以及空间车位与线车位的相对位置，确定输出车位的种类及其位置信息。本发明在识别车位时，进行了车位与障碍物融合、车位与车位融合，得到最终车位。通过本方案的实施，可提高车位识别准确率。同时本方案对SOC处理器要求不高，算法相对较简单，是基于低成本硬件平台上开发的，有益于平台量产推广。
The invention discloses a parking space fusion method and system. The method includes: acquiring the type of parking space, the type of parking space and the position information of the acquired parking space, wherein the type of parking space includes space parking space or line parking space, and the type of parking space includes parallel parking space or vertical parking space; Whether there are obstacles in the parking space, if there are no obstacles in the parking space, and when the types of parking spaces include space parking spaces and line parking spaces, determine the type of output parking space and its relative position according to the type of parking space and the relative position of the space parking space and the line parking space. location information. When recognizing the parking space, the present invention performs the fusion of parking space and obstacle, and the fusion of parking space and parking space to obtain the final parking space. Through the implementation of this scheme, the accuracy of parking space identification can be improved. At the same time, this solution does not have high requirements on SOC processors, and the algorithm is relatively simple. It is developed on a low-cost hardware platform, which is beneficial to the mass production and promotion of the platform.
Description
技术领域technical field
本发明属于智能汽车技术领域，具体涉及一种车位融合方法及系统。The invention belongs to the technical field of intelligent vehicles, and in particular relates to a parking space fusion method and system.
背景技术Background technique
车位融合是智能泊车的关键技术，直接影响泊车路径规划、泊车入位的成功率及泊车的安全性。Parking fusion is the key technology of intelligent parking, which directly affects the planning of parking paths, the success rate of parking and the safety of parking.
目前主要是通过超声波传感器与摄像头进行综合检测并重构输出，该方案虽然能够实现正常的车位融合，但是由于车位识别存在一定的误差，导致融合出来的车位会与实际车位存在偏差。比如地面上线车位为规整的矩形或平行四边形，但是实际采集数据经处理重构后输出的车位可能会为梯形，如图1的垂直线车位所示。再比如作为空间车位参考的参考车辆摆放也不一定整齐，如停放后车身与标准车位边沿有偏角，从而导致最终的空间车位也存在一定偏差。At present, ultrasonic sensors and cameras are mainly used for comprehensive detection and reconstructed output. Although this solution can achieve normal parking space fusion, due to certain errors in parking space recognition, the fused parking space will deviate from the actual parking space. For example, the parking spaces on the ground are regular rectangles or parallelograms, but the outputted parking spaces after processing and reconstructing the actual collected data may be trapezoids, as shown in the vertical line parking spaces in Figure 1. For another example, the reference vehicle used as a reference for the space parking space is not necessarily neatly placed. For example, after parking, the body and the edge of the standard parking space have an off-angle, which leads to a certain deviation in the final space parking space.
现有的另一种车位融合方法是分别以线车位和空间车位及车位内障碍物位置所处相对位置，并且结合泊车过程的泊车规划方案进行车位融合。虽然该方案对被控车辆最后泊入车位姿态准确性有一定的提升，但是并未考虑到车位类型多样性以及车位内障碍物本身位置检测误差性，导致车位误识别等，最终需要通过性能更加强大的SOC处理器加上更加复杂的算法去实现准确泊车，这必然会导致硬件成本大幅增加。Another existing parking space fusion method is to use the relative positions of the line parking spaces, the space parking spaces and the positions of the obstacles in the parking spaces respectively, and combine the parking planning scheme of the parking process to perform the parking space fusion. Although this scheme improves the accuracy of the final parking space of the controlled vehicle, it does not take into account the diversity of parking space types and the error of the position detection of the obstacles in the parking space, resulting in misrecognition of the parking space, etc. Powerful SOC processors and more complex algorithms to achieve accurate parking will inevitably lead to a substantial increase in hardware costs.
发明内容SUMMARY OF THE INVENTION
本发明实施例所要解决的技术问题在于，现有的车位融合未考虑到车位类型多样性以及车位内障碍物本身位置检测误差性，导致车位漏报或误报的问题。为解决上述技术问题，本发明提供了一种车位融合方法，包括：The technical problem to be solved by the embodiments of the present invention is that the existing parking space fusion does not take into account the diversity of parking space types and the detection error of the position of the obstacle itself in the parking space, resulting in the problem of missing or false alarming of the parking space. In order to solve the above-mentioned technical problems, the present invention provides a parking space fusion method, comprising:
步骤S1，获取车位种类、车位类型和所获取车位的位置信息，其中，所述车位种类包括空间车位和线车位中的至少一种，所述车位类型为平行车位或垂直车位；Step S1, acquiring the type of parking space, the type of parking space and the position information of the acquired parking space, wherein the type of parking space includes at least one of a space parking space and a linear parking space, and the type of parking space is a parallel parking space or a vertical parking space;
步骤S2，判断所述车位内是否存在障碍物，若所述车位内不存在障碍物，并且当所述车位种类同时包括空间车位和线车位时，根据所述空间车位的位置信息与所述线车位的位置信息，确定所述空间车位与所述线车位的相对位置；根据所述车位类型，以及所述相对位置，确定输出车位的种类及其位置信息。Step S2, judging whether there is an obstacle in the parking space, if there is no obstacle in the parking space, and when the type of the parking space includes both a space parking space and a line parking space, according to the position information of the space parking space and the line parking space. The position information of the parking space is used to determine the relative position of the space parking space and the line parking space; according to the type of the parking space and the relative position, the type of the output parking space and its position information are determined.
进一步地，所述步骤S2具体包括：Further, the step S2 specifically includes:
当所述空间车位和所述线车位均为平行车位时，比较所述空间车位和所述线车位在车头和车尾处的第一边界的相对位置关系；When both the space parking space and the line parking space are parallel parking spaces, comparing the relative positional relationship between the space parking space and the first boundary of the line parking space at the front and rear of the vehicle;
当所述线车位的两条第一边界均位于所述空间车位的第一边界以内时，则确定输出所述线车位及其位置信息；When the two first boundaries of the line parking space are both located within the first boundary of the space parking space, determine to output the line parking space and its position information;
当所述线车位的至少一条第一边界位于所述空间车位相对应的第一边界以外时，则确定输出所述空间车位及其位置信息。When at least one first boundary of the line parking space is located outside the corresponding first boundary of the space parking space, it is determined to output the space parking space and its position information.
进一步地，所述步骤S2具体包括：Further, the step S2 specifically includes:
当所述空间车位和所述线车位均为垂直车位时，判断所述空间车位和所述线车位的垂直车位类型是否相同；所述垂直车位类型包括：垂直矩形线车位、正向平行斜列车位、反向平行斜列车位、正向锯齿斜列车位和反向锯齿斜列车位；When both the space parking space and the line parking space are vertical parking spaces, it is determined whether the vertical parking space types of the space parking space and the line parking space are the same; the vertical parking space types include: vertical rectangular line parking spaces, forward parallel inclined trains position, anti-parallel ramp, forward sawtooth ramp and reverse sawtooth ramp;
当所述空间车位和所述线车位的垂直车位类型相同时，比较所述空间车位和所述线车位在车辆两侧处的第二边界的相对位置关系；When the vertical parking space types of the space parking space and the line parking space are the same, comparing the relative positional relationship between the space parking space and the second boundary of the line parking space on both sides of the vehicle;
当所述线车位的两条第二边界均位于所述空间车位的第二边界以内时，则确定输出所述线车位及其位置信息；When the two second boundaries of the line parking space are both located within the second boundary of the space parking space, determine to output the line parking space and its position information;
当所述线车位的至少一条第二边界位于所述空间车位相对应的第二边界以外时，则确定输出所述空间车位及其位置信息。When at least one second boundary of the line parking space is located outside the corresponding second boundary of the space parking space, it is determined to output the space parking space and its position information.
进一步地，所述步骤S2具体包括：Further, the step S2 specifically includes:
当所述空间车位和所述线车位的垂直车位类型不相同，且所述线车位为正向平行斜列车位、反向平行斜列车位、正向锯齿斜列车位和反向锯齿斜列车位中的任一种时，则确定输出所述线车位及其位置信息。When the vertical parking space types of the space parking space and the line parking space are different, and the line parking space is a forward parallel oblique parking space, an anti-parallel oblique parking space, a forward sawtooth oblique parking space, and a reverse sawtooth oblique parking space When any one of them is selected, the line parking space and its position information are determined to be output.
进一步地，所述步骤S2还包括：Further, the step S2 also includes:
当车辆开始泊入所述线车位时，更新所述空间车位的位置信息；When the vehicle starts to park in the line parking space, update the position information of the space parking space;
根据所述线车位和更新后的所述空间车位的相对位置，输出更新后的空间车位的位置信息或所述线车位的位置信息。According to the relative position of the line parking space and the updated space parking space, the updated position information of the space parking space or the position information of the line parking space is output.
进一步地，所述根据所述线车位和更新后的所述空间车位的相对位置，输出更新后的空间车位的位置信息或所述线车位的位置信息，具体包括：Further, according to the relative position of the line parking space and the updated space parking space, outputting the updated position information of the space parking space or the position information of the line parking space specifically includes:
比较所述更新后的空间车位和所述线车位在车辆两侧处的第二边界的相对位置关系；comparing the relative positional relationship between the updated space parking space and the second boundary of the line parking space on both sides of the vehicle;
当所述线车位的两条第二边界均位于所述更新后的空间车位的第二边界以内时，则确定输出所述线车位及其位置信息；When the two second boundaries of the line parking spaces are both located within the second boundary of the updated space parking space, determining to output the line parking spaces and their location information;
当所述线车位的至少一条第二边界位于所述更新后的空间车位相对应的第二边界以外时，则确定输出所述更新后的空间车位及其位置信息。When at least one second boundary of the line parking space is outside the second boundary corresponding to the updated space parking space, it is determined to output the updated space parking space and its position information.
进一步地，所述的车位融合方法，还包括：Further, the described parking space fusion method also includes:
步骤S3，当所述车位种类只包括空间车位和线车位中的一种时，确定输出当前获取的空间车位及其位置信息，或确定输出当前获取的线车位及其位置信息。Step S3, when the parking space type includes only one of the space parking space and the line parking space, determine to output the currently obtained space parking space and its position information, or determine to output the currently obtained line parking space and its position information.
进一步地，所述的车位融合方法，还包括：Further, the described parking space fusion method also includes:
步骤S4，当所述车位种类只包括空间车位和线车位中的一种，并且所述车位的面积同时符合平行车位的面积要求和垂直车位的面积要求时，输出所述平行车位的位置信息或所述垂直车位的位置信息。Step S4, when the type of the parking space only includes one of the space parking space and the line parking space, and the area of the parking space meets the area requirements of the parallel parking space and the area requirement of the vertical parking space at the same time, output the position information of the parallel parking space or The location information of the vertical parking space.
一种车位融合系统，包括：A parking space fusion system, comprising:
超声波传感器，用于获取空间车位的车位类型和位置信息；Ultrasonic sensor, used to obtain the parking space type and location information of the space parking space;
摄像头传感器，用于获取线车位的车位类型和位置信息；The camera sensor is used to obtain the parking space type and location information of the line parking space;
其中，所述车位类型为平行车位或垂直车位；Wherein, the parking space type is a parallel parking space or a vertical parking space;
所述超声波传感器和所述摄像头传感器，还用于获取所述车位内的障碍物信息；The ultrasonic sensor and the camera sensor are also used to obtain obstacle information in the parking space;
车位融合处理单元，用于判断所述车位内是否存在障碍物，若所述车位内不存在障碍物，并且当所述车位种类同时包括空间车位和线车位时，根据所述空间车位的位置信息与所述线车位的位置信息，确定所述空间车位与所述线车位的相对位置；根据所述车位类型，以及所述相对位置，确定输出车位的种类及其位置信息。The parking space fusion processing unit is used to judge whether there is an obstacle in the parking space, if there is no obstacle in the parking space, and when the parking space type includes both space parking spaces and line parking spaces, according to the position information of the space parking space Determine the relative position of the space parking space and the line parking space with the position information of the line parking space; determine the type of the output parking space and its position information according to the parking space type and the relative position.
进一步地，所述车位融合处理单元，还用于：Further, the parking space fusion processing unit is also used for:
当所述空间车位和所述线车位均为平行车位时，比较所述空间车位和所述线车位在车头和车尾处的第一边界的相对位置关系；When both the space parking space and the line parking space are parallel parking spaces, comparing the relative positional relationship between the space parking space and the first boundary of the line parking space at the front and rear of the vehicle;
当所述线车位的两条第一边界均位于所述空间车位的第一边界以内时，则确定输出所述线车位及其位置信息；When the two first boundaries of the line parking space are both located within the first boundary of the space parking space, determine to output the line parking space and its position information;
当所述线车位的至少一条第一边界位于所述空间车位相对应的第一边界以外时，则确定输出所述空间车位及其位置信息。When at least one first boundary of the line parking space is located outside the corresponding first boundary of the space parking space, it is determined to output the space parking space and its position information.
进一步地，所述车位融合处理单元，还用于：Further, the parking space fusion processing unit is also used for:
当所述空间车位和所述线车位均为垂直车位时，判断所述空间车位和所述线车位的垂直车位类型是否相同,所述垂直车位类型包括：垂直矩形线车位、正向平行斜列车位、反向平行斜列车位、正向锯齿斜列车位和反向锯齿斜列车位；When both the space parking space and the line parking space are vertical parking spaces, determine whether the vertical parking space types of the space parking space and the line parking space are the same, and the vertical parking space types include: vertical rectangular line parking spaces, forward parallel inclined trains position, anti-parallel ramp, forward sawtooth ramp and reverse sawtooth ramp;
当所述空间车位和所述线车位的垂直车位类型相同时，比较所述空间车位和所述线车位在车辆两侧处的第二边界的相对位置关系；When the vertical parking space types of the space parking space and the line parking space are the same, comparing the relative positional relationship between the space parking space and the second boundary of the line parking space on both sides of the vehicle;
当所述线车位的两条第二边界均位于所述空间车位的第二边界以内时，则确定输出所述线车位及其位置信息；When the two second boundaries of the line parking space are both located within the second boundary of the space parking space, determine to output the line parking space and its position information;
当所述线车位的至少一条第二边界位于所述空间车位相对应的第二边界以外时，则确定输出所述空间车位及其位置信息。When at least one second boundary of the line parking space is located outside the corresponding second boundary of the space parking space, it is determined to output the space parking space and its position information.
进一步地，所述车位融合处理单元，还用于：Further, the parking space fusion processing unit is also used for:
当所述空间车位和所述线车位的垂直车位类型不相同，且所述线车位为正向平行斜列车位、反向平行斜列车位、正向锯齿斜列车位和反向锯齿斜列车位中的任一种时，则确定输出所述线车位及其位置信息。When the vertical parking space types of the space parking space and the line parking space are different, and the line parking space is a forward parallel oblique parking space, an anti-parallel oblique parking space, a forward sawtooth oblique parking space, and a reverse sawtooth oblique parking space When any one of them is selected, the line parking space and its position information are determined to be output.
进一步地，所述车位融合处理单元，还用于：Further, the parking space fusion processing unit is also used for:
当车辆开始泊入所述线车位时，更新所述空间车位的位置信息；When the vehicle starts to park in the line parking space, update the position information of the space parking space;
根据所述线车位和更新后的所述空间车位的相对位置，输出更新后的空间车位的位置信息或所述线车位的位置信息。According to the relative position of the line parking space and the updated space parking space, the updated position information of the space parking space or the position information of the line parking space is output.
进一步地，所述车位融合处理单元还用于，当所述车位种类只包括空间车位和线车位中的一种时，确定输出当前获取的空间车位及其位置信息或确定输出当前获取的线车位及其位置信息。Further, the parking space fusion processing unit is further configured to, when the type of parking space includes only one of the space parking space and the line parking space, determine to output the currently obtained space parking space and its position information or determine to output the currently obtained line parking space. and its location information.
进一步地，所述车位融合处理单元，还用于：Further, the parking space fusion processing unit is also used for:
当所述车位种类只包括空间车位和线车位中的一种，并且所述车位的面积同时符合平行车位的面积要求和垂直车位的面积要求时，输出所述平行车位的位置信息或所述垂直车位的位置信息。When the type of parking space includes only one of the space parking space and the line parking space, and the area of the parking space meets the area requirements of the parallel parking space and the area requirement of the vertical parking space at the same time, output the position information of the parallel parking space or the vertical parking space. The location information of the parking space.
实施本发明实施例，具有如下有益效果：本发明在识别车位时，综合考虑障碍物情况，并结合车位种类和车位类型，进行了车位与障碍物融合、车位与车位融合，得到最终车位。由于车位检测的误差及以及车位类型多样性，若在车位融合过程中考虑不全，会导致最终融合中出的可泊车位被漏报或误报等情况，需要复杂的处理泊车规划流程去实现。因而，通过本方案的实施，可提高车位识别准确率。同时本方案对SOC处理器要求不高，算法相对较简单，是基于低成本硬件平台上开发的，因而有益于平台量产化。The implementation of the embodiment of the present invention has the following beneficial effects: the present invention comprehensively considers the obstacle situation when identifying the parking space, and combines the parking space type and the parking space type to carry out the fusion of the parking space and the obstacle, and the fusion of the parking space and the parking space to obtain the final parking space. Due to the error of parking space detection and the diversity of parking space types, if the parking space fusion process is not fully considered, it will cause the parking spaces in the final fusion to be missed or falsely reported, etc., which requires complex processing of the parking planning process to achieve . Therefore, through the implementation of this solution, the accuracy of parking space identification can be improved. At the same time, this solution does not have high requirements on the SOC processor, and the algorithm is relatively simple. It is developed based on a low-cost hardware platform, so it is beneficial to the mass production of the platform.
附图说明Description of drawings
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简单地介绍，显而易见地，下面描述中的附图仅仅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。In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.
图1为SOC采集的线车位与实际线车位的差异示意图。Figure 1 is a schematic diagram of the difference between the line parking spaces collected by the SOC and the actual line parking spaces.
图2为本发明实施例提供的车位融合方法流程示意图。FIG. 2 is a schematic flowchart of a parking space fusion method provided by an embodiment of the present invention.
图3为本发明定义的车位类型的示意图。FIG. 3 is a schematic diagram of a parking space type defined in the present invention.
图4为本发明定义的车位形状的示意图。FIG. 4 is a schematic diagram of the shape of a parking space defined by the present invention.
图5为本发明实施例中空间车位搜索及与障碍物的融合流程的示意图。FIG. 5 is a schematic diagram of a process of searching for a space parking space and integrating with obstacles in an embodiment of the present invention.
图6为本发明实施例中线车位搜索及与障碍物的融合流程的示意图。FIG. 6 is a schematic diagram of a process of searching for a centerline parking space and integrating with an obstacle according to an embodiment of the present invention.
图7为本发明实施例中车位形状为平行车位的空间车位和线车位的融合示意图。FIG. 7 is a schematic diagram of the fusion of a space parking space and a line parking space in which the parking space shape is a parallel parking space according to an embodiment of the present invention.
图8为本发明实施例中车位形状为平行车位时车位的融合处理逻辑图。8 is a logic diagram of fusion processing of parking spaces when the shape of the parking spaces is a parallel parking space according to an embodiment of the present invention.
图9为本发明实施例中车位形状为垂直车位的空间车位和线车位的融合示意图。FIG. 9 is a schematic diagram of the fusion of a space parking space and a linear parking space in which the shape of the parking space is a vertical parking space according to an embodiment of the present invention.
图10为本发明实施例中车位形状为垂直车位时车位的融合处理逻辑图。FIG. 10 is a logic diagram of fusion processing of parking spaces when the shape of the parking spaces is a vertical parking space according to an embodiment of the present invention.
具体实施方式Detailed ways
以下各实施例的说明是参考附图，用以示例本发明可以用以实施的特定实施例。The following descriptions of the various embodiments refer to the accompanying drawings to illustrate specific embodiments in which the invention may be practiced.
请参照图2所示，本发明实施例提供了一种车位融合方法，包括步骤S101-步骤S102：Referring to FIG. 2, an embodiment of the present invention provides a parking space fusion method, including steps S101-S102:
步骤S101，获取车位种类、车位类型和所获取车位的位置信息，其中，所述车位种类包括空间车位和线车位中的至少一种，所述车位类型为平行车位或垂直车位。Step S101: Acquire the type of parking space, the type of parking space, and the location information of the acquired parking space, wherein the type of parking space includes at least one of a space parking space and a linear parking space, and the parking space type is a parallel parking space or a vertical parking space.
具体地，参考图3和图4，车位种类包括空间车位和线车位，是针对同一停车位参考不同的参考对象而定义的，线车位是参考地面的车位线，空间车位是系统根据车位周围的参照物生成的，例如图3中的空间车位的参照物是车位两侧的车辆，通常只要两侧的车辆停放规范(没有超出线车位范围)，空间车位的面积大于线车位的面积。车位类型包括平行车位和垂直车位，平行车位是指车头到车尾的方向与墙(参照物)大致平行，垂直车位是指车头到车尾的方向与墙大致垂直，其中垂直车位的形状根据实际情况，可以进一步分为垂直矩形线车位、正向平行斜列车位、反向平行斜列车位、正向锯齿斜列车位和反向锯齿斜列车位，如图4所示。由于车位检测的误差以及车位类型多样性，若在车位融合过程中考虑不全，会导致最终融合中出的可泊车位被漏报或误报等情况。本方案综合考虑了车位类型多样性，可以基于低成本硬件平台进行车位融合。Specifically, referring to FIGS. 3 and 4 , the types of parking spaces include space parking spaces and line parking spaces, which are defined with reference to different reference objects for the same parking space. The reference object generated, for example, the reference object of the space parking space in Figure 3 is the vehicles on both sides of the parking space. Usually, as long as the vehicles on both sides are parked according to the specification (not beyond the line parking space range), the area of the space parking space is larger than the area of the line parking space. The types of parking spaces include parallel parking spaces and vertical parking spaces. A parallel parking space means that the direction from the front to the rear of the vehicle is roughly parallel to the wall (reference object), and the vertical parking space means that the direction from the front to the rear of the vehicle is roughly perpendicular to the wall. The shape of the vertical parking space depends on the actual situation. The situation can be further divided into vertical rectangular line parking spaces, forward parallel oblique parking spaces, anti-parallel oblique parking spaces, forward sawtooth oblique parking spaces and reverse sawtooth oblique parking spaces, as shown in Figure 4. Due to the error of parking space detection and the diversity of parking space types, if the parking space fusion process is not fully considered, the parking spaces in the final fusion will be missed or falsely reported. This scheme comprehensively considers the diversity of parking space types, and can integrate parking spaces based on a low-cost hardware platform.
具体来说，车位种类及车位类型的识别，可通过在车辆上设置超声波传感器和摄像头传感器进行检测。通过超声波传感器可以进行空间车位搜索，空间车位搜索需要参考旁边的参照物，参照物可以是单侧参照物或双侧参照物，参照物可以是旁边的车辆、墙壁等易被超声波探测到的物体。在只存在单侧参照物时，可以通过软件算法，得到空间车位。通过摄像头传感器可以检测到各种形状的线车位，即使车位线不够清晰，但只要与被控车辆行驶方向接近的车位顶点被扫描到，就可以通过软件算法实现线车位探测，同时摄像头传感器还能通过一定的算法，实现地锁、雪糕筒、行人等障碍物的探测。在获取到车位种类及车位类型后，将车位的位置信息进行记录，例如获取车位的四个顶点坐标。Specifically, the identification of the type of parking space and the type of parking space can be detected by arranging ultrasonic sensors and camera sensors on the vehicle. The space parking space search can be performed through the ultrasonic sensor. The space parking space search needs to refer to the reference object next to it. The reference object can be a single-sided reference object or a double-sided reference object. The reference object can be a nearby vehicle, wall and other objects that are easily detected by ultrasonic waves. . When there is only one-sided reference object, the space parking space can be obtained through software algorithm. The camera sensor can detect line parking spaces of various shapes. Even if the parking space line is not clear enough, as long as the vertices of the parking space close to the driving direction of the controlled vehicle are scanned, the line parking space detection can be realized through software algorithms. At the same time, the camera sensor can also Through a certain algorithm, the detection of obstacles such as ground locks, ice cream cones, and pedestrians is realized. After obtaining the type of parking space and the type of parking space, the location information of the parking space is recorded, for example, the coordinates of the four vertices of the parking space are obtained.
步骤S102，判断所述车位内是否存在障碍物，若所述车位内不存在障碍物，并且当所述车位种类同时包括空间车位和线车位时，根据所述空间车位的位置信息与所述线车位的位置信息，确定所述空间车位与所述线车位的相对位置；根据所述车位类型，以及所述相对位置，确定输出车位的种类及其位置信息。Step S102, judging whether there is an obstacle in the parking space, if there is no obstacle in the parking space, and when the type of parking space includes both a space parking space and a line parking space, according to the position information of the space parking space and the line parking space. The position information of the parking space is used to determine the relative position of the space parking space and the line parking space; according to the type of the parking space and the relative position, the type of the output parking space and its position information are determined.
具体地，在获取了车位种类、车位类型和车位的位置信息后，可以通过超声波传感器和摄像头传感器进一步判断车位内部是否存在障碍物，可以通过软件算法的配合，实现对地锁、雪糕筒、行人等障碍物是否在当前空间车位内或者线车位内进行判断。若障碍物在空间车位，或者线车位为内，例如车位内存在地锁、雪糕筒等，则取消相应线车位或者空间车位，即无车位信息输出。若车位内不存在障碍物时，进一步根据当前的车位种类只包括空间车位、只包括线车位，以及同时包括空间车位和线车位三种情况进行处理，三种情况分别为：(1)检测的当前车位只有线车位，表示该线车位旁边未停放车辆；(2)检测的当前车位只有空间车位，表示该车位旁边有停放车辆，地面无车位线，可归属于临时停放车位；(3)检测的当前车位包括两种车位，意味着当前线车位至少一个相邻车位停有车辆，传感器据此参照物在线车位的基础上同时生成了空间车位，此时需要对检测到的线车位和空间车位做进一步处理。Specifically, after obtaining the type of parking space, the type of parking space and the location information of the parking space, ultrasonic sensors and camera sensors can be used to further determine whether there are obstacles inside the parking space. It is judged whether the obstacle is in the current space parking space or in the line parking space. If the obstacle is in the space parking space, or the line parking space is inside, for example, there are ground locks, ice cream cones, etc. in the parking space, the corresponding line parking space or space parking space will be cancelled, that is, no parking space information will be output. If there is no obstacle in the parking space, it is further processed according to the current type of parking space including only space parking spaces, only including line parking spaces, and including both space parking spaces and line parking spaces. The three cases are: (1) The detected The current parking space has only a line parking space, which means that no vehicle is parked next to the line parking space; (2) the current parking space detected is only a space parking space, which means that there are parked vehicles next to the parking space, and there is no parking space line on the ground, which can be classified as a temporary parking space; (3) Detection The current parking space includes two types of parking spaces, which means that there is a vehicle parked in at least one adjacent parking space in the current line parking space. The sensor generates a space parking space based on the online parking space based on this reference. At this time, it is necessary to detect the line parking space and the space parking space do further processing.
具体地，当车位只包括空间车位和线车位中的一种时，即传感器只识别到空间车位，或者只识别到线车位，则直接输出当前获取的空间车位的位置信息或线车位的位置信息，比如输出车位图形的四个顶点坐标。本实施例中，只识别到空间车位时，空间车位搜索及与障碍物的融合流程如图5所示。只识别到线车位时，线车位搜索及与障碍物的融合流程如图6所示。Specifically, when the parking space includes only one of the space parking space and the line parking space, that is, the sensor only recognizes the space parking space, or only recognizes the line parking space, the currently obtained position information of the space parking space or the position information of the line parking space is directly output. , such as outputting the coordinates of the four vertices of the parking space graph. In this embodiment, when only the space parking space is identified, the process of searching for the space parking space and the fusion with the obstacle is shown in FIG. 5 . When only the line parking spaces are identified, the process of line parking space search and fusion with obstacles is shown in Figure 6.
当检测的当前车位包括空间车位和线车位两种时，需根据车位的类型分情况对两种车位进行融合处理。首先定义方向：以与车头朝向一致的运动方向为纵向，且远离车头的方向定义为前方。反之，以与车头朝向相反，且远离车头方向定义为后方。When the detected current parking spaces include space parking spaces and line parking spaces, it is necessary to perform fusion processing on the two parking spaces according to the types of parking spaces. First define the direction: the direction of movement consistent with the front of the car is the longitudinal direction, and the direction away from the front of the car is defined as the front. Conversely, the direction opposite to the front of the vehicle and away from the front of the vehicle is defined as the rear.
(1)当空间车位和线车位为平行车位时，如图7所示，比较空间车位(MNQP)和线车位(M'N'Q'P')在车头和车尾处的边界(第一边界)的相对位置关系，即MN、M'N'的相对位置关系，以及PQ和P'Q'的相对位置关系。若MN在M'N'前方且PQ在P'Q'后方，此时判断线车位有效，以线车位的车位坐标作为当前平行车位融合输出。若否，即MN在M'N'后方或PQ在P'Q'前方，为了安全要求，则此时线车位无效，以空间车位的车位坐标作为当前平行车位融合输出，处理逻辑图如图8所示。(1) When the space parking space and the line parking space are parallel parking spaces, as shown in Figure 7, compare the boundaries of the space parking space (MNQP) and the line parking space (M'N'Q'P') at the front and rear of the vehicle (the first boundary), that is, the relative positional relationship between MN and M'N', and the relative positional relationship between PQ and P'Q'. If MN is in front of M'N' and PQ is behind P'Q', then it is judged that the line parking space is valid, and the parking space coordinates of the line parking space are used as the current parallel parking space fusion output. If not, that is, MN is behind M'N' or PQ is in front of P'Q'. For safety requirements, the line parking space is invalid at this time, and the parking space coordinates of the space parking space are used as the current parallel parking space fusion output. The processing logic diagram is shown in Figure 8 shown.
(2)当空间车位和线车位为垂直车位，需要判断垂直车位类型是否一致，当垂直车位的形状一致时，比较空间车位(MNQP)和线车位(M'N'Q'P')在车辆(泊入车位后的状态)两侧处的边界(第二边界)，即图9中MN、M'N'的相对位置关系，以及PQ和P'Q'的相对位置关系，若MN在M'N'前方且PQ在P'Q'后方，此时判断线车位有效，以线车位的车位坐标作为当前平行车位融合输出。若否，即MN在M'N'后方或PQ在P'Q'前方，为了安全要求，则此时线车位无效，以空间车位的车位坐标作为当前平行车位融合输出。(2) When the space parking space and the line parking space are vertical parking spaces, it is necessary to judge whether the vertical parking space types are consistent. When the shapes of the vertical parking spaces are the same, compare the space parking space (MNQP) and the line parking space (M'N'Q'P') in the vehicle (The state after parking in the parking space) The boundary (second boundary) on both sides, that is, the relative positional relationship between MN and M'N' in Figure 9, and the relative positional relationship between PQ and P'Q', if MN is in M In front of 'N' and PQ is behind P'Q', the line parking space is judged to be valid at this time, and the parking space coordinates of the line parking space are used as the current parallel parking space fusion output. If no, that is, MN is behind M'N' or PQ is in front of P'Q', for safety requirements, the line parking space is invalid at this time, and the parking space coordinates of the space parking space are used as the current parallel parking space fusion output.
(3)当空间车位和线车位为垂直车位、垂直车位类型不一致，且线车位为正向平行斜列车位、反向平行斜列车位、正向锯齿斜列车位和反向锯齿斜列车位中的任一种，即线车位不是垂直矩形车位时，由于汽车沿着纵向运动方向，超声波传感器只能检测到垂直方向矩形空间车位，且此矩形车位可能为满足车位要求，也可能不满足被取消掉了，因而，此时以线车位为准，输出线车位的位置信息。第(2)、(3)种情形的处理逻辑图如图10所示。(3) When the space parking space and the line parking space are vertical parking spaces, the types of vertical parking spaces are inconsistent, and the line parking spaces are forward parallel inclined train spaces, anti-parallel inclined train spaces, forward sawtooth inclined train spaces, and reverse sawtooth inclined train spaces. When the line parking space is not a vertical rectangular parking space, the ultrasonic sensor can only detect a rectangular space parking space in the vertical direction because the car moves along the longitudinal direction, and this rectangular parking space may meet the parking space requirements, or may not meet the requirements and be cancelled. Therefore, at this time, the line parking space shall prevail, and the position information of the line parking space is output. The processing logic diagram of the cases (2) and (3) is shown in Figure 10.
进一步地，针对第(3)种情形，判断以线车位为准后，当车辆开始泊入线车位时，重新获取空间车位的位置信息，此时能够获取到与线车位的垂直车位类型一致的空间车位，此时重复第(2)种情形的执行步骤即可得到最终的车位种类，并输出相应的车位位置。Further, for the (3) kind of situation, after judging that the line parking space is the criterion, when the vehicle starts to park in the line parking space, the position information of the space parking space is re-acquired, and the vertical parking space type consistent with the line parking space can be obtained at this time. Space parking spaces, at this time, repeat the execution steps of the (2) case to obtain the final parking space type, and output the corresponding parking space position.
针对一些特殊情况，检测到的车位只包括空间车位和线车位中的一种，并且该车位的面积足够大，以至于同时符合平行车位的面积要求和垂直车位的面积要求时，此时输出平行车位的位置信息或垂直车位的位置信息，车辆可以按照平行车位或垂直车位进行泊车。For some special cases, the detected parking space only includes one of the space parking space and the line parking space, and the area of the parking space is large enough to meet the area requirements of the parallel parking space and the vertical parking space at the same time. The position information of the parking space or the position information of the vertical parking space, the vehicle can be parked according to the parallel parking space or the vertical parking space.
通过上述说明可知，与现有技术相比，本发明的有益效果在于：本发明在识别车位时，综合考虑障碍物情况，并结合车位种类和车位类型，进行了车位与障碍物融合、车位与车位融合，得到最终车位。由于车位检测的误差及以及车位类型多样性，若在车位融合过程中考虑不全，会导致最终融合中出的可泊车位被漏报或误报等情况，需要复杂的处理泊车规划流程去实现。因而，通过本方案的实施，可提高车位识别准确率。同时本方案对SOC处理器要求不高，算法相对较简单，是基于低成本硬件平台上开发的，因而有益于平台量产化。It can be seen from the above description that, compared with the prior art, the beneficial effect of the present invention is that: the present invention comprehensively considers the obstacle situation when recognizing the parking space, and combines the type of parking space and the parking space type to perform the fusion of parking space and obstacle, and the integration of parking space and obstacle. The parking spaces are merged to get the final parking space. Due to the error of parking space detection and the diversity of parking space types, if the parking space fusion process is not fully considered, it will cause the parking spaces in the final fusion to be missed or falsely reported, etc., which requires complex processing of the parking planning process to achieve . Therefore, through the implementation of this solution, the accuracy of parking space identification can be improved. At the same time, this solution does not have high requirements on the SOC processor, and the algorithm is relatively simple. It is developed based on a low-cost hardware platform, so it is beneficial to the mass production of the platform.
基于上述实施例，本发明提供了一种车位融合系统实施例，包括：Based on the above embodiments, the present invention provides an embodiment of a parking space fusion system, including:
超声波传感器，用于获取空间车位的车位类型和位置信息；Ultrasonic sensor, used to obtain the parking space type and location information of the space parking space;
摄像头传感器，用于获取线车位的车位类型和位置信息；The camera sensor is used to obtain the parking space type and location information of the line parking space;
其中，所述车位类型为平行车位或垂直车位；Wherein, the parking space type is a parallel parking space or a vertical parking space;
所述超声波传感器和所述摄像头传感器，还用于获取所述车位内的障碍物信息；The ultrasonic sensor and the camera sensor are also used to obtain obstacle information in the parking space;
车位融合处理单元，用于判断所述车位内是否存在障碍物，若所述车位内不存在障碍物，并且当所述车位种类同时包括空间车位和线车位时，根据所述空间车位的位置信息与所述线车位的位置信息，确定所述空间车位与所述线车位的相对位置；根据所述车位类型，以及所述相对位置，确定输出车位的种类及其位置信息。The parking space fusion processing unit is used to judge whether there is an obstacle in the parking space, if there is no obstacle in the parking space, and when the parking space type includes both space parking spaces and line parking spaces, according to the position information of the space parking space Determine the relative position of the space parking space and the line parking space with the position information of the line parking space; determine the type of the output parking space and its position information according to the parking space type and the relative position.
进一步地，所述车位融合处理单元还可以用于，所述车位融合处理单元，还用于：当所述空间车位和所述线车位均为平行车位时，比较所述空间车位和所述线车位在车头和车尾处的第一边界的相对位置关系；Further, the parking space fusion processing unit may also be used for: when the space parking space and the line parking space are both parallel parking spaces, compare the space parking space and the line parking space The relative positional relationship of the first boundary of the parking space at the front and rear of the vehicle;
当所述线车位的两条第一边界均位于所述空间车位的第一边界以内时，则确定输出所述线车位及其位置信息；When the two first boundaries of the line parking space are both located within the first boundary of the space parking space, determine to output the line parking space and its position information;
当所述线车位的至少一条第一边界位于所述空间车位相对应的第一边界以外时，则确定输出所述空间车位及其位置信息。When at least one first boundary of the line parking space is located outside the corresponding first boundary of the space parking space, it is determined to output the space parking space and its position information.
进一步地，所述车位融合处理单元，还用于：当所述空间车位和所述线车位均为垂直车位时，判断所述空间车位和所述线车位的垂直车位类型是否相同,所述垂直车位类型包括：垂直矩形线车位、正向平行斜列车位、反向平行斜列车位、正向锯齿斜列车位和反向锯齿斜列车位；Further, the parking space fusion processing unit is further configured to: when both the space parking space and the line parking space are vertical parking spaces, determine whether the vertical parking space types of the space parking space and the line parking space are the same, and the vertical parking space of the space parking space and the line parking space are the same. The types of parking spaces include: vertical rectangular line parking spaces, forward parallel oblique train spaces, anti-parallel inclined train spaces, forward sawtooth inclined train spaces and reverse sawtooth inclined train spaces;
当所述空间车位和所述线车位的垂直车位类型相同时，比较所述空间车位和所述线车位在车辆两侧处的第二边界的相对位置关系；When the vertical parking space types of the space parking space and the line parking space are the same, comparing the relative positional relationship between the space parking space and the second boundary of the line parking space on both sides of the vehicle;
当所述线车位的两条第二边界均位于所述空间车位的第二边界以内时，则确定输出所述线车位及其位置信息；When the two second boundaries of the line parking space are both located within the second boundary of the space parking space, determine to output the line parking space and its position information;
当所述线车位的至少一条第二边界位于所述空间车位相对应的第二边界以外时，则确定输出所述空间车位及其位置信息。When at least one second boundary of the line parking space is located outside the corresponding second boundary of the space parking space, it is determined to output the space parking space and its position information.
进一步地，所述车位融合处理单元，还用于：Further, the parking space fusion processing unit is also used for:
当所述空间车位和所述线车位的垂直车位类型不相同，且所述线车位为正向平行斜列车位、反向平行斜列车位、正向锯齿斜列车位和反向锯齿斜列车位中的任一种时，则确定输出所述线车位及其位置信息。When the vertical parking space types of the space parking space and the line parking space are different, and the line parking space is a forward parallel inclined train space, an antiparallel inclined train space, a forward sawtooth inclined train space, and a reverse sawtooth inclined train space When any one of them is selected, the line parking space and its position information are determined to be output.
进一步地，所述车位融合处理单元还用于，当所述车位种类只包括空间车位和线车位中的一种时，确定输出当前获取的空间车位及其位置信息或确定输出当前获取的线车位及其位置信息。Further, the parking space fusion processing unit is further configured to, when the type of parking space includes only one of the space parking space and the line parking space, determine to output the currently obtained space parking space and its position information or determine to output the currently obtained line parking space. and its location information.
进一步地，所述车位融合处理单元，还用于：当所述车位种类只包括空间车位和线车位中的一种，并且所述车位的面积同时符合平行车位的面积要求和垂直车位的面积要求时，输出所述平行车位的位置信息或所述垂直车位的位置信息。Further, the parking space fusion processing unit is also used for: when the type of the parking space only includes one of the space parking space and the line parking space, and the area of the parking space meets the area requirements of the parallel parking spaces and the area requirements of the vertical parking spaces at the same time. When , the position information of the parallel parking space or the position information of the vertical parking space is output.
有关本实施例车位融合系统的工作原理和过程，参见前述本发明实施例一的说明，此处不再赘述。For the working principle and process of the parking space fusion system in this embodiment, reference may be made to the foregoing description of Embodiment 1 of the present invention, which will not be repeated here.
通过上述说明可知，与现有技术相比，本发明的有益效果在于：本发明在识别车位时，综合考虑障碍物情况，并结合车位种类和车位类型，进行了车位与障碍物融合、车位与车位融合，得到最终车位。通过本方案的实施，可提高车位识别准确率。同时本方案对SOC处理器要求不高，算法相对较简单，是基于低成本硬件平台上开发的，因而有益于平台量产化。It can be seen from the above description that, compared with the prior art, the beneficial effect of the present invention is that: the present invention comprehensively considers the obstacle situation when recognizing the parking space, and combines the type of parking space and the parking space type to perform the fusion of parking space and obstacle, and the fusion of parking space and obstacle. The parking spaces are merged to get the final parking space. Through the implementation of this scheme, the accuracy of parking space identification can be improved. At the same time, this solution does not have high requirements on the SOC processor, and the algorithm is relatively simple. It is developed on a low-cost hardware platform, so it is beneficial to the mass production of the platform.
以上所揭露的仅为本发明较佳实施例而已，当然不能以此来限定本发明之权利范围，因此依本发明权利要求所作的等同变化，仍属本发明所涵盖的范围。The above disclosures are only preferred embodiments of the present invention, and of course, the scope of the rights of the present invention cannot be limited by this. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.
Claims (15)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011029534.9A CN112124303A (en) | 2020-09-27 | 2020-09-27 | Parking space fusion method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011029534.9A CN112124303A (en) | 2020-09-27 | 2020-09-27 | Parking space fusion method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112124303A true CN112124303A (en) | 2020-12-25 |
Family
ID=73840384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011029534.9A Pending CN112124303A (en) | 2020-09-27 | 2020-09-27 | Parking space fusion method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112124303A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112846A (en) * | 2021-05-20 | 2021-07-13 | 中国第一汽车股份有限公司 | Parking navigation method, device, equipment and storage medium |
| CN114111815A (en) * | 2021-11-01 | 2022-03-01 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120130449A (en) * | 2011-05-23 | 2012-12-03 | 아진산업(주) | Method for providing of vehicle parking assistant image and system for providing thereof |
| CN106494395A (en) * | 2016-09-30 | 2017-03-15 | 惠州华阳通用电子有限公司 | A kind of automatic parking control method and device based on data fusion |
| CN108806308A (en) * | 2018-04-29 | 2018-11-13 | 惠州市德赛西威汽车电子股份有限公司 | A kind of parking stall recognition methods and method of parking |
| CN110293964A (en) * | 2019-06-25 | 2019-10-01 | 重庆长安汽车股份有限公司 | Automatic parking merges parking stall judgment method, system, computer readable storage medium and vehicle |
| CN110889974A (en) * | 2018-09-11 | 2020-03-17 | 广州汽车集团股份有限公司 | Intelligent parking space identification method and device and automobile |
| CN111191485A (en) * | 2018-11-14 | 2020-05-22 | 广州汽车集团股份有限公司 | A parking space detection method and system thereof, and a vehicle |
| CN111624610A (en) * | 2020-04-29 | 2020-09-04 | 东风汽车集团有限公司 | Parking space angle-based self-adaptive parking ultrasonic radar adjusting method |
-
2020
- 2020-09-27 CN CN202011029534.9A patent/CN112124303A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120130449A (en) * | 2011-05-23 | 2012-12-03 | 아진산업(주) | Method for providing of vehicle parking assistant image and system for providing thereof |
| CN106494395A (en) * | 2016-09-30 | 2017-03-15 | 惠州华阳通用电子有限公司 | A kind of automatic parking control method and device based on data fusion |
| CN108806308A (en) * | 2018-04-29 | 2018-11-13 | 惠州市德赛西威汽车电子股份有限公司 | A kind of parking stall recognition methods and method of parking |
| CN110889974A (en) * | 2018-09-11 | 2020-03-17 | 广州汽车集团股份有限公司 | Intelligent parking space identification method and device and automobile |
| CN111191485A (en) * | 2018-11-14 | 2020-05-22 | 广州汽车集团股份有限公司 | A parking space detection method and system thereof, and a vehicle |
| CN110293964A (en) * | 2019-06-25 | 2019-10-01 | 重庆长安汽车股份有限公司 | Automatic parking merges parking stall judgment method, system, computer readable storage medium and vehicle |
| CN111624610A (en) * | 2020-04-29 | 2020-09-04 | 东风汽车集团有限公司 | Parking space angle-based self-adaptive parking ultrasonic radar adjusting method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112846A (en) * | 2021-05-20 | 2021-07-13 | 中国第一汽车股份有限公司 | Parking navigation method, device, equipment and storage medium |
| CN114111815A (en) * | 2021-11-01 | 2022-03-01 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and device |
| CN114111815B (en) * | 2021-11-01 | 2023-02-03 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109649384B (en) | Parking assisting method | |
| CN105467394B (en) | Parking space exploration device and its heuristic approach | |
| CN104354656B (en) | The detection of obstacles of Intelligent parking system and warehouse compartment method of discrimination and realize system | |
| Jung et al. | Scanning laser radar-based target position designation for parking aid system | |
| CN109031323B (en) | Parking space detection method based on ultrasonic ranging radar | |
| CN112455430B (en) | Method for detecting inclined parking places without parking place lines, parking method and parking system | |
| CN108491782B (en) | Vehicle identification method based on driving image acquisition | |
| US20030210807A1 (en) | Monitoring device, monitoring method and program for monitoring | |
| TWI656518B (en) | Marked parking space identification system and method thereof | |
| WO2019210599A1 (en) | Parking space identification method and parking method | |
| CN105946853A (en) | Long-distance automatic parking system and method based on multi-sensor fusion | |
| JP2007030700A (en) | Parking assistance device | |
| CN103481820B (en) | A kind of auxiliary parking system with safety monitoring and method thereof | |
| CN114056324A (en) | Parking space identification method and system based on data fusion | |
| CN113313935B (en) | Image processing apparatus and image processing method | |
| JPH08329393A (en) | Preceding vehicle detector | |
| CN114132305A (en) | Method and system for planning vertical and inclined parking paths, storage medium and vehicle | |
| CN112124303A (en) | Parking space fusion method and system | |
| JP2009245042A (en) | Traffic flow measurement device and program | |
| CN114655193B (en) | Method, device, equipment and readable storage medium for searching effective parking spaces | |
| CN114495066B (en) | Method for assisting reversing | |
| CN112002125A (en) | Vertical parking space fusion identification method and system | |
| CN117734702A (en) | Parking space searching method, module and vehicle based on side ultrasonic radar | |
| JP6579144B2 (en) | Obstacle detection device | |
| Zhao et al. | Omni-directional detection and tracking of on-road vehicles using multiple horizontal laser scanners |
Legal Events
| 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201225 |
|
| RJ01 | Rejection of invention patent application after publication |