WO2023045798A1 - 一种过道区域识别方法及装置 - Google Patents

一种过道区域识别方法及装置 Download PDF

Info

Publication number
WO2023045798A1
WO2023045798A1 PCT/CN2022/118384 CN2022118384W WO2023045798A1 WO 2023045798 A1 WO2023045798 A1 WO 2023045798A1 CN 2022118384 W CN2022118384 W CN 2022118384W WO 2023045798 A1 WO2023045798 A1 WO 2023045798A1
Authority
WO
WIPO (PCT)
Prior art keywords
aisle
area
areas
target
candidate
Prior art date
Application number
PCT/CN2022/118384
Other languages
English (en)
French (fr)
Inventor
王朕
郁顺昌
Original Assignee
追觅创新科技(苏州)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 追觅创新科技(苏州)有限公司 filed Critical 追觅创新科技(苏州)有限公司
Publication of WO2023045798A1 publication Critical patent/WO2023045798A1/zh

Links

Images

Definitions

  • the present disclosure relates to the field of artificial intelligence, in particular, to a method and device for identifying an aisle area.
  • the surveying and mapping with area division function is mentioned in the related technology, and the mobile cleaning device completes the surveying and mapping of the total space area by measuring the surrounding distance during driving. Then the door handle is detected by the traditional visual method to obtain the door information, and the area threshold is assisted to divide the total area of the space into sub-areas. With the traditional image processing method, the sub-area can only be divided by the door, but there is no effective processing method for the division of the aisle. Secondly, the above-mentioned documents can only divide sub-areas, and do not identify the room types of the sub-areas, and cannot realize intelligent cleaning services based on different room types.
  • Aisle is a transitional area connecting different rooms
  • aisle corridor
  • Aisle (or corridor) recognition is a key point for cleaning robot area recognition.
  • the aisle is usually the last cleaning after all areas are cleaned, so the identification of the aisle is especially important for intelligent cleaning.
  • the aisle cannot be effectively identified, and thus the cleaning route cannot be planned based on the aisle, resulting in reduced cleaning efficiency and effect, and reduced user experience.
  • the purpose of the present disclosure is to provide a method and device for identifying an aisle area, so as to at least solve the problem in the related art that the aisle cannot be effectively identified, and thus cleaning routes cannot be planned based on the aisle.
  • a method for identifying an aisle area including:
  • the aisle area is identified from the plurality of target areas according to the adjacent relationship of each target area.
  • determining the aisle candidate area according to the adjacent relationship includes:
  • acquiring the adjacency relationship among the regions in the plurality of regions on the initial partition map includes:
  • the aisle candidate areas are segmented according to preset rules to obtain multiple target areas including:
  • the detection point information is item information collected by the cleaning robot
  • the aisle candidate area is segmented according to the detection point information to obtain multiple target areas.
  • obtaining the detection point information of the aisle candidate area includes:
  • the item information is determined as the detection point information.
  • identifying the aisle area from the plurality of target areas according to the adjacent relationship of each target area includes:
  • the aisle area is determined according to the target dividing line.
  • setting initial segmentation lines for the aisle candidate area along the horizontal direction and the vertical direction respectively includes:
  • the initial dividing line with a preset length is set in the initial partition map at the positions where the number of area pixels in the horizontal direction and the vertical direction changes abruptly.
  • an aisle area identification device including:
  • An acquisition module configured to acquire the adjacency relationship between each area in multiple areas on the initial partition map
  • a determination module configured to determine aisle candidate areas according to the adjacent relationship
  • a segmentation module configured to segment the aisle candidate area according to preset rules to obtain multiple target areas
  • An identification module configured to identify the aisle area from the plurality of target areas according to the adjacent relationship of each target area.
  • the determination module includes:
  • a selection submodule configured to select a predetermined number of areas with the largest number of adjacent relationships from the plurality of areas
  • a first determining submodule configured to determine the predetermined number of areas as the passageway candidate areas.
  • the acquisition module includes:
  • the traversal submodule is used to traverse the initial partition map with a preset step size by using a sliding window of a preset size
  • the reading submodule is used to read the pixel value of the pixel in the sliding window during the traversal process
  • the second determining submodule is used to determine that a new adjacent relationship appears if there are different pixel values in the sliding window, and save the new adjacent relationship;
  • a generation submodule is used to complete the traversal and generate the adjacency relationship of the various regions.
  • the segmentation module includes:
  • the obtaining sub-module is used to obtain the detection point information of the aisle candidate area, wherein the detection point information is the item information collected by the cleaning robot;
  • the segmentation sub-module is configured to segment the aisle candidate area according to the detection point information to obtain multiple target areas.
  • the acquisition submodule is also used for the acquisition submodule.
  • the item information is determined as the detection point information.
  • the identification module includes:
  • An update submodule configured to generate a plurality of new target areas based on the initial dividing line, and update the adjacency relationship of the plurality of target areas;
  • the third determination sub-module is configured to determine the target dividing line according to the adjacent relationship between the detection point information and the plurality of target areas; and determine the aisle area according to the target dividing line.
  • the setting submodule is also used for
  • the initial dividing line with a preset length is set in the initial partition map at the positions where the number of area pixels in the horizontal direction and the vertical direction changes abruptly.
  • a computer-readable storage medium is provided, and a computer program is stored in the storage medium, wherein the computer program is configured to execute the above method when running.
  • an electronic device including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to perform the above method.
  • the purpose of the present disclosure is achieved through the following technical solutions: obtain the adjacency relationship between various areas in multiple areas on the initial partition map; determine the aisle candidate area according to the adjacency relationship; Segmentation to obtain multiple target areas; aisle areas are identified from the multiple target areas according to the adjacent relationship of each target area, which solves the problem in the related art that the aisle cannot be effectively identified, and thus cleaning routes cannot be planned based on the aisle.
  • the present disclosure has the following beneficial effects: the aisle area can be effectively identified, which is beneficial to the later personalized cleaning mode and cleaning order, and makes the cleaning robot more intelligent.
  • FIG. 1 is a block diagram of the hardware structure of a cleaning robot of an aisle area identification method according to an embodiment of the present disclosure
  • FIG. 2 is a flowchart of a method for identifying an aisle area according to an embodiment of the present disclosure
  • FIG. 3 is a flowchart of aisle division and identification according to an embodiment of the present disclosure
  • Fig. 4 is a schematic diagram of acquiring neighbor relations according to an embodiment of the present disclosure.
  • Fig. 5 is a schematic diagram of identification of aisle partitions according to an embodiment of the present disclosure.
  • FIG. 6 is a block diagram of an aisle area identification device according to an embodiment of the present disclosure.
  • FIG. 1 is a block diagram of a hardware structure of a cleaning robot according to an aisle area identification method according to an embodiment of the present disclosure.
  • the cleaning robot can include one or more (only one is shown in Figure 1) processor 102 (processor 102 can include but not limited to microprocessor (Microprocessor Unit, MPU for short) or programmable logic device (Programmable logic device, PLD for short) and other processing devices and a memory 104 for storing data, optionally, the above-mentioned cleaning robot can also include a transmission device 106 and an input and output device 108 for communication functions.
  • MPU Microprocessor Unit
  • PLD programmable logic device
  • the structure shown in Figure 1 is only illustrative, and it does not limit the structure of the above-mentioned cleaning robot.
  • the cleaning robot can also include more or less components than shown in Figure 1, or have the same Functionally equivalent to that shown in Figure 1 or a different configuration with more functionality than shown in Figure 1.
  • the memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the aisle area identification method in the embodiment of the present disclosure, and the processor 102 executes the computer program stored in the memory 104 by running the computer program.
  • the memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.
  • memory 104 may further include memory located remotely from processor 102 , and these remote memories may be connected to cleaning robot 10 via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the transmission device 106 is used to receive or transmit data via the network.
  • the specific example of the network mentioned above may include a wireless network provided by the communication provider of the robot 10 .
  • the transmission device 106 includes a network interface controller (NIC for short), which can be connected to other network devices through a base station so as to communicate with the Internet.
  • the transmission device 106 may be a radio frequency (Radio Frequency, RF for short) module, which is used to communicate with the Internet in a wireless manner.
  • RF Radio Frequency
  • FIG. 2 is a flowchart of an aisle area identification method according to an embodiment of the present disclosure. As shown in FIG. 2 , the process includes the following steps:
  • Step S202 obtaining the adjacency relationship of each area in the multiple areas on the initial partition map
  • the initial partition map is collected by the cleaning robot during the pre-execution of the sweeping task, and the adjacent relationship includes: the name or logo of the adjacent area, the number of adjacent areas, and the like.
  • Step S204 determining aisle candidate areas according to the adjacent relationship
  • a part is determined from multiple areas as aisle candidate areas.
  • Step S206 segment the aisle candidate area according to preset rules to obtain multiple target areas
  • Step S208 identifying the aisle area from the plurality of target areas according to the adjacent relationship of each target area.
  • the adjacency relationship of each area in the multiple areas is obtained on the initial partition map; the aisle candidate area is determined according to the adjacency relationship; the aisle candidate area is segmented according to preset rules to obtain multiple targets area; according to the adjacent relationship of each target area in the multiple target areas, the aisle area is identified from the multiple target areas, which solves the problem that the aisle cannot be effectively identified in the related technology, and then the cleaning route cannot be planned based on the aisle. Effective identification of the aisle area is conducive to the later personalized cleaning mode and cleaning sequence, making the cleaning robot more intelligent.
  • step S204 may specifically include:
  • the predetermined number can be set according to the actual situation, for example, it can be set to 2; optionally, it can first
  • the plurality of regions are sorted according to the number of adjacent relations of the plurality of regions, for example, a total of 5 regions are included: region 1, region 2, region 3, region 4, region 5, wherein the relative The number of neighbors is 2, the number of neighbors in region 2 is 1, the number of neighbors in region 3 is 3, the number of neighbors in region 4 is 3, and the number of neighbors in region 5 is 2 , the sorting results obtained are area 3, area 4, area 1, area 5, and area 2; from the areas of the predetermined number of areas after sorting, if the sorting is from large to small, then directly select the predetermined number of areas area.
  • the aforementioned region selection based on the number of adjacent relationships makes it more likely that the selected region is an aisle, thereby making the formed aisle candidate region more accurate.
  • the above step S202 may specifically include: using a sliding window of a preset size to traverse the initial partition map with a preset step size, wherein the preset size and the preset step size can be set according to the actual situation, for example, the The preset size is set to 2 ⁇ 2, and the preset step size is set to 1, that is, the initial partition map is traversed with a step size of 1 through a 2 ⁇ 2 sliding window; during the traversal process, all pixels in the sliding window are read The pixel value of the point; if the pixel points in the sliding window have different pixel values, it is determined that a new adjacency relationship occurs, and the new adjacency relationship is saved.
  • the adjacent relationship of each area can be generated.
  • the adjacent relationship in this embodiment can also be called the neighborhood relationship.
  • the adjacent relationship determined by the above method is more accurate, and it is done to improve the accuracy of the aisle candidate area. ready.
  • the above step S206 may specifically include: obtaining the detection point information of the aisle candidate area, wherein the detection point information is the item information collected by the sweeping robot cleaning robot, and further, obtaining the sweeping robot in the aisle candidate area The item information collected by the cleaning robot, wherein the item information includes the item label, the size of the box where the item is located, and the distance between the item and the cleaning robot of the sweeping robot.
  • the item includes a sofa, coffee table, dining table, bed, stool, etc.
  • the item tag can be is the name of the item
  • the size of the box where the item is located is the size of the area where the item is collected by the cleaning robot of the sweeping robot through the camera, and the distance between the item and the cleaning robot of the sweeping robot can be collected by a sensor
  • the information of the item is determined as the Monitoring point information Detection point information.
  • the aisle candidate area is segmented according to the detection point information of the monitoring point information to obtain multiple target areas. Based on the detection point information, the accuracy of the target area can be improved.
  • step S208 may specifically include:
  • S2081 respectively setting initial dividing lines along the horizontal direction and vertical direction for the aisle candidate area, and further, respectively setting the mutation positions of the number of area pixels in the horizontal direction and the vertical direction in the initial partition map
  • the initial dividing line of preset length for example, the number of pixels at the horizontal position Yi of the aisle candidate area 1 is 70, and the number of pixels at the next position Yi+1 is 20, and the horizontal position Yi can be determined as the abrupt position.
  • Draw a dividing line segment at the horizontal position Yi the actual length of the dividing line segment can be set according to the width range of the actual aisle;
  • S2083. Determine the target dividing line according to the adjacent relationship between the detection point information and the plurality of target areas. Specifically, determine whether there is an item in each target area according to the detection point information, and determine the target dividing line according to the judgment result. If there is no item in a certain area or the number of items is much less than other areas, then determine the best segmentation line as the target segmentation line;
  • S2084. Determine the aisle area according to the target dividing line. Specifically, after obtaining the target dividing line, divide the aisle candidate area into at least two areas through the target dividing line, and the area where the width is the width of the target dividing line is the aisle area .
  • the final aisle is extracted, and the aisle area is accurately extracted with high precision and no false detection.
  • Fig. 3 is a flow chart of aisle division and identification according to an embodiment of the present disclosure, as shown in Fig. 3 , specifically including:
  • Acquire detection point information of the candidate area that is, use the visual detection model to detect the item information in the current screen of the cleaning robot in real time.
  • the item information includes the item label, frame size and the position of the item from the cleaning robot, wherein the item distance can be obtained through the laser point cloud data.
  • FIG. 4 is a schematic diagram of obtaining adjacent relations according to an embodiment of the present disclosure. As shown in FIG. 4, a new area is generated based on the extracted segmentation line, and the adjacent relation is updated.
  • Fig. 5 is a schematic diagram of aisle partition recognition according to an embodiment of the present disclosure. As shown in Fig. 5, the detection point information in the cleaning of the auxiliary cleaning robot, for example, there is almost no item information in this area, and the best segmented line segment is obtained, that is, the aisle is obtained area.
  • the aisle is finally divided and recognized, with high accuracy and no false detection.
  • the technical solution of the present disclosure can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as a read-only memory (Read-Only Memory) Memory, abbreviated as ROM), random access memory (Random Access Memory, abbreviated as RAM), magnetic disk, optical disk), including several instructions to make a terminal device (which can be a mobile phone, computer, server, or network device) etc.) to perform the methods described in various embodiments of the present disclosure.
  • a storage medium such as a read-only memory (Read-Only Memory) Memory, abbreviated as ROM), random access memory (Random Access Memory, abbreviated as RAM), magnetic disk, optical disk
  • a terminal device which can be a mobile phone, computer, server, or network device
  • This embodiment also provides an aisle area identification device, which can be applied to an intelligent cleaning robot or robot, and the intelligent cleaning robot or robot is used to implement the above embodiments and preferred implementation modes, and those that have already been described will not be repeated.
  • the term "module” may be a combination of software and/or hardware that realizes a predetermined function.
  • the devices described in the following embodiments are preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
  • Fig. 6 is a block diagram of an aisle area identification device according to an embodiment of the present disclosure, as shown in Fig. 6 , including:
  • An acquisition module 62 configured to acquire the adjacency relationship between each area in the multiple areas on the initial partition map
  • a determining module 64 configured to determine aisle candidate areas according to the adjacent relationship
  • a segmentation module 66 configured to segment the aisle candidate areas according to preset rules to obtain multiple target areas
  • An identification module 68 configured to identify the aisle area from the plurality of target areas according to the adjacent relationship of each target area.
  • the determining module 64 includes:
  • a selection submodule configured to select a predetermined number of areas with the largest number of adjacent relationships from the plurality of areas
  • a first determining submodule configured to determine the predetermined number of areas as the passageway candidate areas.
  • the acquisition module 62 includes:
  • the traversal submodule is used to traverse the initial partition map with a preset step size by using a sliding window of a preset size
  • the reading submodule is used to read the pixel value of the pixel in the sliding window during the traversal process
  • the second determination submodule is used to determine that a new adjacent relationship occurs if there are different pixel values in the sliding window, and save the new adjacent relationship;
  • a generation submodule is used to complete the traversal and generate the adjacency relationship of the various regions.
  • the segmentation module 66 includes:
  • the obtaining sub-module is used to obtain the detection point information of the aisle candidate area, wherein the detection point information is the item information collected by the cleaning robot;
  • the segmentation sub-module is configured to segment the aisle candidate area according to the detection point information to obtain multiple target areas.
  • the acquisition submodule is also used for the acquisition submodule.
  • the item information is determined as the detection point information.
  • the identification module 68 includes:
  • An update submodule configured to generate a plurality of new target areas based on the initial dividing line, and update the adjacency relationship of the plurality of target areas;
  • the third determination sub-module is configured to determine the target dividing line according to the adjacent relationship between the detection point information and the plurality of target areas; and determine the aisle area according to the target dividing line.
  • the setting submodule is also used for
  • the initial dividing line with a preset length is set in the initial partition map at the positions where the number of area pixels in the horizontal direction and the vertical direction changes abruptly.
  • the above-mentioned modules can be realized by software or hardware. For the latter, it can be realized by the following methods, but not limited to this: the above-mentioned modules are all located in the same processor; or, the above-mentioned modules can be combined in any combination The forms of are located in different processors.
  • Embodiments of the present disclosure also provide a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps in any one of the above method embodiments when running.
  • the above-mentioned storage medium may be configured to store a computer program for performing the following steps:
  • the above-mentioned storage medium may include but not limited to: various media capable of storing computer programs such as USB flash drive, read-only memory ROM, random access memory RAM, mobile hard disk, magnetic disk or optical disk.
  • various media capable of storing computer programs such as USB flash drive, read-only memory ROM, random access memory RAM, mobile hard disk, magnetic disk or optical disk.
  • Embodiments of the present disclosure also provide an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
  • the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.
  • the above-mentioned processor may be configured to execute the following steps through a computer program:
  • each module or each step of the above-mentioned disclosure can be realized by a general-purpose computing device, and they can be concentrated on a single computing device, or distributed in a network composed of multiple computing devices Alternatively, they may be implemented in program code executable by a computing device so that they may be stored in a storage device to be executed by a computing device, and in some cases in an order different from that shown here
  • the steps shown or described are carried out, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps among them are fabricated into a single integrated circuit module for implementation.
  • the present disclosure is not limited to any specific combination of hardware and software.

Landscapes

  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种过道区域识别方法及装置，方法包括：在初始分区地图上获取多个区域中各个区域的相邻关系；根据相邻关系确定过道候选区域；根据预设规则对过道候选区域进行分割，得到多个目标区域；根据各个目标区域的相邻关系从多个目标区域中识别过道区域，解决了相关技术中无法有效识别过道，进而无法基于过道进行清扫路线规划的问题，可以有效识别出过道区域，有利于后期的个性化清扫模式和清扫顺序，使得清洁机器人更加智能。

Description

一种过道区域识别方法及装置
本公开要求如下专利申请的优先权：于2021年09月23日提交中国专利局、申请号为202111117651.5、发明名称为“一种过道区域识别方法及装置”的中国专利申请；上述专利申请的全部内容通过引用结合在本公开中。
技术领域
本公开涉及人工智能领域，具体而言，涉及一种过道区域识别方法及装置。
背景技术
清洁机器人在室内初次清扫过程中建立二维地图，已经成为业界共识。准确的地图划分和房间类型识别，既有利于清洁机器人的定位，同时也有利于个性的设置清扫模式和清扫顺序，使得清扫更加智能化。
相关技术中提到了具有区域划分功能的测绘制图，移动清洁装置在行驶中通过周边距离测量，完成空间总区域的测绘制图。然后通过传统视觉方法检测门把手获取门的信息，辅助面积阈值，将空间总区域划分成子区域。通过传统图像处理方法，仅能通过门来划分子区域，对于过道的划分却没有有效的处理方式。其次，上述文件仅能划分子区域，并没有对子区域的房间类型进行识别，无法实现基于不同房间类型的智能清扫业务。
过道(或走廊)是连接不同房间的过渡区域，过道(走廊)识别是清洁机器人区域识别的关键点。按房间类型进行清扫，需要规划机器的清扫路线，具体的，比如清扫完卧室，再去清扫客厅，应当控制机器人中间只能经过过度区域(过道)到达，否则会对其他区域造成污染或者二次污染。进一步的，过道通常是所有区域清扫完成后最后清扫，因此过道的识别对于智能清扫尤其重要。但是现有技术中，无法有效识别过道，进而无法基于过道进行清扫路线规划，导致清洁效率、效果降低，用户体验降低。
因此，有必要对现有技术予以改良以克服现有技术中的所述缺陷。
发明内容
本公开的目的在于提供一种过道区域识别方法及装置，以至少解决相关技术中无法有效识别过道，进而无法基于过道进行清扫路线规划的问题。
根据本公开的一个可选实施例，提供了一种过道区域识别方法，包括：
在初始分区地图上获取多个区域中各个区域的相邻关系；
根据所述相邻关系确定过道候选区域；
根据预设规则对过道候选区域进行分割，得到多个目标区域；
根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域。
可选地，根据所述相邻关系确定所述过道候选区域包括：
从所述多个区域中选取所述相邻关系的数量最多的预定数量的区域；
将所述预定数量的区域确定为所述过道候选区域。
可选地，在所述初始分区地图上获取所述多个区域中各个区域之间的相邻关系包括：
利用预设大小的滑窗，以预设步长遍历所述初始分区地图；
在遍历过程中，读取所述滑窗内像素点的像素值；
若所述滑窗内存在不同像素值，确定出现新的相邻关系，保存所述新的相邻关系；
遍历完成，生成所述各个区域的相邻关系。
可选地，根据预设规则对过道候选区域进行分割，得到多个目标区域包括：
获取所述过道候选区域的检测点信息，其中，所述检测点信息为清洁机器人采集的物品信息；
根据所述检测点信息对所述过道候选区域进行分割，得到多个目标区域。
可选地，获取所述过道候选区域的检测点信息包括：
获取所述过道候选区域内清洁机器人采集的物品信息，其中，所述物品信息包括物品标签、物品所在框大小和物品与所述清洁机器人的距离；
将所述物品信息确定为所述检测点信息。
可选地，根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域包括：
分别对所述过道候选区域沿着水平方向和竖直方向设置初始分割线；
基于所述初始分割线生成新的多个目标区域，并更新所述多个目标区域的相邻关系；
根据所述检测点信息与所述多个目标区域的相邻关系确定目标分割线；
根据所述目标分割线确定所述过道区域。
可选地，分别对所述过道候选区域沿着水平方向和竖直方向设置初始分割线包括：
分别在所述初始分区地图中所述水平方向和所述竖直方向上区域像素个数的突变位置设置预设长度的所述初始分割线。
根据本公开的另一个可选实施例，提供了一种过道区域识别装置，包括：
获取模块，用于在初始分区地图上获取多个区域中各个区域之间的相邻关系；
确定模块，用于根据所述相邻关系确定过道候选区域；
分割模块，用于根据预设规则对过道候选区域进行分割，得到多个目标区域；
识别模块，用于根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域。
可选地，所述确定模块包括：
选取子模块，用于从所述多个区域中选取所述相邻关系的数量最多的预定数量的区域；
第一确定子模块，用于将所述预定数量的区域确定为所述过道候选区域。
可选地，所述获取模块包括：
遍历子模块，用于利用预设大小的滑窗，以预设步长遍历所述初始分区地图；
读取子模块，用于在遍历过程中，读取所述滑窗内像素点的像素值；
第二确定子模块，用于若所述滑窗内存在不同像素值，确定出现新的相邻关系，保存所述新的相邻关系；
生成子模块，用于遍历完成，生成所述各个区域的相邻关系。
可选地，所述分割模块包括：
获取子模块，用于获取所述过道候选区域的检测点信息，其中，所述检测点信息为清洁机器人采集的物品信息；
分割子模块，用于根据所述检测点信息对所述过道候选区域进行分割，得到多个目标区域。
可选地，所述获取子模块，还用于
获取所述过道候选区域内清洁机器人采集的物品信息，其中，所述物品信息包括物品标签、物品所在框大小和物品与所述清洁机器人的距离；
将所述物品信息确定为所述检测点信息。
可选地，所述识别模块包括：
设置子模块，用于分别对所述过道候选区域沿着水平方向和竖直方向设置初始分割线；
更新子模块，用于基于所述初始分割线生成新的多个目标区域，并更新所述多个目标区域的相邻关系；
第三确定子模块，用于根据所述检测点信息与所述多个目标区域的相邻关系确定目标分割线；并根据所述目标分割线确定所述过道区域。
可选地，所述设置子模块，还用于
分别在所述初始分区地图中所述水平方向和所述竖直方向上区域像素个数的突变位置设置预设长度的所述初始分割线。
根据本公开的再一个可选实施例，提供了一种计算机可读的存储介质，所述存储介质中存储有计算机程序，其中，所述计算机程序被设置为运行时执行上述方法。
根据本公开的再一个可选实施例，提供了一种电子装置，包括存储器和处理器，所述存 储器中存储有计算机程序，所述处理器被设置为运行所述计算机程序以执行上述方法。
本公开的目的是通过以下技术方案实现：在初始分区地图上获取多个区域中各个区域之间的相邻关系；根据所述相邻关系确定过道候选区域；根据预设规则对过道候选区域进行分割，得到多个目标区域；根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域，解决了相关技术中无法有效识别过道，进而无法基于过道进行清扫路线规划的问题。
与现有技术相比，本公开具有如下有益效果：可以有效识别出过道区域，有利于后期的个性化清扫模式和清扫顺序，使得清洁机器人更加智能。
附图说明
此处所说明的附图用来提供对本公开的进一步理解，构成本公开的一部分，本公开的示意性实施例及其说明用于解释本公开，并不构成对本公开的不当限定。在附图中：
图1是本公开实施例的过道区域识别方法的清洁机器人的硬件结构框图；
图2是根据本公开实施例的过道区域识别方法的流程图；
图3是根据本公开实施例的过道划分和识别的流程图；
图4是根据本公开实施例的相邻关系获取的示意图；
图5是根据本公开实施例的过道分区识别的示意图；
图6是根据本公开实施例的过道区域识别装置的框图。
具体实施方式
下文中将参考附图并结合实施例来详细说明本公开。需要说明的是，在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等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。
本公开实施例所提供的方法实施例可以在清洁机器人或者类似的运算装置中执行。以运行在机器人上为例，图1是本公开实施例的过道区域识别方法的清洁机器人的硬件结构框图。如图1所示，清洁机器人可以包括一个或多个(图1中仅示出一个)处理器102(处理器102可以包括但不限于微处理器(Microprocessor Unit,简称是MPU)或可编程逻辑器件(Programmable logic device,简称是PLD)等的处理装置和用于存储数据的存储器104，可选地，上述清洁机器人还可以包括用于通信功能的传输设备106以及输入输出设备108。本领域普通技术人员可以理解，图1所示的结构仅为示意，其并不对上述清洁机器人的结构造成限定。例如，清洁机器人还可包括比图1中所示更多或者更少的组件，或者具有与图1所示等同功 能或比图1所示功能更多的不同的配置。
存储器104可用于存储计算机程序，例如，应用软件的软件程序以及模块，如本公开实施例中的过道区域识别方法对应的计算机程序，处理器102通过运行存储在存储器104内的计算机程序，从而执行各种功能应用以及数据处理，即实现上述的方法。存储器104可包括高速随机存储器，还可包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器104可进一步包括相对于处理器102远程设置的存储器，这些远程存储器可以通过网络连接至清洁机器人10。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
传输设备106用于经由网络接收或者发送数据。上述的网络具体实例可包括机器人10的通信供应商提供的无线网络。在一个实例中，传输设备106包括一个网络适配器(Network Interface Controller，简称为NIC)，其可通过基站与其他网络设备相连从而可与互联网进行通讯。在一个实例中，传输设备106可以为射频(Radio Frequency，简称为RF)模块，其用于通过无线方式与互联网进行通讯。
在本实施例中提供了一种运行于上述过道区域识别方法，图2是根据本公开实施例的过道区域识别方法的流程图，如图2所示，该流程包括如下步骤：
步骤S202，在初始分区地图上获取多个区域中各个区域的相邻关系；
本实施例中，初始分区地图清洁机器人在预先执行扫地任务过程中采集的，该相邻关系包括：相邻区域的名称或标识，相邻区域的数量等。
步骤S204，根据所述相邻关系确定过道候选区域；
具体的，从多个区域中确定部分为过道候选区域。
步骤S206，根据预设规则对过道候选区域进行分割，得到多个目标区域；
步骤S208，根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域。
通过上述步骤S202至S208，在初始分区地图上获取多个区域中各个区域的相邻关系；根据所述相邻关系确定过道候选区域；根据预设规则对过道候选区域进行分割，得到多个目标区域；根据该多个目标区域中各个目标区域的相邻关系从所述多个目标区域中识别过道区域，解决了相关技术中无法有效识别过道，进而无法基于过道进行清扫路线规划的问题，可以有效识别出过道区域，有利于后期的个性化清扫模式和清扫顺序，使得清洁机器人更加智能。
本实施例中，上述步骤S204具体可以包括：
S2041，从排序后的所述多个区域中选取所述相邻关系的数量最多的预定数量的区域，其中，预定数量可以根据实际情况进行设置，例如可以设置为2；可选的，可以先根据所述 多个区域的相邻关系的数量对所述多个区域进行排序，例如，总共包括5个区域：区域1，区域2，区域3，区域4，区域5，其中，区域1的相邻关系的数量为2，区域2的相邻关系的数量为1，区域3的相邻关系的数量为3，区域4的相邻关系的数量为3，区域5的相邻关系的数量为2，得到的排序结果为区域3、区域4、区域1、区域5、区域2；从排序后的多个区域中预定数量的区域，若排序是由大到小排序，则直接选取前预定数量的区域即可。
S2042，将所述预定数量的区域确定为所述过道候选区域。
从上述的排序结果中选取两个数据最大的区域，得到区域3、区域4，区域3与区域4即为过道候选区域。
上述通过相邻关系的数量选取区域，使得选中的区域为过道的可能性较大，从而使得组成的过道候选区域更为准确。
本实施例中，上述步骤S202具体可以包括：利用预设大小的滑窗，以预设步长遍历初始分区地图，其中，预设大小、预设步长均可以根据实际情况设置，例如可以将预设大小设置为2×2，将预设步长设置为1，即通过2×2的滑窗，以步长1遍历初始分区地图；在遍历过程中，读取所述滑窗内所有像素点的像素值；若所述滑窗内的像素点存在不同像素值，确定出现新的相邻关系，保存所述新的相邻关系，如区域1和区域2互为相邻，则保存；遍历完成，便可生成各个区域的相邻关系,本实施例中的相邻关系也可称为邻域关系，通过上述方式确定的相邻关系更准确，为提高过道候选区域的准确性做好了准备。
本实施例中，上述步骤S206具体可以包括：获取所述过道候选区域的检测点信息，其中，所述检测点信息为扫地机器人清洁机器人采集的物品信息，进一步的，获取过道候选区域内扫地机器人清洁机器人采集的物品信息，其中，所述物品信息包括物品标签、物品所在框大小、物品与所述扫地机器人清洁机器人的距离，例如物品包括沙发、茶几、餐桌、床、凳子等，物品标签可以是物品的名称，物品所在框大小为扫地机器人清洁机器人通过摄像头采集到的物品所在区域的大小，物品与所述扫地机器人清洁机器人的距离可以通过传感器采集到；将所述物品信息确定为所述监测点信息检测点信息。之后，根据所述监测点信息检测点信息对所述过道候选区域进行分割，得到多个目标区域，基于检测点信息，可以提高了目标区域的准确性。
本实施例中，上述步骤S208具体可以包括：
S2081，分别对过道候选区域沿着水平方向和竖直方向设置初始分割线，进一步的，分别在所述初始分区地图中所述水平方向和所述竖直方向上区域像素个数的突变位置设置预设长度的所述初始分割线，例如，过道候选区域1的水平位置Yi的像素个数为70，下一位置Yi+1处的像素个数为20，可确定水平位置Yi为突变位置。在水平位置Yi处画分割线段， 分割线段的实际长度可以设置可以根据实际过道的宽度范围；
S2082，基于所述初始分割线生成新的多个目标区域，并更新所述多个目标区域的相邻关系；
S2083，根据所述检测点信息与所述多个目标区域的相邻关系确定目标分割线，具体的，根据检测点信息判断每个目标区域中是否存在物品，根据判断的结果确定目标分割线，若某个区域不存在物品或物品相较与其他区域少很多，则确定该最佳分割线为目标分割线；
S2084，根据所述目标分割线确定所述过道区域,具体的,得到目标分割线之后，通过目标分割线将过道候选区域分割为至少两个区域，宽度为目标分割线宽度所在区域即为过道区域。
通过获取的该区域的物体信息，过道的几何形态，提取出最终的过道，准确的提取出过道区域，精度高，没有误检。
本公开实施例中，首先在初始分区地图上获取各个区域的相邻关系，包括相邻区域名和邻域数量，认为相邻关系最多的top2区域为过道可疑区域。其次结合视觉检测模型获取的该区域的特征物信息，过道的几何形态，提取出最终的过道。该方法准确的设计出过道的特征，精度高，没有误检。图3是根据本公开实施例的过道划分和识别的流程图，如图3所示，具体包括：
S301，获取初始分区地图；
S302，获取初始分区地图的相邻关系，基于过道的特征，认为相邻关系最多的top2区域为过道候选区域。此区域本身可能就是过道或者区域中包含过道部分，需要进一步提取。该假设是符合过道实际特征的，因为连接不同房间的过渡区域。其中，初始分区地图是基于视觉清洁机器人清扫中二维激光点云数据，和简单的门框宽度特征得到的，不同区域的像素值不同。初始分区地图中过道完全提取不出来，更谈不上识别。基于此假设，设计相邻关系获取算法。即利用2×2的滑窗遍历初始分区地图，步长为1。遍历过程中，读取滑窗内像素点的像素值。若存在不同像素值，则认为出现新的相邻关系，如区域1和区域2互为相邻，保存下来。遍历完成，生成最终的相邻关系。
S303，获取候选区域的检测点信息，即利用视觉检测模型，实时检测清洁机器人当前画面中物品信息。例如沙发、茶几、餐桌、床等，作为后期过道提取和识别的辅助信息。所述物品信息包括物品标签、框大小和物品距离清洁机器人的位置，其中，物品距离可以通过激光器点云数据获得。
S304，提取分割线，对过道候选区域沿着水平和竖直方向提取分割线，其中，分割线为分区地图中该方向上区域像素个数的突变位置。例如，候选区域1的水平位置Yi处的像素个数为60，下一位置Yi+1处的像素个数为30，此位置即为突变位置。在该位置处画分割线 段，分割线段的实际长度为0.8-1.5m，即实际过道的宽度范围。
S305，基于形态学分割提取过道区域，图4是根据本公开实施例的相邻关系获取的示意图，如图4所示，基于提取的分割线，生成新的区域，并更新相邻关系。图5是根据本公开实施例的过道分区识别的示意图，如图5所示，辅助清洁机器人清扫中的检测点信息，例如此区域范围内几乎无物品信息，得到最佳分割线段，即得到过道区域。
以区域相邻关系为核心特征，综合考虑视觉检测中的室内物品信息和形态学信息，最终划分和识别出过道，精度高，不会出现误检。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本公开的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如只读存储器(Read-Only Memory，简称为ROM)、随机存取存储器(Random Access Memory，简称为RAM)、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本公开各个实施例所述的方法。
在本实施例中还提供了一种过道区域识别装置，可以应用于智能清洁机器人或机器人，该智能清洁机器人或机器人用于实现上述实施例及优选实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。
图6是根据本公开实施例的过道区域识别装置的框图，如图6所示，包括：
获取模块62，用于在初始分区地图上获取多个区域中各个区域之间的相邻关系；
确定模块64，用于根据所述相邻关系确定过道候选区域；
分割模块66，用于根据预设规则对过道候选区域进行分割，得到多个目标区域；
识别模块68，用于根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域。
可选地，所述确定模块64包括：
选取子模块，用于从所述多个区域中选取所述相邻关系的数量最多的预定数量的区域；
第一确定子模块，用于将所述预定数量的区域确定为所述过道候选区域。
可选地，所述获取模块62包括：
遍历子模块，用于利用预设大小的滑窗，以预设步长遍历所述初始分区地图；
读取子模块，用于在遍历过程中，读取所述滑窗内像素点的像素值；
第二确定子模块，用于若所述滑窗内存在不同像素值，确定出现新的相邻关系，保存所 述新的相邻关系；
生成子模块，用于遍历完成，生成所述各个区域的相邻关系。
可选地，所述分割模块66包括：
获取子模块，用于获取所述过道候选区域的检测点信息，其中，所述检测点信息为清洁机器人采集的物品信息；
分割子模块，用于根据所述检测点信息对所述过道候选区域进行分割，得到多个目标区域。
可选地，所述获取子模块，还用于
获取所述过道候选区域内清洁机器人采集的物品信息，其中，所述物品信息包括物品标签、物品所在框大小和物品与所述清洁机器人的距离；
将所述物品信息确定为所述检测点信息。
可选地，所述识别模块68包括：
设置子模块，用于分别对所述过道候选区域沿着水平方向和竖直方向设置初始分割线；
更新子模块，用于基于所述初始分割线生成新的多个目标区域，并更新所述多个目标区域的相邻关系；
第三确定子模块，用于根据所述检测点信息与所述多个目标区域的相邻关系确定目标分割线；并根据所述目标分割线确定所述过道区域。
可选地，所述设置子模块，还用于
分别在所述初始分区地图中所述水平方向和所述竖直方向上区域像素个数的突变位置设置预设长度的所述初始分割线。
需要说明的是，上述各个模块是可以通过软件或硬件来实现的，对于后者，可以通过以下方式实现，但不限于此：上述模块均位于同一处理器中；或者，上述各个模块以任意组合的形式分别位于不同的处理器中。
本公开的实施例还提供了一种计算机可读的存储介质，该存储介质中存储有计算机程序，其中，该计算机程序被设置为运行时执行上述任一项方法实施例中的步骤。
可选地，在本实施例中，上述存储介质可以被设置为存储用于执行以下步骤的计算机程序：
S1，在初始分区地图上获取多个区域中各个区域之间的相邻关系；
S2，根据所述相邻关系确定过道候选区域；
S3，根据预设规则对所述过道候选区域进行分割，得到多个目标区域；
S4，根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域。
可选地，在本实施例中，上述存储介质可以包括但不限于：U盘、只读存储器ROM、随机存取存储器RAM、移动硬盘、磁碟或者光盘等各种可以存储计算机程序的介质。
本公开的实施例还提供了一种电子装置，包括存储器和处理器，该存储器中存储有计算机程序，该处理器被设置为运行计算机程序以执行上述任一项方法实施例中的步骤。
可选地，上述电子装置还可以包括传输设备以及输入输出设备，其中，该传输设备和上述处理器连接，该输入输出设备和上述处理器连接。
可选地，在本实施例中，上述处理器可以被设置为通过计算机程序执行以下步骤：
S1，在初始分区地图上获取多个区域中各个区域之间的相邻关系；
S2，根据所述相邻关系确定过道候选区域；
S3，根据预设规则对所述过道候选区域进行分割，得到多个目标区域；
S4，根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域。
可选地，本实施例中的具体示例可以参考上述实施例及可选实施方式中所描述的示例，本实施例在此不再赘述。
显然，本领域的技术人员应该明白，上述的本公开的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本公开不限制于任何特定的硬件和软件结合。
以上所述仅为本公开的优选实施例而已，并不用于限制本公开，对于本领域的技术人员来说，本公开可以有各种更改和变化。凡在本公开的原则之内，所作的任何修改、等同替换、改进等，均应包含在本公开的保护范围之内。

Claims (12)

  1. 一种过道区域识别方法，其特征在于，包括：
    在初始分区地图上获取多个区域中各个区域之间的相邻关系；
    根据所述相邻关系确定过道候选区域；
    根据预设规则对过道候选区域进行分割，得到多个目标区域；
    根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域。
  2. 根据权利要求1所述的方法，其特征在于，根据所述相邻关系确定所述过道候选区域包括：
    从所述多个区域中选取所述相邻关系的数量最多的预定数量的区域；
    将所述预定数量的区域确定为所述过道候选区域。
  3. 根据权利要求2所述的方法，其特征在于，所述从所述多个区域中选取所述相邻关系的数量最多的预定数量的区域包括：
    根据所述多个区域的相邻关系的数量对所述多个区域进行排序，得到排序结果；
    从所述排序结果中选取数量最多的预定数量的区域。
  4. 根据权利要求1所述的方法，其特征在于，在所述初始分区地图上获取所述多个区域中各个区域之间的相邻关系包括：
    利用预设大小的滑窗，以预设步长遍历所述初始分区地图；
    在遍历过程中，读取所述滑窗内像素点的像素值；
    若所述滑窗内存在不同像素值，确定出现新的相邻关系，保存所述新的相邻关系；
    遍历完成，生成所述各个区域的相邻关系。
  5. 根据权利要求1所述的方法，其特征在于，根据预设规则对过道候选区域进行分割，得到多个目标区域包括：
    获取所述过道候选区域的检测点信息，其中，所述检测点信息为清洁机器人采集的物品信息；
    根据所述检测点信息对所述过道候选区域进行分割，得到多个目标区域。
  6. 根据权利要求5所述的方法，其特征在于，获取所述过道候选区域的检测点信息包括：
    获取所述过道候选区域内所述清洁机器人采集的所述物品信息，其中，所述物品信息包括物品标签、物品所在框大小、以及物品与所述清洁机器人的距离；
    将所述物品信息确定为所述检测点信息。
  7. 根据权利要求1至6中任一项所述的方法，其特征在于，根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域包括：
    分别对所述过道候选区域沿着水平方向和竖直方向设置初始分割线；
    基于所述初始分割线生成新的多个目标区域，并更新所述多个目标区域的相邻关系；
    根据所述检测点信息与所述多个目标区域的相邻关系确定目标分割线；
    根据所述目标分割线确定所述过道区域。
  8. 根据权利要求7所述的方法，其特征在于，分别对所述过道候选区域沿着水平方向和竖直方向设置初始分割线包括：
    分别在所述初始分区地图中所述水平方向和所述竖直方向上区域像素个数的突变位置设置预设长度的所述初始分割线。
  9. 一种区域划分过程中过道识别装置，其特征在于，包括：
    获取模块，用于在初始分区地图上获取多个区域中各个区域之间的相邻关系；
    确定模块，用于根据所述相邻关系确定过道候选区域；
    分割模块，用于根据预设规则对过道候选区域进行分割，得到多个目标区域；
    识别模块，用于根据各个目标区域的相邻关系从所述多个目标区域中识别过道区域。
  10. 根据权利要求9所述的装置，其特征在于，所述确定模块包括：
    选取子模块，用于从所述多个区域中选取所述相邻关系的数量最多的预定数量的区域；
    第一确定子模块，用于将所述预定数量的区域确定为所述过道候选区域。
  11. 一种计算机可读的存储介质，其特征在于，所述存储介质中存储有计算机程序，其中，所述计算机程序被设置为运行时执行所述权利要求1至8任一项中所述的方法。
  12. 一种电子装置，包括存储器和处理器，其特征在于，所述存储器中存储有计算机程序，所述处理器被设置为运行所述计算机程序以执行所述权利要求1至8任一项中所述的方法。
PCT/CN2022/118384 2021-09-23 2022-09-13 一种过道区域识别方法及装置 WO2023045798A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111117651.5A CN113780233B (zh) 2021-09-23 2021-09-23 一种过道区域识别方法及装置
CN202111117651.5 2021-09-23

Publications (1)

Publication Number Publication Date
WO2023045798A1 true WO2023045798A1 (zh) 2023-03-30

Family

ID=78853107

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/118384 WO2023045798A1 (zh) 2021-09-23 2022-09-13 一种过道区域识别方法及装置

Country Status (2)

Country Link
CN (1) CN113780233B (zh)
WO (1) WO2023045798A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113780233B (zh) * 2021-09-23 2024-04-12 追觅创新科技(苏州)有限公司 一种过道区域识别方法及装置
CN114596417B (zh) * 2022-02-22 2023-04-07 北京城市网邻信息技术有限公司 房屋装修的数据处理方法、装置、电子设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102612698A (zh) * 2009-10-12 2012-07-25 高通股份有限公司 用于电子地图上的特征的自动化确定的方法和设备
CN104615138A (zh) * 2015-01-14 2015-05-13 上海物景智能科技有限公司 一种划分移动机器人室内区域动态覆盖方法及其装置
US20160300182A1 (en) * 2015-04-07 2016-10-13 Point Inside, Inc. Pog adjacency determination
US20180306591A1 (en) * 2017-04-21 2018-10-25 X Development Llc Aisle-based Roadmap Generation
CN112990098A (zh) * 2021-04-13 2021-06-18 追创科技(苏州)有限公司 区域划分方法和装置、存储介质、电子装置
CN113780233A (zh) * 2021-09-23 2021-12-10 追觅创新科技(苏州)有限公司 一种过道区域识别方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109522803B (zh) * 2018-10-18 2021-02-09 深圳乐动机器人有限公司 一种室内区域划分和识别方法、装置及终端设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102612698A (zh) * 2009-10-12 2012-07-25 高通股份有限公司 用于电子地图上的特征的自动化确定的方法和设备
CN104615138A (zh) * 2015-01-14 2015-05-13 上海物景智能科技有限公司 一种划分移动机器人室内区域动态覆盖方法及其装置
US20160300182A1 (en) * 2015-04-07 2016-10-13 Point Inside, Inc. Pog adjacency determination
US20180306591A1 (en) * 2017-04-21 2018-10-25 X Development Llc Aisle-based Roadmap Generation
CN112990098A (zh) * 2021-04-13 2021-06-18 追创科技(苏州)有限公司 区域划分方法和装置、存储介质、电子装置
CN113780233A (zh) * 2021-09-23 2021-12-10 追觅创新科技(苏州)有限公司 一种过道区域识别方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
BI ZENG, LIN ZHAN-PENG;DENG JIE-HANG: "Algorithm Ｒesearch on Ｒecognition and Improvement for Corridor of Autonomous Mobile Ｒobot", JOURNAL OF GUANGDONG UNIVERSITY OF TECHNOLOGY, vol. 33, no. 5, 1 September 2016 (2016-09-01), XP093051843 *

Also Published As

Publication number Publication date
CN113780233B (zh) 2024-04-12
CN113780233A (zh) 2021-12-10

Similar Documents

Publication Publication Date Title
WO2023045798A1 (zh) 一种过道区域识别方法及装置
WO2020134082A1 (zh) 一种路径规划方法、装置和移动设备
CN109522803A (zh) 一种室内区域划分和识别方法、装置及终端设备
US10083517B2 (en) Segmentation of an image based on color and color differences
CN110084243B (zh) 一种基于二维码和单目相机的档案识别与定位方法
CN110033478A (zh) 基于深度对抗训练的视觉目标跟踪方法和装置
Richter et al. Object class segmentation of massive 3D point clouds of urban areas using point cloud topology
WO2020248458A1 (zh) 一种信息处理方法、装置及存储介质
CN112802204B (zh) 未知环境下三维空间场景先验的目标语义导航方法及系统
CN112990098B (zh) 区域划分方法和装置、存储介质、电子装置
Beumier et al. Digital terrain models derived from digital surface model uniform regions in urban areas
CN115393386B (zh) 三维场景图的生成方法、装置、设备及可读存储介质
CN110764513B (zh) 一种地图盲区识别方法
CN108764297B (zh) 一种可移动设备位置的确定方法、装置及电子设备
US20160085831A1 (en) Method and apparatus for map classification and restructuring
CN113985866A (zh) 扫地机器人路径规划方法、装置、电子设备、存储介质
CN111369688B (zh) 一种结构化场景表达的认知导航方法及系统
WO2023179382A1 (zh) 机器人地图中障碍物的标记方法及装置
CN116883612A (zh) 一种三维场景模型生成方法及系统
WO2022247544A1 (zh) 地图分区方法、装置、自主移动设备和存储介质
CN112435274A (zh) 一种基于面向对象分割的遥感影像面状地物提取方法
CN114073454A (zh) 房间划分方法、装置、设备及可读存储介质
CA2845601A1 (en) Segmentation of an image based on color and color differences
WO2023179207A1 (zh) 地图的处理方法、装置、清洁设备、存储介质及电子装置
WO2023155681A1 (zh) 区域信息的处理方法和装置、存储介质及电子装置

Legal Events

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

Ref country code: DE