WO2019201065A1 - 基于地理图像学确定人流热区的方法和装置 - Google Patents

基于地理图像学确定人流热区的方法和装置 Download PDF

Info

Publication number
WO2019201065A1
WO2019201065A1 PCT/CN2019/079900 CN2019079900W WO2019201065A1 WO 2019201065 A1 WO2019201065 A1 WO 2019201065A1 CN 2019079900 W CN2019079900 W CN 2019079900W WO 2019201065 A1 WO2019201065 A1 WO 2019201065A1
Authority
WO
WIPO (PCT)
Prior art keywords
flow
person
area
density
processor
Prior art date
Application number
PCT/CN2019/079900
Other languages
English (en)
French (fr)
Inventor
赵振功
Original Assignee
京东方科技集团股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 京东方科技集团股份有限公司 filed Critical 京东方科技集团股份有限公司
Priority to US16/496,213 priority Critical patent/US11068714B2/en
Publication of WO2019201065A1 publication Critical patent/WO2019201065A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/20—Drawing from basic elements, e.g. lines or circles
    • G06T11/206—Drawing of charts or graphs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/20—Drawing from basic elements, e.g. lines or circles
    • G06T11/203—Drawing of straight lines or curves
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/40—Analysis of texture
    • G06T7/41—Analysis of texture based on statistical description of texture
    • G06T7/44—Analysis of texture based on statistical description of texture using image operators, e.g. filters, edge density metrics or local histograms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/176—Urban or other man-made structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance

Definitions

  • the present disclosure relates to the field of data mining, and more particularly to a method and apparatus for determining a hot stream of a person based on geographic imaging.
  • the flow map of the hot stream is an estimate of the position of the descendant of the current scene, and generates an image indicating the level of the stream density of the current scene.
  • the flow of hot zone map technology has a wide range of applications in the fields of human flow analysis and security monitoring. For example, in security monitoring, the security department can determine which locations are most active and identify them as key monitoring areas through the hotline map.
  • the pedestrian hot zone map can be used to characterize the pedestrian active area for a period of time for subsequent high-level analysis.
  • a computer implemented method for determining a hot stream of a person's stream based on geographic imaging includes: determining height data of each coordinate point in a geographical image sense based on human flow density data of each coordinate point in a region within a time period; and using geographic image data to draw the region within the region according to the height data Contour lines; and determining the hot stream of the person in the area based on the range of contours drawn by the contour lines.
  • the step of determining the height data of each coordinate point in the geographic image sense based on the human flow density data of each coordinate point in the region within a time period comprises: directly using the human flow density data of each coordinate point as the corresponding coordinate The height data of the point in the sense of geographic imaging.
  • the step of determining a hot stream of the person flow in the area according to the circled range of the contours drawn includes: determining the contour line drawn as a density line of human flow; and according to the flow of people, etc.
  • the range of the density line is used to determine the hot stream of the person in the area.
  • the determining, according to the range of the density line of the human flow, the step of determining a hotspot of the flow in the area includes: selecting a circle of a density line of a flow of a person whose heat is greater than a set heat value as the The hot zone of the person flow in the area; or the range of the density line of the flow of people whose flow density is higher than the set threshold is taken as the hot zone of the person in the area.
  • the determining, according to the range of the density line of the human flow, the step of determining a hotspot of the flow in the area includes: selecting a range of the density line of the flow of the person whose heat is greater than the set heat value, and selecting An alternate hot zone; and an alternate hot zone greater than the set area is determined as the hot stream of the person in the zone.
  • the method further comprises: sorting the determined flow hot zones according to the heat; and, according to the sorting result, marking each of the hot runners in different colors in the display interface.
  • the step of using geographic imagery to map contours within the region based on the height data comprises: for each uniformly divided grid cells in the region, corresponding to each grid cell The height data of the coordinate point is compared with the set height value; in response to the height data of the coordinate point corresponding to one grid unit being greater than the set height value, the upper left corner of the grid unit is marked black; according to the grid In the black condition of the four corners of the unit, the corresponding contour line is drawn in the grid unit; the contour line in each grid unit constitutes a contour line in which the height in the area is calibrated to the set height value; The set height value is equal to the set flow density value.
  • an apparatus for determining a hot stream of a person stream based on geographic imaging comprising: a processor; a memory storing instructions that, when executed by the processor, cause the processor : determining height data of each coordinate point in the geographic image sense based on the human flow density data of each coordinate point in the region within a time period; and using the geographic data to draw the contour line in the region according to the height data And determining the hot stream of the person in the area based on the range of the contours drawn.
  • the instructions when executed by the processor, further cause the processor to directly use the human stream density data for each coordinate point as height data in a geographic imaging sense of the corresponding coordinate point.
  • the instructions when executed by the processor, further cause the processor to: determine the contours drawn as a density line of human flows; and according to a range of density lines of the human flow A hot stream of people in the area is determined.
  • the instructions when executed by the processor, further cause the processor to: select a range of density lines of a stream of people having a heat greater than a set heat value as a hot stream of people in the area; or The circle of the equal density line of the flow of people whose flow density is higher than the set threshold is selected as the hot zone of the flow in the area.
  • the instructions when executed by the processor, further cause the processor to: select, as an alternative hot zone, a range of density lines of a person flow having a heat greater than a set heat value; and to be greater than The candidate hot zone of the set area is determined to be the hot stream of the person in the area.
  • the instructions when executed by the processor, further cause the processor to: sort the determined person stream hotspots according to the heat; and display the interface according to the ranking result of the hot zone sorting module The different areas are marked with different colors.
  • a non-transitory computer readable storage medium storing instructions that, when executed by a processor, enable the processor to perform the aforementioned methods.
  • FIG. 1 is a flowchart of an exemplary method for determining a hot stream of a person flow based on geographic imagery according to an embodiment of the present disclosure
  • FIG. 2 is a flow chart of an exemplary method for drawing contour lines using geographic imagery according to an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of an example of a grid unit uniformly divided in a region according to an embodiment of the present disclosure
  • FIG. 4 is a schematic diagram showing an example of a situation in which an upper left corner of a grid unit is provided according to an embodiment of the present disclosure
  • 5a is a schematic diagram showing an example of a black condition of an upper left corner of 16 types of grid cells according to an embodiment of the present disclosure
  • FIG. 5b is a schematic diagram showing an example of a midpoint of an edge of a grid unit according to an embodiment of the present disclosure
  • FIG. 6 is a schematic diagram showing an example of drawing outline lines of 16 types of grid cells according to an embodiment of the present disclosure
  • FIG. 7 is a schematic diagram showing an example of contour lines formed by contour lines of a grid unit according to an embodiment of the present disclosure
  • FIG. 8 is a block diagram showing an internal structure of an example apparatus for determining a hot stream of a person based on geographic imagery according to an embodiment of the present disclosure
  • FIG. 9 is a hardware layout diagram of an example apparatus for determining a hot stream of a person based on geographic imagery according to an embodiment of the present disclosure.
  • the density clustering algorithm is usually used to calculate the heat of the person, and the hot stream is circled according to the calculated heat of the person.
  • the density clustering algorithm has a large amount of calculation and a slow convergence rate. Therefore, it is difficult to realize real-time calculation and display of the hot stream of the hot stream.
  • the human flow density data of each coordinate point in the region may be used as the height data of each coordinate point, and then the method for calculating the medium-high line of the geographic image can be used to quickly obtain the density line of the human flow, and based on the flow of people, etc.
  • the density line determines the hot zone. Since the algorithm of the geographic image calculation contour line is simple and fast, in some embodiments of the present disclosure, the hot area is determined by geographic image, the calculation amount is small, and the hot stream area can be quickly determined, thereby realizing the real time of the hot area. Calculation and display.
  • the term "human flow density" refers to the number of humans or objects visible in an area of a unit area.
  • the hot water zone determination is mainly performed for humans in this document, the present disclosure is not limited thereto, but can be applied to hot zone determination of any actual object. For example, in farms, zoos or safari parks, or in the wild, it can be used to determine the hot spots where animals are concentrated. Further, in an automated factory, for example, the determination of the hot spot of the object can be performed with a target of a non-living object such as a robot, and for example, in the road traffic monitoring, the determination of the hot spot of the object can be performed with a target of a non-living object such as a vehicle. . Therefore, in this article, "person flow” and "object flow” can be used interchangeably as synonyms.
  • the specific process of the method for determining a hot stream of a person based on geographic image data provided by the embodiment of the present disclosure may be as shown in FIG. 1 , and includes the following steps:
  • Step S101 Count the flow density data of each coordinate point in the area in a period of time.
  • the video of the surveillance video of the area may be analyzed, and the data of the person flow in the area, including the coordinates of the person and the time point of the video, may be collected; and then the flow of people with the same coordinates in a period of time is accumulated into a human flow. , thereby counting the flow density data of each coordinate point in the region over a period of time.
  • this step S101 can be an optional step. For example, in the case of studying historical data, existing human flow density data can be used without the need to instantly calculate the flow density data.
  • Step S102 The human flow density data of each coordinate point is used as height data of each coordinate point, and contour lines in the area are drawn by using geographic image data based on the height data.
  • Step S103 After the drawn contour line is used as the density line of the human flow, the hot region of the human flow in the area is determined according to the circle of the density line such as the human flow.
  • the hot stream of the person flow can be selected according to the set rules.
  • a range of the density line of the human flow equal to the set heat value may be selected as the hot zone of the human flow in the area; for example, a circle of the equal density line of the flow of the heat greater than 200 is selected as the area.
  • a range of the density line of the flow of people whose flow density is higher than a set threshold is selected as the hot zone of the person in the area.
  • the term "human flow iso-density line” as used herein has a similar meaning to "contour line” in geographic imaging.
  • the equal-flow line of people flow can refer to a line formed by points having the same flow density in the area, that is, all points on a density line such as a person flow have the same flow density.
  • the area factor may be considered: the range of the density line of the flow of the person whose heat is greater than the set heat value is selected as the candidate hot zone;
  • An alternative hot zone greater than the set area is determined to be the hot stream of the person in the area. For example, an alternative hot zone greater than 2 square meters is identified as the hot zone of the person in the area.
  • the determined hot water zones may be sorted according to the heat; according to the sorting result, different colors are matched for each hot zone, so that the display interface is different.
  • the color indicates each person's hot zone. For example, the five hotspots with high heat to low heat in the sorting result are matched with deep red, red, water red, yellow, and blue, so that the hot zone distribution of different heats can be more intuitively understood.
  • the specific method for drawing the contour lines in the area according to the height data of each coordinate point in the area mentioned in the above step S102 is as shown in FIG. 2, but is not limited thereto, and includes the following steps. :
  • the height data of the coordinate point corresponding to the grid unit is marked at the vertex of each grid unit, that is, the coordinate point corresponding to the grid unit.
  • Human flow density data is marked at the vertex of each grid unit, that is, the coordinate point corresponding to the grid unit.
  • the height data of the coordinate points corresponding to each grid unit is compared with a set height value; wherein the set height value is equal to the set human flow density value. In this way, the flow density data of the coordinate points corresponding to each grid unit is compared with the set flow density value.
  • the upper left corner of the grid unit may be marked black; for example, if the set height value is 5, then FIG. 3
  • the black condition in the upper left corner of the grid cell shown in Fig. 4 is shown in Fig. 4.
  • the present disclosure is not limited thereto.
  • some other corner of the grid unit may also be black, such as the lower left corner, the lower right corner, or the upper right corner.
  • the specific black flag does not affect the implementation of the final result.
  • the contour can be drawn by connecting the midpoint of the edge of the grid cell as shown in Figure 5b.
  • the 16 black conditions can correspond to the 16 contour lines in the grid unit, as shown in Figure 6.
  • a contour line in each of the grid cells is formed as a contour line in which the height in the area is set to the set height value.
  • the contour line drawn according to the black condition of each grid unit in FIG. 5 constitutes a contour line whose height is calibrated to the set height value, which is also the density of the set person flow. Density values of people flow equal density lines.
  • the algorithm for drawing contour lines in the region using geographic imagery is very simple, mainly including simple numerical comparison and line drawing, without complicated convergence calculation, which greatly reduces the calculation amount and calculation time.
  • the real-time determination of the hot zone and the display can be realized.
  • an embodiment of the present disclosure provides a device for determining a hot stream of a person based on geographic image.
  • the internal structure may be as shown in FIG. 8 , including: a human flow density statistics module 801 , a contour drawing module 802 , and a hot zone.
  • the module 803 is determined.
  • the flow density statistics module 801 is configured to collect the flow density data of each coordinate point in the region in a period of time;
  • the contour drawing module 802 is configured to use the human stream density data of each coordinate point counted by the human flow density statistics module 801 as the height data of each coordinate point, and then use geographic image data to draw the area in the area according to the height data of each coordinate point. contour line.
  • the specific method for the contour drawing module 802 to use the geographic data to draw the contour lines in the area according to the height data of each coordinate point can refer to the method flow shown in FIG. 2 above, and details are not described herein again.
  • the hot zone determining module 803 is configured to use the contour line drawn by the contour drawing module 802 as a density line of the human flow, and determine the hot stream of the hot stream in the area according to the circle of the density line such as the human flow. Specifically, the hot zone determining module 803 may select a range of the density line of the human flow equal to the set heat value as the hot zone of the human flow in the area; or select a circle of equal density of the flow of the human flow density higher than the set threshold. The range serves as the hot stream of people in the area.
  • the hot zone determining module 803 is configured to select a range of the density line of the human flow equal to the set heat value as the candidate hot zone; and determine the candidate hot zone that is greater than the set area. It is a hot zone for people in the area.
  • the apparatus for determining a hot stream of a person based on geographic image data may further include: a hot zone sorting module 804 and a hot zone display module 805.
  • the hot zone sorting module 804 is configured to sort the determined hot stream of the person stream according to the heat
  • the hot zone display module 805 is configured to mark each hot zone in different colors in the display interface according to the sorting result of the hot zone sorting module 804.
  • FIG. 9 is a hardware layout diagram of an example apparatus 900 for determining a hot stream of a person based on geographic imagery according to an embodiment of the present disclosure.
  • Hardware arrangement 900 includes a processor 906 (eg, a digital signal processor (DSP), central processing unit (CPU), etc.).
  • Processor 906 can be a single processing unit or a plurality of processing units for performing different acts of the flows described herein.
  • the arrangement 900 can also include an input unit 902 for receiving signals from other entities, and an output unit 904 for providing signals to other entities.
  • Input unit 902 and output unit 904 may be arranged as a single entity or as separate entities.
  • input unit 902 and output unit 904 may also include a communicator for communication with external processor 906, such as a wireless communication unit, a wired communication unit, and the like.
  • the wireless communication unit may be a communication supporting protocols such as Wi-Fi, Bluetooth, 3GPP series (including, for example, GSM, GPRS, CDMA, WCDMA, CDMA2000, TD-SCDMA, LTE, LTE-A, 5G NR, etc.), Wi-Max, and the like.
  • the wired communication unit may be a communication module that supports protocols such as Ethernet, USB, fiber optics, xDSL, and the like.
  • input unit 902 and/or output unit 904 can also be an interface that is communicatively coupled to an external communicator.
  • the example device 900 itself may not include a communicator, but rather communicates with an external communicator via an interface and implements the same or similar functionality.
  • arrangement 900 can include at least one readable storage medium 908 in the form of a non-volatile or volatile memory, such as an electrically erasable programmable read only memory (EEPROM), flash memory, and/or a hard drive.
  • the readable storage medium 908 includes a computer program 910 that includes code/computer readable instructions that, when executed by the processor 906 in the arrangement 900, cause the hardware arrangement 900 and/or the device including the hardware arrangement 900 to The flow described above in connection with Figures 1-7 and any variations thereof are performed.
  • Computer program 910 can be configured as computer program code having a computer program module 910A-910C architecture, for example. Accordingly, the code in the computer program of arrangement 900 can include a module 910A for determining height data for each coordinate point in a geographic imaging sense based on human flow density data for each coordinate point in the region over a period of time; module 910B, For mapping the contour lines in the region using geographic imagery according to the height data; and module 910C for determining the hot stream of the person flow in the region according to the circled range of the contour lines drawn.
  • a module 910A for determining height data for each coordinate point in a geographic imaging sense based on human flow density data for each coordinate point in the region over a period of time
  • module 910B For mapping the contour lines in the region using geographic imagery according to the height data
  • module 910C for determining the hot stream of the person flow in the region according to the circled range of the contour lines drawn.
  • the computer program module can substantially perform various actions in the flows illustrated in FIGS. 1-7 to simulate device 800.
  • processor 906 when different computer program modules are executed in processor 906, they may correspond to different units or modules in device 800.
  • code means in the embodiment disclosed above in connection with FIG. 9 is implemented as a computer program module that, when executed in processor 906, causes hardware arrangement 900 to perform the actions described above in connection with FIGS. 1-7, however In an embodiment, at least one of the code means can be implemented at least in part as a hardware circuit.
  • the processor may be a single CPU (Central Processing Unit), but may also include two or more processing units.
  • a processor can include a general purpose microprocessor, an instruction set processor, and/or a related chipset and/or a special purpose microprocessor (eg, an application specific integrated circuit (ASIC)).
  • the processor may also include an onboard memory for caching purposes.
  • the computer program can be carried by a computer program product connected to the processor.
  • the computer program product can comprise a computer readable medium having stored thereon a computer program.
  • the computer program product can be a flash memory, a random access memory (RAM), a read only memory (ROM), an EEPROM, and the computer program modules described above can be distributed to different computers in the form of memory within the device in alternative embodiments. In the program product.
  • the method for calculating the medium-high line of the geographic image can quickly obtain the density line of the human flow, and based on the flow of people.
  • the isothermal line determines the hot zone. Since the algorithm for calculating the contour of the geographic image is simple and fast, the technical solution of the disclosed technology has a small amount of calculation, and can quickly determine the hot zone of the human flow, thereby realizing real-time calculation and display of the hot zone.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

本公开公开了一种基于地理图像学确定人流热区的方法和装置，所述方法包括：统计一段时间内区域中各坐标点的人流密度数据；将各坐标点的人流密度数据，作为各坐标点的高度数据后，根据所述高度数据运用地理图像学绘制所述区域内的等高线；将绘制的等高线作为人流等密度线后，根据人流等密度线所圈范围确定所述区域中的人流热区。应用本公开确定人流热区的计算量小，能快速确定人流热区，实现实时计算和显示。

Description

基于地理图像学确定人流热区的方法和装置
相关申请的交叉引用
本申请要求于2018年4月20日递交的题为“一种基于地理图像学确定人流热区的方法和装置”的中国专利申请(申请号201810359674.9)的优先权，在此以全文引用的方式将该中国专利申请并入本文中。
技术领域
本公开涉及数据挖掘领域，特别是指一种基于地理图像学确定人流热区的方法和装置。
背景技术
人流热区图，即对当前场景下行人的位置进行估计，并生成可表示当前场景下行人等人流密度高低的图像。人流热区图技术在人流分析，安全监控等领域具有广泛的应用。譬如，在安全监控中，安全部门可以通过人流热区图来确定哪些位置人流最为活跃，并确定为重点监控区域。在人流分析中，可以使用人流热区图表征一段时间内行人活跃区域，用于后续的高层面分析。
发明内容
根据本公开的一个方面，提供了一种计算机实现的基于地理图像学来确定人流热区的方法。该方法包括：基于一时间段内区域中各坐标点的人流密度数据来确定各坐标点在地理图像学意义下的高度数据；根据所述高度数据，运用地理图像学来绘制所述区域内的等高线；以及根据所绘制的等高线所圈范围来确定所述区域中的人流热区。
在一些实施例中，基于一时间段内区域中各坐标点的人流密度数据来确定各坐标点在地理图像学意义下的高度数据的步骤包括：将各坐标点的人流密度数据直接作为相应坐标点的在地理图像学意义下的高度数据。
在一些实施例中，根据所绘制的等高线所圈范围来确定所述区域中的人流 热区的步骤包括：将所绘制的等高线确定为人流等密度线；以及根据所述人流等密度线所圈范围来确定所述区域中的人流热区。
在一些实施例中，所述根据所述人流等密度线所圈范围来确定所述区域中的人流热区的步骤包括：选取热度大于设定热度值的人流等密度线所圈范围作为所述区域中的人流热区；或者选取人流密度高于设定阈值的人流等密度线所圈范围作为所述区域中的人流热区。
在一些实施例中，所述根据所述人流等密度线所圈范围来确定所述区域中的人流热区的步骤包括：将热度大于设定热度值的人流等密度线所圈范围，选取为备选热区；以及将大于设定面积的备选热区，确定为所述区域中的人流热区。
在一些实施例中，所述方法还包括：根据热度对确定的人流热区进行排序；以及根据排序结果，在显示界面中以不同颜色标示各人流热区。
在一些实施例中，根据所述高度数据运用地理图像学来绘制所述区域内的等高线的步骤包括：对于所述区域中均匀划分的网格单元，将每个网格单元所对应的坐标点的高度数据与设定高度值进行比较；响应于一个网格单元所对应的坐标点的高度数据大于所述设定高度值，将该网格单元的左上角标黑；根据该网格单元四角的标黑情况，在该网格单元中绘制对应的轮廓线；由各网格单元中的轮廓线构成所述区域内高度标定为所述设定高度值的等高线；其中，所述设定高度值等于设定的人流密度值。
根据本公开的另一方面，提供了一种基于地理图像学来确定人流热区的装置，包括：处理器；存储器，存储指令，所述指令在由所述处理器执行时使得所述处理器：基于一时间段内区域中各坐标点的人流密度数据来确定各坐标点在地理图像学意义下的高度数据；根据所述高度数据，运用地理图像学来绘制所述区域内的等高线；以及根据所绘制的等高线所圈范围来确定所述区域中的人流热区。
在一些实施例中，所述指令在由所述处理器执行时还使得所述处理器：将各坐标点的人流密度数据直接作为相应坐标点的在地理图像学意义下的高度数据。
在一些实施例中，所述指令在由所述处理器执行时还使得所述处理器：将 所绘制的等高线确定为人流等密度线；以及根据所述人流等密度线所圈范围来确定所述区域中的人流热区。
在一些实施例中，所述指令在由所述处理器执行时还使得所述处理器：选取热度大于设定热度值的人流等密度线所圈范围作为所述区域中的人流热区；或者选取人流密度高于设定阈值的人流等密度线所圈范围作为所述区域中的人流热区。
在一些实施例中，所述指令在由所述处理器执行时还使得所述处理器：将热度大于设定热度值的人流等密度线所圈范围，选取为备选热区；以及将大于设定面积的备选热区，确定为所述区域中的人流热区。
在一些实施例中，所述指令在由所述处理器执行时还使得所述处理器：根据热度对确定的人流热区进行排序；以及根据所述热区排序模块的排序结果，在显示界面中以不同颜色标示各人流热区。
根据本公开的又一方面，提供了一种存储指令的非暂时计算机可读存储介质，所述指令在由处理器执行时使所述处理器能够执行前述方法。
附图说明
为了更清楚地说明本公开实施例中的技术方案，下面将对实施例的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公开的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本公开实施例提供的一种基于地理图像学确定人流热区的示例方法流程图；
图2为本公开实施例提供的运用地理图像学绘制等高线的示例方法流程图；
图3为本公开实施例提供的区域内均匀划分的网格单元的示例示意图；
图4为本公开实施例提供的网格单元左上角标示情况的示例示意图；
图5a为本公开实施例提供的16种网格单元左上角标黑情况的示例示意图；
图5b为本公开实施例提供的网格单元的边的中点的示例示意图；
图6为本公开实施例提供的16种网格单元内轮廓线绘制方式的示例示意 图；
图7为本公开实施例提供的由网格单元的轮廓线构成等高线的示例示意图；
图8为本公开实施例提供的一种基于地理图像学确定人流热区的示例装置的内部结构框图；以及
图9为本公开实施例提供的一种基于地理图像学确定人流热区的示例装置的硬件布置图。
具体实施方式
为使本公开的目的、技术方案和优点更加清楚明白，以下结合具体实施例，并参照附图，对本公开进一步详细说明。
下面详细描述本公开的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本公开，而不能解释为对本公开的限制。
本技术领域技术人员可以理解，除非特意声明，这里使用的单数形式“一”、“一个”、“所述”和“该”也可包括复数形式。这里使用的措辞“和/或”包括一个或更多个相关联的列出项的全部或任一单元和全部组合。
需要说明的是，本公开实施例中所有使用“第一”和“第二”的表述仅是为了区分两个相同名称非相同的实体或者非相同的参量，可见“第一”“第二”仅为了表述的方便，不应理解为对本公开实施例的限定，后续实施例对此不再一一说明。
目前的人流热区的确定方法中，通常基于密度聚类算法进行人流热度的计算，再根据计算出的人流热度圈出人流热区。但密度聚类算法计算量很大，收敛速度慢，因此，难以实现人流热区的实时计算和显示。
在本公开一些实施例中，可以将区域中各坐标点的人流密度数据作为各坐标点的高度数据，然后可以利用地理图像学中等高线计算的方法快速得到人流等密度线，而基于人流等密度线则可以确定热区。由于地理图像学计算等高线的算法简单、快速，因此，在本公开的一些实施例中，利用地理图像学确定热 区，计算量小，可以快速确定人流热区，从而实现热区的实时计算和显示。在本文中，术语“人流密度”指的是在单位面积的区域内可见的人类或对象的数量。
此外，需要注意的是：尽管在本文中主要以人类为对象来进行人流热区确定，但本公开不限于此，而是可以应用于任何实际对象的热区确定。例如，在养殖场、动物园或野生动物园、或野外中，可以用于对动物聚集的热区进行确定。此外，在例如自动化工厂中，可以以例如机器人等非生命对象为目标来进行对象热区的确定，又例如在道路交通监控中，可以以车辆等非生命对象为目标来进行对象热区的确定。因此，在本文中，可以将“人流”和“对象流”当做同义词来互换使用。
下面结合附图详细说明本公开技术方案。
本公开实施例提供的一种可由计算机实现的基于地理图像学来确定人流热区的方法具体流程可如图1所示，包括如下步骤：
步骤S101：统计一段时间内区域中各坐标点的人流密度数据。
例如，在一些实施例中，可以对所述区域的监控录像的视频进行分析，收集区域内人流数据，包括人员的坐标和视频的时间点；进而将一段时间内相同坐标的人流累加成为人流量，从而统计出一段时间内区域中各坐标点的人流密度数据。此外，需要注意的是该步骤S101可以是可选步骤。例如，在研究历史数据的情况下，可以采用已有的人流密度数据，而无需即时统计人流密度数据。
步骤S102：将各坐标点的人流密度数据，作为各坐标点的高度数据后，根据所述高度数据运用地理图像学绘制所述区域内的等高线。
本步骤中，根据区域内各坐标点的高度数据运用地理图像学绘制所述区域内的等高线的具体方法将在后续详细介绍。然而，需要注意的是本公开不限于此。例如，在另一些实施例中，也可以对各坐标点的高度数据进行各种预处理，而不是直接将其用作地理图像学意义下的高度数据。例如，在一些实施例中，可以对人流密度数据中存在明显错误的数据加以剔除，例如人流密度超出实际人流密度极限的数据等。
步骤S103：将绘制的等高线作为人流等密度线后，根据人流等密度线所 圈范围确定所述区域中的人流热区。
本步骤中，可以按照设定的规则选取人流热区。在一些实施例中，可以选取热度大于设定热度值的人流等密度线所圈范围作为所述区域中的人流热区；比如，选取热度大于200的人流等密度线所圈范围作为所述区域中的人流热区。其中，热度＝范围内总热量/范围的面积；范围内总热量＝范围内所有坐标点的人流密度之和。
或者，选取人流密度高于设定阈值的人流等密度线所圈范围作为所述区域中的人流热区。
需要注意的是，这里使用的术语“人流等密度线”具备类似于地理图像学中“等高线”类似的含义。换言之，人流等密度线可以指的是区域中由具有相同的人流密度的点所形成的线，即在一条人流等密度线上的所有点都具有相同的人流密度。
在另一些实施例中，在选取人流热区时，除了考虑热度因素外，还可考虑面积因素：将热度大于设定热度值的人流等密度线所圈范围，选取为备选热区；将大于设定面积的备选热区，确定为所述区域中的人流热区。比如，将大于2平米的备选热区确定为所述区域中的人流热区。
在又一些实施例中，在选取了多个人流热区后，还可根据热度对确定的人流热区进行排序；根据排序结果，为各人流热区匹配不同颜色，从而在显示界面中以不同颜色标示各人流热区。比如，将排序结果中热度从高到低的5个人流热区，依次匹配深红、红色、水红、黄色、蓝色，从而可以更为直观地了解到不同热度的热区分布。
上述步骤S102中提到的根据区域内各坐标点的高度数据运用地理图像学绘制所述区域内的等高线的具体方法，流程可如图2所示(但不限于此)，包括如下步骤：
S201：对于所述区域中均匀划分的网格单元，将每个网格单元所对应的坐标点的高度数据与设定高度值进行比较。
例如，如图3所示的均匀划分的网格单元中，每个网格单元顶点处标记了该网格单元所对应的坐标点的高度数据，亦即该网格单元所对应的坐标点的人流密度数据。
将每个网格单元所对应的坐标点的高度数据与设定高度值进行比较；其中，所述设定高度值等于设定的人流密度值。如此，即是将每个网格单元所对应的坐标点的人流密度数据与设定的人流密度值进行比较。
S202：将每个网格单元所对应的坐标点的高度数据与设定高度值进行比较，并根据比较结果对网格单元左上角或其它角进行相应标示。
具体地，当一个网格单元所对应的坐标点的高度数据大于所述设定高度值时，可以将该网格单元的左上角标黑；比如，设定高度值为5，则图3所示的网格单元中左上角标黑情况如图4所示。
也就是说，当一个网格单元所对应的坐标点的人流密度数据大于设定的人流密度值时，将该网格单元的左上角标黑。
此外，尽管在本实施例中将网格单元的左上角标黑，但本公开不限于此。在另一些实施例中，也可以对网格单元的其它某个角标黑，例如左下角、右下角或右上角。换言之，只要在对所有网格单元进行该处理时都对同一个角进行操作，则具体标黑哪个角并不影响最后结果的实现。
S203：对于每个网格单元，根据该网格单元四角的标示情况，在该网格单元中绘制对应的轮廓线。
具体地，每个网格单元中包括四个顶点，而四个顶点的网格单元可以有2^4＝16种标黑情况，如图5a所示。通过连接如图5b所示的网格单元的边的中点，就可以绘制轮廓了。而16种标黑情况又可分别对应于网格单元中16种轮廓线绘制方式，如图6所示。
S204：由各网格单元中的轮廓线构成所述区域内高度标定为所述设定高度值的等高线。
如图7所示，根据图5中每个网格单元的标黑情况所绘制的轮廓线，构成了高度标定为所述设定高度值的等高线，其也是密度标定为设定的人流密度值的人流等密度线。
从上述可以看出，运用地理图像学绘制所述区域内的等高线的算法非常简单，主要包括简单的数值大小比较，和线条绘制，没有复杂的收敛计算，大大减少了计算量和计算时间，可以实现热区的确定和显示的实时性。
基于上述的方法，本公开实施例提供的一种基于地理图像学确定人流热区 的装置，内部结构可如图8所示，包括：人流密度统计模块801、等高线绘制模块802、热区确定模块803。
人流密度统计模块801用于统计一段时间内区域中各坐标点的人流密度数据；
等高线绘制模块802用于将人流密度统计模块801统计的各坐标点的人流密度数据，作为各坐标点的高度数据后，根据各坐标点的高度数据运用地理图像学绘制所述区域内的等高线。等高线绘制模块802根据各坐标点的高度数据运用地理图像学绘制所述区域内的等高线的具体方法可参考上述图2所示的方法流程，此处不再赘述。
热区确定模块803用于将等高线绘制模块802绘制的等高线作为人流等密度线后，根据人流等密度线所圈范围确定所述区域中的人流热区。具体地，热区确定模块803可以选取热度大于设定热度值的人流等密度线所圈范围作为所述区域中的人流热区；或者选取人流密度高于设定阈值的人流等密度线所圈范围作为所述区域中的人流热区。
或者，在一些实施例中，热区确定模块803用于将热度大于设定热度值的人流等密度线所圈范围，选取为备选热区；将大于设定面积的备选热区，确定为所述区域中的人流热区。
进一步，本公开实施例提供的一种基于地理图像学确定人流热区的装置还可以包括：热区排序模块804、热区显示模块805。
热区排序模块804用于根据热度对确定的人流热区进行排序；
热区显示模块805用于根据热区排序模块804的排序结果，在显示界面中以不同颜色标示各人流热区。
图9为本公开实施例提供的一种基于地理图像学确定人流热区的示例装置900的硬件布置图。硬件布置900包括处理器906(例如，数字信号处理器(DSP)、中央处理单元(CPU)等)。处理器906可以是用于执行本文描述的流程的不同动作的单一处理单元或者是多个处理单元。布置900还可以包括用于从其他实体接收信号的输入单元902、以及用于向其他实体提供信号的输出单元904。输入单元902和输出单元904可以被布置为单一实体或者是分离的实体。
此外，在一些实施例中，输入单元902和输出单元904还可以包括供处理器906与外部通信的通信器，例如无线通信单元、有线通信单元等。无线通信单元可以是支持例如Wi-Fi、蓝牙、3GPP系列(包括例如GSM、GPRS、CDMA、WCDMA、CDMA2000、TD-SCDMA、LTE、LTE-A、5G NR等)、Wi-Max等协议的通信模块。有线通信单元可以是支持例如以太网、USB、光纤、xDSL等协议的通信模块。在一些实施例中，输入单元902和/或输出单元904也可以是与外部的通信器通信连接的接口。换言之，在这些实施例中，示例装置900自身可以不包括通信器，而是通过接口与外部通信器通信连接并实现相同或相似功能。
此外，布置900可以包括具有非易失性或易失性存储器形式的至少一个可读存储介质908，例如是电可擦除可编程只读存储器(EEPROM)、闪存、和/或硬盘驱动器。可读存储介质908包括计算机程序910，该计算机程序910包括代码/计算机可读指令，其在由布置900中的处理器906执行时使得硬件布置900和/或包括硬件布置900在内的设备可以执行例如上面结合图1～图7所描述的流程及其任何变形。
计算机程序910可被配置为具有例如计算机程序模块910A～910C架构的计算机程序代码。因此，布置900的计算机程序中的代码可包括：模块910A，用于基于一时间段内区域中各坐标点的人流密度数据来确定各坐标点在地理图像学意义下的高度数据；模块910B，用于根据高度数据，运用地理图像学来绘制区域内的等高线；以及模块910C，用于根据所绘制的等高线所圈范围来确定区域中的人流热区。
计算机程序模块实质上可以执行图1～图7中所示出的流程中的各个动作，以模拟装置800。换言之，当在处理器906中执行不同计算机程序模块时，它们可以对应于装置800中的不同单元或模块。
尽管上面结合图9所公开的实施例中的代码手段被实现为计算机程序模块，其在处理器906中执行时使得硬件布置900执行上面结合图1～图7所描述的动作，然而在备选实施例中，该代码手段中的至少一项可以至少被部分地实现为硬件电路。
处理器可以是单个CPU(中央处理单元)，但也可以包括两个或更多个处 理单元。例如，处理器可以包括通用微处理器、指令集处理器和/或相关芯片组和/或专用微处理器(例如，专用集成电路(ASIC))。处理器还可以包括用于缓存用途的板载存储器。计算机程序可以由连接到处理器的计算机程序产品来承载。计算机程序产品可以包括其上存储有计算机程序的计算机可读介质。例如，计算机程序产品可以是闪存、随机存取存储器(RAM)、只读存储器(ROM)、EEPROM，且上述计算机程序模块在备选实施例中可以用设备内的存储器的形式被分布到不同计算机程序产品中。
本公开实施例的技术方案中，将区域中各坐标点的人流密度数据，作为各坐标点的高度数据后，利用地理图像学中等高线计算的方法可以快速得到人流等密度线，而基于人流等密度线则可以确定热区。由于地理图像学计算等高线的算法简单、快速，因此，本公开技术方案计算量小，可以快速确定人流热区，从而实现热区的实时计算和显示。
本技术领域技术人员可以理解，本公开中已经讨论过的各种操作、方法、流程中的步骤、措施、方案可以被交替、更改、组合或删除。进一步地，具有本公开中已经讨论过的各种操作、方法、流程中的其他步骤、措施、方案也可以被交替、更改、重排、分解、组合或删除。进一步地，现有技术中的具有与本公开中公开的各种操作、方法、流程中的步骤、措施、方案也可以被交替、更改、重排、分解、组合或删除。
所属领域的普通技术人员应当理解：以上任何实施例的讨论仅为示例性的，并非旨在暗示本公开的范围(包括权利要求)被限于这些例子；在本公开的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，步骤可以以任意顺序实现，并存在如上所述的本公开的不同方面的许多其它变化，为了简明它们没有在细节中提供。因此，凡在本公开的精神和原则之内，所做的任何省略、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 (14)

  1. 一种计算机实现的基于地理图像学来确定人流热区的方法，包括：
    基于一时间段内区域中各坐标点的人流密度数据来确定各坐标点在地理图像学意义下的高度数据；
    根据所述高度数据，运用地理图像学来绘制所述区域内的等高线；以及
    根据所绘制的等高线所圈范围来确定所述区域中的人流热区。
  2. 根据权利要求1所述的方法，其中，基于一时间段内区域中各坐标点的人流密度数据来确定各坐标点在地理图像学意义下的高度数据的步骤包括：
    将各坐标点的人流密度数据直接作为相应坐标点的在地理图像学意义下的高度数据。
  3. 根据权利要求1所述的方法，其中，根据所绘制的等高线所圈范围来确定所述区域中的人流热区的步骤包括：
    将所绘制的等高线确定为人流等密度线；以及
    根据所述人流等密度线所圈范围来确定所述区域中的人流热区。
  4. 根据权利要求3所述的方法，其中，所述根据所述人流等密度线所圈范围来确定所述区域中的人流热区的步骤包括：
    选取热度大于设定热度值的人流等密度线所圈范围作为所述区域中的人流热区；或者
    选取人流密度高于设定阈值的人流等密度线所圈范围作为所述区域中的人流热区。
  5. 根据权利要求3所述的方法，其中，所述根据所述人流等密度线所圈范围来确定所述区域中的人流热区的步骤包括：
    将热度大于设定热度值的人流等密度线所圈范围，选取为备选热区；以及
    将大于设定面积的备选热区，确定为所述区域中的人流热区。
  6. 根据权利要求1-5任一所述的方法，还包括：
    根据热度对确定的人流热区进行排序；以及
    根据排序结果，在显示界面中以不同颜色标示各人流热区。
  7. 根据权利要求1-6任一所述的方法，其中，根据所述高度数据运用地理图像学来绘制所述区域内的等高线的步骤包括：
    对于所述区域中均匀划分的网格单元，将每个网格单元所对应的坐标点的高度数据与设定高度值进行比较；
    响应于一个网格单元所对应的坐标点的高度数据大于所述设定高度值，将该网格单元的左上角标黑；
    根据该网格单元四角的标黑情况，在该网格单元中绘制对应的轮廓线；
    由各网格单元中的轮廓线构成所述区域内高度标定为所述设定高度值的等高线；
    其中，所述设定高度值等于设定的人流密度值。
  8. 一种基于地理图像学来确定人流热区的装置，包括：
    处理器；
    存储器，存储指令，所述指令在由所述处理器执行时使得所述处理器：
    基于一时间段内区域中各坐标点的人流密度数据来确定各坐标点在地理图像学意义下的高度数据；
    根据所述高度数据，运用地理图像学来绘制所述区域内的等高线；以及
    根据所绘制的等高线所圈范围来确定所述区域中的人流热区。
  9. 根据权利要求8所述的装置，其中，所述指令在由所述处理器执行时还使得所述处理器：
    将各坐标点的人流密度数据直接作为相应坐标点的在地理图像学意义下的高度数据。
  10. 根据权利要求8所述的装置，其中，所述指令在由所述处理器执行时还使得所述处理器：
    将所绘制的等高线确定为人流等密度线；以及
    根据所述人流等密度线所圈范围来确定所述区域中的人流热区。
  11. 根据权利要求10所述的装置，其中，所述指令在由所述处理器执行时还使得所述处理器：
    选取热度大于设定热度值的人流等密度线所圈范围作为所述区域中的人流热区；或者
    选取人流密度高于设定阈值的人流等密度线所圈范围作为所述区域中的人流热区。
  12. 根据权利要求10所述的装置，其中，所述指令在由所述处理器执行时还使得所述处理嚣：
    将热度大于设定热度值的人流等密度线所圈范围，选取为备选热区；以及
    将大于设定面积的备选热区，确定为所述区域中的人流热区。
  13. 根据权利要求10-12任一所述的装置，其中，所述指令在由所述处理器执行时还使得所述处理器：
    根据热度对确定的人流热区进行排序；以及
    根据所述热区排序模块的排序结果，在显示界面中以不同颜色标示各人流热区。
  14. 一种存储指令的非暂时计算机可读存储介质，所述指令在由处理器执行时使所述处理器能够执行如权利要求1-7任一所述的方法。
PCT/CN2019/079900 2018-04-20 2019-03-27 基于地理图像学确定人流热区的方法和装置 WO2019201065A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/496,213 US11068714B2 (en) 2018-04-20 2019-03-27 Method and apparatus for determining hot zones of human flow based on cartography

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810359674.9 2018-04-20
CN201810359674.9A CN108564638B (zh) 2018-04-20 2018-04-20 一种基于地理图像学确定人流热区的方法和装置

Publications (1)

Publication Number Publication Date
WO2019201065A1 true WO2019201065A1 (zh) 2019-10-24

Family

ID=63535844

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/079900 WO2019201065A1 (zh) 2018-04-20 2019-03-27 基于地理图像学确定人流热区的方法和装置

Country Status (3)

Country Link
US (1) US11068714B2 (zh)
CN (1) CN108564638B (zh)
WO (1) WO2019201065A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113128299A (zh) * 2019-12-30 2021-07-16 深圳云天励飞技术有限公司 人流密度检测方法、装置、终端设备、服务器及存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108564638B (zh) 2018-04-20 2020-07-10 京东方科技集团股份有限公司 一种基于地理图像学确定人流热区的方法和装置
CN113486223B (zh) * 2021-06-07 2022-09-09 海南太美航空股份有限公司 一种航线显示方法、系统和电子设备
CN115237289B (zh) * 2022-07-01 2024-02-23 杭州涂鸦信息技术有限公司 热区范围确定方法、装置、设备及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103942854A (zh) * 2013-01-17 2014-07-23 新谊整合科技股份有限公司 能量输出控制系统与方法
CN107644218A (zh) * 2017-09-29 2018-01-30 重庆市智权之路科技有限公司 基于图像采集功能实现人流密集区域行为分析判断的工作方法
CN108564638A (zh) * 2018-04-20 2018-09-21 京东方科技集团股份有限公司 一种基于地理图像学确定人流热区的方法和装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5360989B2 (ja) * 2009-09-29 2013-12-04 株式会社日立ソリューションズ 地理情報生成システム及び地理情報生成方法
CN102254786B (zh) * 2010-05-20 2013-02-13 上海华虹Nec电子有限公司 芯片的局部图形密度的分析和检查方法
CN104200502B (zh) * 2014-08-28 2017-02-15 杭州师范大学 一种二维散点数据密度制图方法
CN106407466A (zh) * 2016-10-17 2017-02-15 山东浪潮商用系统有限公司 一种基于人流量的税务大厅热力图显示方法
CN106708955B (zh) * 2016-11-29 2020-01-14 浙江宇视科技有限公司 一种热力图生成方法及设备

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103942854A (zh) * 2013-01-17 2014-07-23 新谊整合科技股份有限公司 能量输出控制系统与方法
CN107644218A (zh) * 2017-09-29 2018-01-30 重庆市智权之路科技有限公司 基于图像采集功能实现人流密集区域行为分析判断的工作方法
CN108564638A (zh) * 2018-04-20 2018-09-21 京东方科技集团股份有限公司 一种基于地理图像学确定人流热区的方法和装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113128299A (zh) * 2019-12-30 2021-07-16 深圳云天励飞技术有限公司 人流密度检测方法、装置、终端设备、服务器及存储介质
CN113128299B (zh) * 2019-12-30 2024-06-11 深圳云天励飞技术有限公司 人流密度检测方法、装置、终端设备、服务器及存储介质

Also Published As

Publication number Publication date
US11068714B2 (en) 2021-07-20
CN108564638A (zh) 2018-09-21
US20200380256A1 (en) 2020-12-03
CN108564638B (zh) 2020-07-10

Similar Documents

Publication Publication Date Title
WO2019201065A1 (zh) 基于地理图像学确定人流热区的方法和装置
JP6871314B2 (ja) 物体検出方法、装置及び記憶媒体
Xu et al. Wheat ear counting using K-means clustering segmentation and convolutional neural network
WO2021051601A1 (zh) 利用Mask R-CNN选择检测框的方法及系统、电子装置及存储介质
CN113822247B (zh) 基于航拍影像的违章建筑识别方法及系统
CN112766302B (zh) 一种图像融合方法、装置、存储介质及电子装置
CN111209892A (zh) 一种基于卷积神经网络的人群密度及数量估计方法
TW201022708A (en) Method of change detection for building models
WO2020125057A1 (zh) 牲畜个数的识别方法及装置
CN111079518B (zh) 一种基于执法办案区场景下的倒地异常行为识别方法
CN105426863B (zh) 检测车道线的方法和装置
Dai et al. Building segmentation and outline extraction from UAV image-derived point clouds by a line growing algorithm
CN111209822A (zh) 一种热红外图像的人脸检测方法
CN115937439B (zh) 城市建筑三维模型的构建方法、装置及电子设备
US20190096066A1 (en) System and Method for Segmenting Out Multiple Body Parts
CN108229473A (zh) 车辆年检标签检测方法及装置
CN112036269A (zh) 跌倒检测方法、装置、计算机设备和存储介质
Xin et al. Three‐dimensional reconstruction of Vitis vinifera (L.) cvs Pinot Noir and Merlot grape bunch frameworks using a restricted reconstruction grammar based on the stochastic L‐system
CN113326925A (zh) 基于密度图回归的卷积神经网络的花量统计方法、系统、设备及介质
WO2021051382A1 (zh) 白平衡处理方法和设备、可移动平台、相机
CN114235815A (zh) 基于场景过滤的换流站户外电气设备表面缺陷检测方法
CN106960188B (zh) 天气图像分类方法及装置
CN113674205A (zh) 一种基于单目深度摄像头的人体测量的方法及系统
KR102260556B1 (ko) 전역 정보와 지역 정보 통합을 통한 딥러닝 기반 주차구획 검출 방법 및 장치
CN110619365B (zh) 一种落水检测方法

Legal Events

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

Ref document number: 19789209

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19789209

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19789209

Country of ref document: EP

Kind code of ref document: A1

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

Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 10.05.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19789209

Country of ref document: EP

Kind code of ref document: A1