WO2020233221A1 - 热力分析方法、装置和系统 - Google Patents

热力分析方法、装置和系统 Download PDF

Info

Publication number
WO2020233221A1
WO2020233221A1 PCT/CN2020/080781 CN2020080781W WO2020233221A1 WO 2020233221 A1 WO2020233221 A1 WO 2020233221A1 CN 2020080781 W CN2020080781 W CN 2020080781W WO 2020233221 A1 WO2020233221 A1 WO 2020233221A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
heat distribution
map
layout
target area
Prior art date
Application number
PCT/CN2020/080781
Other languages
English (en)
French (fr)
Inventor
吴江旭
张伟华
马事伟
石海龙
雍兴辉
胡淼枫
王璟璟
徐荣图
张洪光
孔磊锋
李凡
Original Assignee
北京京东尚科信息技术有限公司
北京京东世纪贸易有限公司
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 北京京东尚科信息技术有限公司, 北京京东世纪贸易有限公司 filed Critical 北京京东尚科信息技术有限公司
Publication of WO2020233221A1 publication Critical patent/WO2020233221A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Definitions

  • the present disclosure relates to the field of image processing technology, in particular to a thermal analysis method, device and system.
  • heat map data can be collected as an important basis for analyzing the popularity of customers' browsing areas and screening of popular shelves. According to the heat data, shelf adjustment and product display optimization can be carried out, which is helpful for intelligent decision-making in stores.
  • a thermal analysis method which includes: determining a legal heat distribution area and an illegal heat distribution area in a layout map of a target area; obtaining an initial heat distribution map of the target area; In the distribution map, the heat value located in the illegal heat distribution area in the layout map is moved to the corresponding position of the legal heat distribution area in the layout map, and the updated heat distribution map is obtained.
  • the thermal analysis method further includes adjusting one or more of the item distribution in the target area or the item inventory according to the updated thermal distribution map.
  • the thermal analysis method further includes: adjusting the distribution of items in the target area according to the updated thermal distribution map test, and obtaining the adjusted updated thermal distribution map; when the ratio of the updated thermal distribution map before and after the test exceeds a predetermined threshold In this case, adjust the item inventory in the target area according to the updated heat distribution map; in the case that the change ratio of the updated heat distribution map before and after the test does not exceed a predetermined threshold, adjust the item distribution in the target area according to demand.
  • determining the legal area of heat distribution and the illegal area of heat distribution in the layout map of the target area includes: obtaining the layout map of the target area; determining the area allowed to pass and the area not allowed to pass in the floor plan; Set the area that allows people to pass is the legal area of heat distribution, and the area that does not allow people to pass is the illegal area of heat distribution.
  • determining the areas that allow people to pass and the areas where people are not allowed to pass in the layout diagram includes: filling and inverting the binary layout diagram with flood water to obtain a flood water reversal map; Reverse the map and the binary layout map to obtain the item frame selection layout; according to the item frame selection layout, determine the area that allows people to pass and the area that is not allowed to pass.
  • determining the areas that allow people to pass and the areas that are not allowed to pass in the layout diagram further includes: selecting items in the layout map for an expansion operation; selecting the items after the expansion operation on the layout map for a corrosion operation, Obtain the updated item frame selection layout; according to the item frame selection layout, determine the areas allowed and not allowed to pass including: according to the updated item frame selection layout, determine the area where the items are placed and the area where the items are placed The enclosed area is the area where people are not allowed to pass, and the area surrounded by the area where no items are placed and where no items are placed is the area where people are allowed to pass.
  • determining the areas that allow people to pass and the areas where people are not allowed to pass in the layout diagram further includes: binarizing the layout diagram, wherein the background color of the binary layout diagram is the first predetermined Color, the non-base color part is the second predetermined color; doing flood filling and inverting includes: using the second predetermined color as flood filling; modifying the first predetermined color part to the second predetermined color, and changing the second predetermined color part Modify it to the first predetermined color; obtaining the item frame selection layout according to the flood reversal map and the binarized layout map includes: at least one of the second predetermined color in the flood reversal map or the binarized layout map Position, the item frame selection layout map is the second predetermined color, in the flood reversal map and the binarized layout map both the first predetermined color position, the item frame selection layout map is the first predetermined color; frame selection according to the item The layout diagram determines the area allowed to pass and the area not allowed to pass, including: the area of the second predetermined Color
  • moving the heat value located in the illegal area of heat distribution in the layout map to the corresponding position of the legal area of heat distribution in the layout diagram includes: determining a position where the heat value in the illegal area of heat distribution in the initial heat distribution map is non-zero Is an abnormal position; determine the nearest legal position corresponding to each abnormal position, where the nearest legal position is located in the legal thermal distribution area; accumulate the thermal value of each abnormal position in the corresponding nearest legal position.
  • obtaining the initial thermal distribution map of the target area includes: obtaining the surveillance video of the target area through the image acquisition device; detecting the position of the pedestrian in each frame of the surveillance video through the pedestrian detection and recognition algorithm; The number of people with a predetermined duration and the length of stay determine the initial heat distribution map of the target area.
  • acquiring the initial thermal distribution map of the target area further includes: mapping each detection area to the plane of the same target area according to the positional relationship of the detection areas of the multiple image acquisition devices.
  • the layout drawing of the target area includes a design drawing of the target area, a construction drawing or a scene drawing of the target area restored based on scanning.
  • a thermal analysis device including: an area determining unit configured to determine a legal heat distribution area and an illegal heat distribution area in a layout map of a target area; initial heat distribution acquisition The unit is configured to obtain the initial heat distribution map of the target area; the heat distribution acquisition unit is configured to move the heat value in the illegal heat distribution area in the layout map to the legal area of the heat distribution in the layout map according to the initial heat distribution map Corresponding location, get the updated heat distribution map.
  • the thermal analysis device further includes a thermal distribution application unit configured to adjust one or more of the item distribution in the target area or the inventory of the items according to the updated thermal distribution map.
  • the thermal analysis device further includes: a testing unit configured to test and adjust the distribution of items in the target area according to the updated thermal distribution map to obtain the adjusted updated thermal distribution map; the thermal distribution application unit is configured to update When the change ratio of the heat distribution map before and after the test exceeds the predetermined threshold, adjust the item inventory in the target area according to the updated heat distribution map; when the change ratio of the updated heat distribution map before and after the test does not exceed the predetermined threshold, according to demand Adjust the distribution of items in the target area.
  • a testing unit configured to test and adjust the distribution of items in the target area according to the updated thermal distribution map to obtain the adjusted updated thermal distribution map
  • the thermal distribution application unit is configured to update When the change ratio of the heat distribution map before and after the test exceeds the predetermined threshold, adjust the item inventory in the target area according to the updated heat distribution map; when the change ratio of the updated heat distribution map before and after the test does not exceed the predetermined threshold, according to demand Adjust the distribution of items in the target area.
  • a thermal analysis device including: a memory; and a processor coupled to the memory, and the processor is configured to execute any of the above thermal analysis based on instructions stored in the memory. Analytical method.
  • a computer-readable storage medium on which computer program instructions are stored, which, when executed by a processor, implement the steps of any of the above thermal analysis methods.
  • a thermal analysis system including: any of the above thermal analysis devices; and, an image acquisition device configured to monitor a target area and obtain surveillance video.
  • FIG. 1 is a flowchart of some embodiments of the thermal analysis method of the present disclosure.
  • FIG. 2 is a flowchart of other embodiments of the thermal analysis method of the present disclosure.
  • FIG. 3 is a flowchart of some embodiments of determining the legal area of heat distribution and the illegal area of heat distribution in the thermal analysis method of the present disclosure.
  • 4A to 4E are schematic diagrams of some embodiments for determining the legal area of heat distribution and the illegal area of heat distribution in the thermal analysis method of the present disclosure.
  • FIG. 5 is a flowchart of still other embodiments of the thermal analysis method of the present disclosure.
  • FIG. 6 is a schematic diagram of some embodiments of the thermal analysis device of the present disclosure.
  • FIG. 7 is a schematic diagram of other embodiments of the thermal analysis device of the present disclosure.
  • FIG. 8 is a schematic diagram of still other embodiments of the thermal analysis device of the present disclosure.
  • FIG. 9 is a schematic diagram of some embodiments of the thermal analysis system of the present disclosure.
  • AI Artificial Intelligence
  • the data collected through the above algorithms provide basic data support for store selection, location, pricing, and promotion decisions.
  • the quality of the collected data is critical to the store system that makes intelligent decisions based on the data.
  • the coordinate points reported by the computer vision algorithm can be directly mapped to the shop global map for drawing.
  • the reported coordinate points cannot be correctly mapped in a reasonable area at some time.
  • Many thermal coordinates are mapped to the containers, shelves, and exhibition stands, resulting in the thermal map. The presentation effect and credibility are greatly reduced.
  • FIG. 1 The flowchart of some embodiments of the thermal analysis method of the present disclosure is shown in FIG. 1 and includes steps 101-103.
  • an area with legal heat distribution and an area with illegal heat distribution are determined in the layout map of the target area.
  • the legal heat distribution area refers to the area that people can reach
  • the illegal heat distribution area refers to the area that cannot be reached by people. For example, the location where shelves are placed or the location that customers cannot enter is considered to be heat. Distribute illegal areas.
  • an initial heat distribution map of the target area is obtained.
  • the initial heat distribution map may be a heat distribution map collected by an image acquisition device such as a camera and analyzed by a computer vision algorithm.
  • step 101 and step 102 are irrelevant.
  • step 103 according to the initial heat distribution map, the heat value located in the illegal heat distribution area in the layout diagram is moved to the corresponding position of the legal heat distribution area in the layout diagram to obtain an updated heat distribution diagram.
  • the heat value of the illegal heat distribution area may be moved to the position of the legal heat distribution area that is closest to the current position in the layout.
  • the legal area of heat distribution and the illegal area of heat distribution can be obtained on the basis of the layout map of the target area, and then the collected initial heat distribution map can be corrected to rationalize the heat distribution map and improve the accuracy and reliability of thermal analysis. Reliability.
  • the commodity inventory can be adjusted according to the updated heat distribution map. For example, determine the items placed on the shelf closest to the position with the highest or higher heating value to increase the inventory of that type of item; determine the items placed on the shelf closest to the position with the lowest or lower heating value to reduce the item In order to make full use of the shelf by using the popularity of the product, it can improve the utilization rate of space and the rate of return.
  • the distribution of items can be adjusted according to the updated heat distribution map. For example, items with higher profits are placed on the shelves closest to the position with the highest or higher heat value to reduce the profits. Lower items are placed on the shelf closest to the position with the lowest or lower heating value, thereby using the popularity of the area to improve the rationality of the layout and increase the profit margin.
  • FIG. 2 The flowchart of other embodiments of the thermal analysis method of the present disclosure is shown in FIG. 2.
  • step 201 a legal heat distribution area and an illegal heat distribution area are determined in the layout map of the target area.
  • step 202 an initial heat distribution map of the target area is acquired.
  • step 203 according to the initial heat distribution map, the heat value located in the illegal heat distribution area in the layout diagram is moved to the corresponding position of the legal heat distribution area in the layout diagram to obtain an updated heat distribution diagram.
  • step 204 the item distribution in the target area is adjusted according to the updated heat distribution map test, and the adjusted updated heat distribution map is obtained.
  • the adjustment of the distribution of items may include: exchanging items on the shelf closest to the position with the highest or higher heating value with the items on the shelf closest to the position with the lowest or lower heating value, or Randomly disrupt the arrangement of items.
  • step 205 it is determined whether the change ratio of the updated thermal distribution map before and after the test exceeds a predetermined threshold.
  • the heating value of each point in the updated thermal distribution map before and after the test can be compared to determine the ratio of the number of points that have changed, and compared with a predetermined threshold. If the change ratio of the updated heat distribution map before and after the test is greater than the predetermined threshold, step 206 is executed; if the change ratio of the updated heat distribution map before and after the test is not greater than the predetermined threshold, step 207 is executed.
  • step 206 since the updated heat distribution map has a large change, it indicates that the deviation of the heat distribution is more caused by the item itself, and the item inventory in the target area is adjusted according to the updated heat distribution map.
  • step 207 since the update of the thermal distribution map does not change much, it indicates that the deviation of the thermal distribution is more caused by the position, and the distribution of the items in the target area is adjusted according to the demand.
  • the design drawings such as CAD( Computer Aided Design (Computer Aided Design) drawings
  • construction drawings or scene graphs of the target area recovered based on scan analysis to determine the areas that allow people to pass and areas that are not allowed to pass.
  • FIGS. 4A to 4E the schematic diagrams in each step can be shown in FIGS. 4A to 4E, where FIGS. 4A to 4E Unclear text or scattered color blocks are the true state of the processed image and the effect of the processed image in the process, not the unclearness of the image itself. Unclear words and lines do not affect the technical solution of the present disclosure.
  • the binarized layout map is filled with flood water and inverted to obtain a flood inversion map.
  • binarization can be performed first, the background color is the first predetermined color, and the non-background color part is the second predetermined color, as shown in FIG. 4A, the first predetermined color The color is black, and the second predetermined color is white.
  • the second predetermined color is used for flood filling, as shown in FIG. 4B.
  • performing the inversion processing includes modifying the first predetermined color portion to the second predetermined color, and modifying the second predetermined color portion to the first predetermined color.
  • the item frame selection layout diagram is obtained according to the flood reversal diagram and the binarized layout diagram.
  • at least one of the positions of the second predetermined color can be set in the flood reversal map or the binarized layout map, and the item frame selection layout map is the second predetermined color.
  • the binarized layout diagram are the positions of the first predetermined color, and the item frame selection layout diagram is the first predetermined color.
  • the position of the second predetermined color in the flood inversion map and the binarized layout map can be set to 1, and the position of the first predetermined color is 0, and the two images are ORed, and the result of the operation is 1.
  • the position of is the second predetermined color, and the position where the calculation result is 0 is the first predetermined color.
  • the area of the second predetermined color may be set as an area that does not allow people to pass through, that is, an area where heat distribution is illegal, and the area of the first predetermined color is an area that allows people to pass, that is, an area where heat distribution is legal.
  • step 303 and step 304 may also be performed.
  • step 303 an expansion operation is performed on the item frame selection layout, as shown in FIG. 4D.
  • the expansion coefficient may be preset.
  • step 304 the item frame selection layout map after the expansion operation is corroded to restore the size of the item before expansion, and the updated item frame selection layout map is obtained, as shown in FIG. 4E.
  • step 305 according to the updated item selection layout, it is determined that the area where the items are placed and the area surrounded by the area where the items are placed are areas that are not allowed to pass through, and the items are not placed and are not surrounded by the area where the items are placed. The area where people are allowed to pass.
  • the illegal heat distribution area and the legal heat distribution area can be obtained through the calculation operation of the layout map, so that the initial heat distribution map can be corrected, and the updated heat distribution map can be obtained, which improves the credibility of the heat distribution map. At the same time, it also improves the accuracy and efficiency of correction.
  • FIG. 5 The flowchart of other embodiments of the thermal analysis method of the present disclosure is shown in FIG. 5.
  • the surveillance video of the target area is acquired through the image acquisition device.
  • the surveillance video may be collected by one or more cameras distributed in the target area.
  • step 502 the position of the pedestrian in each frame of the surveillance video is detected by a pedestrian detection and recognition algorithm.
  • the position of the image acquisition device and the relationship with the coordinates of the target area can be calibrated in advance, so as to improve the accuracy of the initial thermal distribution map as much as possible.
  • the initial heat distribution map of the target area is determined according to the number of people who stay at each position for more than a predetermined time and the stay time.
  • the surveillance video can be disassembled into picture frames, the number of people appearing at each position in the picture frame, and the number of picture frames where people appearing at each position can be determined, and accumulated, so as to determine the number of people and stay time. Collect the heat distribution.
  • the position relationship is determined to realize image stitching, and for the overlapping part, only the monitoring image based on the overlapping part collected by one camera is used, or for the overlapping part, all the heat in the monitoring image collected by the camera that can collect the overlapping part is used The value is averaged to further improve accuracy.
  • step 504 an area with legal heat distribution and an area with illegal heat distribution are determined in the layout map of the target area.
  • any one of the methods mentioned above may be used to determine the legal area of heat distribution and the illegal area of heat distribution.
  • step 505 it is determined that a position with a non-zero heat value in an area with an illegal heat distribution in the initial heat distribution map is an abnormal position.
  • the pixel value of the result of the diagram can be output to form a two-dimensional matrix.
  • the value of each element of the array Represents whether it is in a closed area. For example, black (the first predetermined color) is 0, which means that the heat distribution is legal in an unclosed area; white (the second predetermined color) is 255, which means it is a closed area, which is an illegal heat distribution.
  • Each point on the layout map is marked with 0 or 255. Assuming that the coordinate of a reported non-zero thermal value is (x, y), substitute the x and y of this coordinate into the mapping mask matrix. If the obtained value is 0, it means that the mapping coordinate is reasonable and the thermal point is drawn directly; if the obtained value is 255, it indicates that the mapping coordinate is unreasonable.
  • step 506 the nearest legal position corresponding to each abnormal position is determined.
  • the point with the closest Euclidean distance from the abnormal location to the legal heat distribution area can be calculated, that is, its corresponding nearest legal position.
  • the heating value of each abnormal position is accumulated in the corresponding nearest legal position.
  • the thermal value of each abnormal position corresponding to the nearest legal position is accumulated in the nearest legal position.
  • the Euclidean algorithm can be used to find a point (x1, y1) with the nearest value of 0 on the mapping mask matrix, and the (x1, y1) coordinates of this point can be returned to replace x and y.
  • the hot spot is (x1, y1).
  • FIG. 6 A schematic diagram of some embodiments of the thermal analysis device of the present disclosure is shown in FIG. 6.
  • the area determining unit 601 can determine the area with legal heat distribution and the area with illegal heat distribution in the layout map of the target area.
  • the area with legal heat distribution refers to an area that can be reached by humans
  • the area with illegal heat distribution refers to an area that cannot be reached by humans.
  • the initial heat distribution acquisition unit 602 can acquire the initial heat distribution map of the target area.
  • the initial heat distribution map may be a heat distribution map collected by an image acquisition device such as a camera and analyzed by a computer vision algorithm.
  • the heat distribution obtaining unit 603 can move the heat value located in the illegal heat distribution area in the layout map to the corresponding position of the legal heat distribution area in the layout map to obtain an updated heat distribution map.
  • the heat value of the illegal heat distribution area may be moved to the position of the legal heat distribution area that is closest to the current position in the layout.
  • Such a device can obtain the legal heat distribution area and the illegal heat distribution area on the basis of the target area layout map, and then correct the collected initial heat distribution map to rationalize the heat distribution map and improve the accuracy of thermal analysis.
  • the thermal analysis device may further include a thermal distribution application unit 604, which can adjust the commodity inventory according to the updated thermal distribution map, for example, determine the shelf closest to the position with the highest or higher thermal value. Place items to increase the inventory of that type of item; determine the items placed on the shelf closest to the position with the lowest or lower heating value, and reduce the inventory of this type of item, so as to use the popularity of the product to realize the full shelf Utilize, improve space utilization.
  • a thermal distribution application unit 604 can adjust the commodity inventory according to the updated thermal distribution map, for example, determine the shelf closest to the position with the highest or higher thermal value. Place items to increase the inventory of that type of item; determine the items placed on the shelf closest to the position with the lowest or lower heating value, and reduce the inventory of this type of item, so as to use the popularity of the product to realize the full shelf Utilize, improve space utilization.
  • the heat distribution application unit 604 can adjust the distribution of items according to the updated heat distribution map. For example, placing items with higher profits on the shelves closest to the position with the highest or higher heat value will reduce the profits. The items are placed on the shelf closest to the position with the lowest or lower heating value, so as to use the popularity of the area to improve the rationality of the layout and increase the profit.
  • the thermal analysis device may further include a testing unit 605, capable of adjusting the distribution of items in the target area according to the updated thermal distribution map test, and activating the area determining unit 601, the initial thermal distribution obtaining unit 602, and the thermal distribution obtaining unit 603 to obtain Update the heat distribution map.
  • the testing unit 605 can compare the updated thermal distribution map obtained by the test with the updated thermal distribution map before the test, and determine the ratio of changes before and after the test. In the case that the change ratio is greater than the predetermined threshold, the thermal distribution application unit adjusts the item inventory in the target area according to the updated thermal distribution map, and when the change ratio is not greater than the predetermined threshold, the thermal distribution application unit adjusts the item distribution in the target area according to demand .
  • Such a thermal analysis device can analyze the influencing factors of thermal distribution by means of testing, thereby specifying corresponding strategies, improving the accuracy of the application of thermal distribution, and improving the effective use of the limited target area space.
  • the thermal analysis device includes a memory 701 and a processor 702.
  • the memory 701 may be a magnetic disk, flash memory or any other non-volatile storage medium.
  • the memory is used to store the instructions in the corresponding embodiment of the above thermal analysis method.
  • the processor 702 is coupled to the memory 701 and can be implemented as one or more integrated circuits, such as a microprocessor or a microcontroller.
  • the processor 702 is used to execute instructions stored in the memory, which can rationalize the thermal distribution map and improve the accuracy of thermal analysis.
  • the thermal analysis device 800 includes a memory 801 and a processor 802.
  • the processor 802 is coupled to the memory 801 through the BUS bus 803.
  • the thermal analysis device 800 can also be connected to an external storage device 805 through a storage interface 804 to call external data, and can also be connected to a network or another computer system (not shown) through a network interface 806. No more detailed introduction here.
  • the data instructions are stored in the memory, and the above instructions are processed by the processor, which can rationalize the thermal distribution map and improve the accuracy of thermal analysis.
  • a computer-readable storage medium has computer program instructions stored thereon, which, when executed by a processor, implement the steps of the method in the corresponding embodiment of the thermal analysis method.
  • the embodiments of the present disclosure may be provided as methods, devices, or computer program products. Therefore, the present disclosure may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware.
  • the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. .
  • FIG. 9 A schematic diagram of some embodiments of the thermal analysis system of the present disclosure is shown in FIG. 9.
  • the thermal analysis device 91 may be any of the above.
  • the image acquisition device 92 can monitor the target area and obtain surveillance video, such as a camera that monitors the target area. In some embodiments, there may be one or more image acquisition devices 92.
  • Such a thermal analysis system can collect surveillance videos and obtain an initial thermal distribution map, obtain the legal thermal distribution area and the illegal thermal distribution area based on the target area layout map, and then correct the collected initial thermal distribution map to make the thermal distribution map Rationalize and improve the accuracy of thermal analysis.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.
  • the method and apparatus of the present disclosure may be implemented in many ways.
  • the method and apparatus of the present disclosure can be implemented by software, hardware, firmware or any combination of software, hardware, and firmware.
  • the above-mentioned order of the steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated.
  • the present disclosure may also be implemented as programs recorded in a recording medium, and these programs include machine-readable instructions for implementing the method according to the present disclosure.
  • the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Water Supply & Treatment (AREA)
  • Signal Processing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Human Resources & Organizations (AREA)
  • General Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Marketing (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Image Analysis (AREA)

Abstract

一种热力分析方法、装置和系统，涉及图像处理技术领域。所述热力分析方法包括：在目标区域的布局图中确定热力分布合法区域和热力分布非法区域（101）；获取目标区域的初始热力分布图（102）；根据初始热力分布图，将位于布局图中热力分布非法区域的热力值移至布局图中热力分布合法区域的对应位置，获取更新热力分布图（103）。通过这样的方法，能够在目标区域布局图的基础上得到热力分布合法区域和热力分布非法区域，进而对采集的初始热力分布图进行校正，使热力分布图合理化，提高热力分析的准确度和可信度。

Description

热力分析方法、装置和系统
相关申请的交叉引用
本申请是以CN申请号为201910427547.2，申请日为2019年5月22日的申请为基础，并主张其优先权，该CN申请的公开内容在此作为整体引入本申请中。
技术领域
本公开涉及图像处理技术领域，特别是一种热力分析方法、装置和系统。
背景技术
在互联网时代，数据是所有应用的基础，线上用户可以根据用户的浏览历史路径、页面停留时长、搜索行为、点击次数、加购物车行为、关注、收藏、交易等数据做智能决策优化。
针对线下场景，可以采集热力图数据，作为分析顾客浏览区域热度和热门货架筛选的重要依据，根据热力数据可以进行货架调整和商品陈列优化，有助于门店智能决策。
发明内容
根据本公开的一些实施例的一个方面，提出一种热力分析方法，包括：在目标区域的布局图中确定热力分布合法区域和热力分布非法区域；获取目标区域的初始热力分布图；根据初始热力分布图，将位于布局图中热力分布非法区域的热力值移至布局图中热力分布合法区域的对应位置，获取更新热力分布图。
在一些实施例中，热力分析方法还包括根据更新热力分布图调整目标区域的物品分布，或物品库存量中的一项或多项。
在一些实施例中，热力分析方法还包括：根据更新热力分布图测试调整目标区域的物品分布，并获取调整后的更新热力分布图；在更新热力分布图在测试前后的变化比例超过预定门限的情况下，根据更新热力分布图调整目标区域的物品库存量；在更新热力分布图在测试前后的变化比例未超过预定门限的情况下，根据需求调整目标区域的物品分布。
在一些实施例中，在目标区域的布局图中确定热力分布合法区域和热力分布非法 区域包括：获取目标区域的布局图；在布局图中确定允许人通过的区域和不允许人通过的区域；设置允许人通过的区域为热力分布合法区域，不允许人通过的区域为热力分布非法区域。
在一些实施例中，在布局图中确定允许人通过的区域和不允许人通过的区域包括：将二值化的布局图做漫水填充并反转，获取漫水反转图；根据漫水反转图与二值化的布局图获取物品框选布局图；根据物品框选布局图确定允许人通过的区域和不允许人通过的区域。
在一些实施例中，在布局图中确定允许人通过的区域和不允许人通过的区域还包括：将物品框选布局图做膨胀操作；将膨胀操作后的物品框选布局图做腐蚀操作，获取更新物品框选布局图；根据物品框选布局图确定允许人通过的区域和不允许人通过的区域包括：根据更新物品框选布局图，确定摆放物品的区域和被摆放物品的区域包围的区域为不允许人通过的区域，未摆放物品且未被摆放物品的区域包围的区域为允许人通过的区域。
在一些实施例中，在布局图中确定允许人通过的区域和不允许人通过的区域还包括：将布局图做二值化处理，其中，二值化的布局图的底色为第一预定颜色，非底色部分为第二预定颜色；做漫水填充并反转包括：采用第二预定颜色做漫水填充；将第一预定颜色部分修改为第二预定颜色，将第二预定颜色部分修改为第一预定颜色；根据漫水反转图与二值化的布局图获取物品框选布局图包括：在漫水反转图或二值化的布局图中至少一个为第二预定色的位置，物品框选布局图为第二预定色，在漫水反转图和二值化的布局图中均第一预定色的位置，物品框选布局图为第一预定色；根据物品框选布局图确定允许人通过的区域和不允许人通过的区域包括：第二预定色的区域为不允许人通过的区域，第一预定色的区域为允许人通过的区域。
在一些实施例中，将位于布局图中热力分布非法区域的热力值移至布局图中热力分布合法区域的对应位置包括：确定初始热力分布图中位于热力分布非法区域的热力值非0的位置为异常位置；确定各个异常位置对应的最近合法位置，其中，最近合法位置位于热力分布合法区域；将各个异常位置的热力值累积在对应的最近合法位置。
在一些实施例中，获取目标区域的初始热力分布图包括：通过图像采集设备获取目标区域的监控视频；通过行人检测识别算法检测监控视频的各帧图像中行人的位置；根据在各个位置停留超过预定时长的人的数量和停留的时长确定目标区域的初始热力分布图。
在一些实施例中，获取目标区域的初始热力分布图还包括：根据多个图像采集设备的探测区域的位置关系，将各个探测区域映射到同一个目标区域的平面中。
在一些实施例中，目标区域的布局图包括目标区域的设计图，施工图或基于扫描恢复的目标区域的场景图。
根据本公开的另一些实施例的一个方面，提出一种热力分析装置，包括：区域确定单元，被配置为在目标区域的布局图中确定热力分布合法区域和热力分布非法区域；初始热力分布获取单元，被配置为获取目标区域的初始热力分布图；热力分布获取单元，被配置为根据初始热力分布图，将位于布局图中热力分布非法区域的热力值移至布局图中热力分布合法区域的对应位置，获取更新热力分布图。
在一些实施例中，热力分析装置还包括热力分布应用单元，被配置为执行根据更新热力分布图调整目标区域的物品分布，或物品库存量中的一项或多项。
在一些实施例中，热力分析装置还包括：测试单元，被配置为根据更新热力分布图测试调整目标区域的物品分布，获取调整后的更新热力分布图；热力分布应用单元，被配置为在更新热力分布图在测试前后的变化比例超过预定门限的情况下，根据更新热力分布图调整目标区域的物品库存量；在更新热力分布图在测试前后的变化比例未超过预定门限的情况下，根据需求调整目标区域的物品分布。
根据本公开的又一些实施例的一个方面，提出一种热力分析装置，包括：存储器；以及耦接至存储器的处理器，处理器被配置为基于存储在存储器的指令执行上文中任意一种热力分析方法。
根据本公开的再一些实施例的一个方面，提出一种计算机可读存储介质，其上存储有计算机程序指令，该指令被处理器执行时实现上文中任意一种热力分析方法的步骤。
另外，根据本公开的一些实施例的一个方面，提出一种热力分析系统，包括：上文中任意一种热力分析装置；和，图像采集设备，被配置为监控目标区域，获取监控视频。
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为本公开的热力分析方法的一些实施例的流程图。
图2为本公开的热力分析方法的另一些实施例的流程图。
图3为本公开的热力分析方法中确定热力分布合法区域和热力分布非法区域的一些实施例的流程图。
图4A～4E为本公开的热力分析方法中确定热力分布合法区域和热力分布非法区域的一些实施例的示意图。
图5为本公开的热力分析方法的又一些实施例的流程图。
图6为本公开的热力分析装置的一些实施例的示意图。
图7为本公开的热力分析装置的另一些实施例的示意图。
图8为本公开的热力分析装置的又一些实施例的示意图。
图9为本公开的热力分析系统的一些实施例的示意图。
具体实施方式
下面通过附图和实施例，对本公开的技术方案做进一步的详细描述。
在线下零售场景下，通过AI(Artificial Intelligence，人工智能)算法对线下门店做进店客流人群画像，顾客轨迹跟踪，人群热力区域分布的数据进行收集分析。通过以上算法采集的数据对店铺的选品，选址，定价，促销等决策进行基础数据支撑。这些采集数据的质量对于依据数据做智能决策的门店系统至关重要。
在热力图坐标映射时在线下门店的店铺全局热力图上做坐标映射时，可以直接把计算机视觉算法上报的坐标点映射到店铺的全局图上进行绘制。但是，由于行人检测算法中视觉误差或运算误差带来的影响，上报坐标点在某些时候不能正确的映射在一个合理的区域，很多热力坐标映射到货柜，货架，展台上，导致热力图的呈现效果和可信度都大大降低。
本公开的热力分析方法的一些实施例的流程图如图1所示，包括步骤101～103。
在步骤101中，在目标区域的布局图中确定热力分布合法区域和热力分布非法区域。在一些实施例中，热力分布合法区域指人能够到达的区域，热力分布非法区域指人不能够到达的区域，例如，摆放了货架的位置，或围起来顾客不可以进入的位置即属于热力分布非法区域。
在步骤102中，获取目标区域的初始热力分布图。在一些实施例中，初始热力分布图可以为通过摄像头等图像采集设备采集，并通过计算机视觉算法分析得到的热力 分布图。
在一些实施例中，步骤101和步骤102的执行顺序不分前后。
在步骤103中，根据初始热力分布图，将位于布局图中热力分布非法区域的热力值移至布局图中热力分布合法区域的对应位置，获取更新热力分布图。在一些实施例中，可以将热力分布非法区域的热力值移至布局图中与当前位置距离最近的热力分布合法区域的位置。
通过这样的方法，能够在目标区域布局图的基础上得到热力分布合法区域和热力分布非法区域，进而对采集的初始热力分布图进行校正，使热力分布图合理化，提高热力分析的准确度和可信度。
在一些实施例中，在获得更新热力分布图后，可以根据更新热力分布图调整商品库存。例如，确定离热力值最高或较高的位置最近的货架上放置的物品，提高该种物品的库存量；确定离热力值最低或较低的位置最近的货架上放置的物品，降低该种物品的库存量，从而利用商品的受欢迎程度实现对货架的充分利用，提高空间的利用率和收益率。
在一些实施例中，在获得更新热力分布图后，可以根据更新热力分布图调整物品分布，例如，将利润更高的物品放置在离热力值最高或较高的位置最近的货架上，将利润较低的物品放置在离热力值最低或较低的位置最近的货架上，从而利用区域的受欢迎程度提高布置的合理性，提高利润率。
本公开的热力分析方法的另一些实施例的流程图如图2所示。
在步骤201中，在目标区域的布局图中确定热力分布合法区域和热力分布非法区域。
在步骤202中，获取目标区域的初始热力分布图。
在步骤203中，根据初始热力分布图，将位于布局图中热力分布非法区域的热力值移至布局图中热力分布合法区域的对应位置，获取更新热力分布图。
在步骤204中，根据更新热力分布图测试调整目标区域的物品分布，并获取调整后的更新热力分布图。在一些实施例中，对物品分布的调整可以包括：将离热力值最高或较高的位置最近的货架上的物品与离热力值最低或较低的位置最近的货架上的物品交换，或可以随机打乱物品排布。
在步骤205中，判断更新热力分布图在测试前后的变化比例是否超过预定门限。在一些实施例中，可以将测试前后的更新热力分布图各个点的热力值进行比较，确定 发生变化的点的数量比例，与预定门限相比较。若更新热力分布图在测试前后的变化比例大于预定门限，则执行步骤206；若更新热力分布图在测试前后的变化比例不大于预定门限，则执行步骤207。
在步骤206中，由于更新热力分布图的变化大，因此说明热力分布的偏差更多是由物品本身引起的，根据更新热力分布图调整目标区域的物品库存量。
在步骤207中，由于更新热力分布图的变化不大，因此说明热力分布的偏差更多是由位置引起的，根据需求调整目标区域的物品分布。
通过这样的方法，能够利用测试的方式分析热力分布的影响因素，从而指定对应的策略，提高对热力分布应用的准确度，进而提高对有限的目标区域空间的有效利用。
在一些实施例中，由于目标区域中会存在位置固定的物体，如货架区域，也存在虽然没有安放物品，但由于设计阻挡的问题使顾客无法进入的区域，因此要在设计图(如CAD(Computer Aided Design,计算机辅助设计)图)、施工图或基于扫描恢复的目标区域场景图中分析确定允许人通过的区域和不允许人通过的区域。本公开的热力分析方法中确定热力分布合法区域和热力分布非法区域的一些实施例的流程图如图3所示，各个步骤中的示意图可以如图4A～4E所示，其中图4A～4E中不清楚的文字或零散的色块为对被处理的图像的真实状态，以及被处理图像在处理过程中产生的效果，并非图像本身的不清楚。不清楚的文字和线条不影响本公开的技术方案。
在步骤301中，将二值化的布局图做漫水填充并反转，获取漫水反转图。在一些实施例中，对于非二值化的布局图，可以先做二值化处理，底色为第一预定颜色，非底色部分为第二预定颜色，如图4A所示，第一预定颜色为黑色，第二预定颜色为白色。在获得二值化的布局图后，采用第二预定颜色做漫水填充，如图4B所示。进而如图4C所示，做反转处理，包括将第一预定颜色部分修改为第二预定颜色，将第二预定颜色部分修改为第一预定颜色。
在步骤302中，根据漫水反转图与二值化的布局图获取物品框选布局图。在一些实施例中，可以设定在漫水反转图或二值化的布局图中至少一个为第二预定颜色的位置，物品框选布局图为第二预定颜色，在漫水反转图和二值化的布局图中均第一预定颜色的位置，物品框选布局图为第一预定颜色。在一些实施例中，可以设置漫水反转图和二值化的布局图中第二预定颜色的位置为1，第一预定颜色的位置为0，将两图做或运算，运算结果为1的位置为第二预定颜色，运算结果为0的位置为第一预定颜色。
在一些实施例中，可以设定第二预定色的区域为不允许人通过的区域，即热力分布非法区域，第一预定色的区域为允许人通过的区域，即热力分布合法区域。
在一些实施例中，为提高准确性，避免噪点、小区域的影响，还可以执行步骤303和步骤304。
在步骤303中，将物品框选布局图做膨胀操作，如图4D所示。在一些实施例中，可以预设膨胀系数。
在步骤304中，将膨胀操作后的物品框选布局图做腐蚀操作，使物品还原膨胀之前的尺寸，获取更新物品框选布局图，如图4E所示。
通过膨胀和腐蚀操作去除了图中的文字、不规则区域等因素形成的非法离散点，提高了准确度。
在步骤305中，根据更新物品框选布局图，确定摆放物品的区域和被摆放物品的区域包围的区域为不允许人通过的区域，未摆放物品且未被摆放物品的区域包围的区域为允许人通过的区域。
通过这样的方法，通过对布局图的运算操作能够得到热力分布非法区域和热力分布合法区域，以便于对初始热力分布图进行矫正，得到更新后的热力分布图，在提高热力分布图的可信度的同时，也提高了矫正的准确度和效率。
本公开的热力分析方法的又一些实施例的流程图如图5所示。
在步骤501中，通过图像采集设备获取目标区域的监控视频。在一些实施例中，监控视频可以由一个或多个分布在目标区域的摄像头采集。
在步骤502中，通过行人检测识别算法检测监控视频的各帧图像中行人的位置。在一些实施例中，可以预先标定图像采集设备的位置、与目标区域坐标的关系等，从而尽可能提高初始热力分布图的准确度。
在步骤503中，根据在各个位置停留超过预定时长的人的数量和停留的时长确定目标区域的初始热力分布图。在一些实施例中，可以将监控视频拆解成图片帧，确定图片帧中各个位置出现的人的数量，以及确定各个位置出现人的图片帧的数量，进行累计，从而从人数、停留时间两方面采集热力分布情况。
在一些实施例中，在存在多个摄像头的情况下，为实现图像的拼接，且避免对采集重叠区域的重复统计，需要预先通过监控图像的区域和尺寸，结合目标区域的实际情况进行图像间位置关系的确定，实现图像拼接，且对于重叠部分，只采用基于一个摄像头采集的重叠部分的监控图像，或对于该重叠部分，将全部能采集到该重叠部分 的摄像头采集的监控图像中的热力值做取平均操作，从而进一步提高准确度。
在步骤504中，在目标区域的布局图中确定热力分布合法区域和热力分布非法区域。在一些实施例中，可以采用上文中提到的任意一种方式确定热力分布合法区域和热力分布非法区域。
在步骤505中，确定初始热力分布图中位于热力分布非法区域的热力值非0的位置为异常位置。
在一些实施例中，在步骤504中得到物品框选布局图或更新物品框选布局图后，可以对该图的结果进行像素值的输出，形成一个二维矩阵，该数组每个元素的值代表是否在封闭区域内，如黑色(第一预定颜色)为0，表示在非封闭区域，热力分布合法区域；白色(第二预定颜色)为255，表示为封闭区域，为热力分布非法区域。对布局图上每个点均用0或255标识，假设某个上报的非0热力值的坐标为(x,y)，把这个坐标的x和y代入到映射掩码矩阵中。如果得到值为0，表示则表示该映射坐标合理，直接绘制该热力点；如果得到值为255，则表示该映射坐标不合理。
在步骤506中，确定各个异常位置对应的最近合法位置。在一些实施例中，可以计算异常位置到热力分布合法区域的欧式距离最近的点，即为其对应的最近合法位置。
在步骤507中，将各个异常位置的热力值累积在对应的最近合法位置。在一些实施例中，对于不同异常位置对应相同最近合法位置的情况，将对应该最近合法位置的各个异常位置的热力值均累计在该最近合法位置。在一些实施例中，可以在映射掩码矩阵上通过欧式算法寻找一个最近的值为0的点(x1,y1)，并把这个点的(x1,y1)坐标返回替换x和y，绘制的热力点是(x1,y1)。
通过这样的方法，能够得到合理的热力分布数据，甚至能对遮挡了图像采集的部分的热力分布实现合理预测，方便为后续的智能决策提供准确的数据支撑，进而提高决策的准确度。
本公开的热力分析装置的一些实施例的示意图如图6所示。
区域确定单元601能够在目标区域的布局图中确定热力分布合法区域和热力分布非法区域。在一些实施例中，热力分布合法区域指人能够到达的区域，热力分布非法区域指人不能够到达的区域。
初始热力分布获取单元602能够获取目标区域的初始热力分布图。在一些实施例中，初始热力分布图可以为通过摄像头等图像采集设备采集，并通过计算机视觉算法 分析得到的热力分布图。
热力分布获取单元603能够根据初始热力分布图，将位于布局图中热力分布非法区域的热力值移至布局图中热力分布合法区域的对应位置，获取更新热力分布图。在一些实施例中，可以将热力分布非法区域的热力值移至布局图中与当前位置距离最近的热力分布合法区域的位置。
这样的装置能够在目标区域布局图的基础上得到热力分布合法区域和热力分布非法区域，进而对采集的初始热力分布图进行校正，使热力分布图合理化，提高热力分析的准确度。
在一些实施例中，如图6所示，热力分析装置还可以包括热力分布应用单元604，能够根据更新热力分布图调整商品库存，例如，确定离热力值最高或较高的位置最近的货架上放置的物品，提高该种物品的库存量；确定离热力值最低或较低的位置最近的货架上放置的物品，降低该种物品的库存量，从而利用商品的受欢迎程度实现对货架的充分利用，提高空间的利用率。
在一些实施例中，热力分布应用单元604，能够根据更新热力分布图调整物品分布，例如，将利润更高的物品放置在离热力值最高或较高的位置最近的货架上，将利润较低的物品放置在离热力值最低或较低的位置最近的货架上，从而利用区域的受欢迎程度提高布置的合理性，提高利润。
在一些实施例中，热力分析装置还可以包括测试单元605，能够根据更新热力分布图测试调整目标区域的物品分布，并激活区域确定单元601、初始热力分布获取单元602和热力分布获取单元603获取更新热力分布图。测试单元605能够将测试得到的更新热力分布图与测试前的更新热力分布图进行比较，确定测试前后的变化比例。在变化比例大于预定门限的情况下，热力分布应用单元根据更新热力分布图调整目标区域的物品库存量，在变化比例不大于预定门限的情况下，热力分布应用单元根据需求调整目标区域的物品分布。
这样的热力分析装置能够利用测试的方式分析热力分布的影响因素，从而指定对应的策略，提高对热力分布应用的准确度，进而提高对有限的目标区域空间的有效利用。
本公开热力分析装置的一个实施例的结构示意图如图7所示。热力分析装置包括存储器701和处理器702。其中：存储器701可以是磁盘、闪存或其它任何非易失性存储介质。存储器用于存储上文中热力分析方法的对应实施例中的指令。处理器702 耦接至存储器701，可以作为一个或多个集成电路来实施，例如微处理器或微控制器。该处理器702用于执行存储器中存储的指令，能够使热力分布图合理化，提高热力分析的准确度。
在一个实施例中，还可以如图8所示，热力分析装置800包括存储器801和处理器802。处理器802通过BUS总线803耦合至存储器801。该热力分析装置800还可以通过存储接口804连接至外部存储装置805以便调用外部数据，还可以通过网络接口806连接至网络或者另外一台计算机系统(未标出)。此处不再进行详细介绍。
在该实施例中，通过存储器存储数据指令，再通过处理器处理上述指令，能够使热力分布图合理化，提高热力分析的准确度。
在另一个实施例中，一种计算机可读存储介质，其上存储有计算机程序指令，该指令被处理器执行时实现热力分析方法对应实施例中的方法的步骤。本领域内的技术人员应明白，本公开的实施例可提供为方法、装置、或计算机程序产品。因此，本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用非瞬时性存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本公开的热力分析系统的一些实施例的示意图如图9所示。热力分析装置91可以为上文中的任意一种。图像采集设备92能够监控目标区域，获取监控视频，如监控目标区域的摄像头等。在一些实施例中，图像采集设备92可以为一个或多个。
这样的热力分析系统能够采集监控视频并得到初始热力分布图，在目标区域布局图的基础上得到热力分布合法区域和热力分布非法区域，进而对采集的初始热力分布图进行校正，使热力分布图合理化，提高热力分析的准确度。
本公开是参照根据本公开实施例的方法、设备(系统)和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
至此，已经详细描述了本公开。为了避免遮蔽本公开的构思，没有描述本领域所公知的一些细节。本领域技术人员根据上面的描述，完全可以明白如何实施这里公开的技术方案。
可能以许多方式来实现本公开的方法以及装置。例如，可通过软件、硬件、固件或者软件、硬件、固件的任何组合来实现本公开的方法以及装置。用于所述方法的步骤的上述顺序仅是为了进行说明，本公开的方法的步骤不限于以上具体描述的顺序，除非以其它方式特别说明。此外，在一些实施例中，还可将本公开实施为记录在记录介质中的程序，这些程序包括用于实现根据本公开的方法的机器可读指令。因而，本公开还覆盖存储用于执行根据本公开的方法的程序的记录介质。
最后应当说明的是：以上实施例仅用以说明本公开的技术方案而非对其限制；尽管参照较佳实施例对本公开进行了详细的说明，所属领域的普通技术人员应当理解：依然可以对本公开的具体实施方式进行修改或者对部分技术特征进行等同替换；而不脱离本公开技术方案的精神，其均应涵盖在本公开请求保护的技术方案范围当中。

Claims (17)

  1. 一种热力分析方法，包括：
    在目标区域的布局图中确定热力分布合法区域和热力分布非法区域；
    获取所述目标区域的初始热力分布图；
    根据所述初始热力分布图，将位于所述布局图中热力分布非法区域的热力值移至所述布局图中热力分布合法区域的对应位置，获取更新热力分布图。
  2. 根据权利要求1所述的热力分析方法，还包括根据所述更新热力分布图调整目标区域的物品分布或物品库存量中的一项或多项。
  3. 根据权利要求1所述的热力分析方法，还包括：
    根据所述更新热力分布图测试调整目标区域的物品分布，并获取调整后的更新热力分布图；
    在所述更新热力分布图在测试前后的变化比例超过预定门限的情况下，根据所述更新热力分布图调整所述目标区域的物品库存量；和
    在所述更新热力分布图在测试前后的变化比例未超过预定门限的情况下，根据需求调整目标区域的物品分布。
  4. 根据权利要求1～3任意一项所述的热力分析方法，其中，所述在目标区域的布局图中确定热力分布合法区域和热力分布非法区域包括：
    获取所述目标区域的布局图；
    在所述布局图中确定允许人通过的区域和不允许人通过的区域；
    设置所述允许人通过的区域为热力分布合法区域，所述不允许人通过的区域为热力分布非法区域。
  5. 根据权利要求4所述的热力分析方法，其中，所述在所述布局图中确定允许人通过的区域和不允许人通过的区域包括：
    将二值化的布局图做漫水填充并反转颜色，获取漫水反转图；
    根据所述漫水反转图与所述二值化的布局图获取物品框选布局图；
    根据所述物品框选布局图确定所述允许人通过的区域和不允许人通过的区域。
  6. 根据权利要求5所述的热力分析方法，其中，所述在所述布局图中确定允许人通过的区域和不允许人通过的区域还包括：
    将所述物品框选布局图做膨胀操作；
    将膨胀操作后的所述物品框选布局图做腐蚀操作，获取更新物品框选布局图；
    所述根据所述物品框选布局图确定所述允许人通过的区域和不允许人通过的区域包括：根据所述更新物品框选布局图，确定摆放物品的区域和被摆放物品的区域包围的区域为不允许人通过的区域，未摆放物品且未被摆放物品的区域包围的区域为允许人通过的区域。
  7. 根据权利要求5所述的热力分析方法，其中，
    所述在所述布局图中确定允许人通过的区域和不允许人通过的区域还包括：将所述布局图做二值化处理，其中，二值化的布局图的底色为第一预定颜色，非底色部分为第二预定颜色；
    所述做漫水填充并反转颜色包括：采用所述第二预定颜色做漫水填充；将所述第一预定颜色部分修改为所述第二预定颜色，将所述第二预定颜色部分修改为所述第一预定颜色；
    所述根据所述漫水反转图与所述二值化的布局图获取物品框选布局图包括：在所述漫水反转图或所述二值化的布局图中至少一个为所述第二预定色的位置，所述物品框选布局图为所述第二预定色，在所述漫水反转图和所述二值化的布局图中均所述第一预定色的位置，所述物品框选布局图为所述第一预定色；
    所述根据所述物品框选布局图确定所述允许人通过的区域和不允许人通过的区域包括：所述第二预定色的区域为不允许人通过的区域，所述第一预定色的区域为允许人通过的区域。
  8. 根据权利要求1～3任意一项所述的热力分析方法，其中，所述将位于所述布局图中热力分布非法区域的热力值移至所述布局图中热力分布合法区域的对应位置包括：
    确定所述初始热力分布图中位于所述热力分布非法区域的热力值非0的位置为异常位置；
    确定各个所述异常位置对应的最近合法位置，其中，所述最近合法位置位于所述热力分布合法区域；
    将各个所述异常位置的所述热力值累积在对应的所述最近合法位置。
  9. 根据权利要求1～3任意一项所述的热力分析方法，其中，所述获取所述目标区 域的初始热力分布图包括：
    通过图像采集设备获取所述目标区域的监控视频；
    通过行人检测识别算法检测所述监控视频的各帧图像中行人的位置；
    根据在各个位置停留超过预定时长的人的数量和停留的时长确定所述目标区域的初始热力分布图。
  10. 根据权利要求9所述的热力分析方法，其中，所述获取所述目标区域的初始热力分布图还包括：
    根据多个所述图像采集设备的探测区域的位置关系，将各个所述探测区域映射到同一个所述目标区域的平面中。
  11. 根据权利要求1～3任意一项所述的热力分析方法，其中，所述目标区域的布局图包括所述目标区域的设计图，施工图或基于扫描恢复的目标区域的场景图。
  12. 一种热力分析装置，包括：
    区域确定单元，被配置为在目标区域的布局图中确定热力分布合法区域和热力分布非法区域；
    初始热力分布获取单元，被配置为获取所述目标区域的初始热力分布图；
    热力分布获取单元，被配置为根据所述初始热力分布图，将位于所述布局图中热力分布非法区域的热力值移至所述布局图中热力分布合法区域的对应位置，获取更新热力分布图。
  13. 根据权利要求12所述的热力分析装置，还包括：
    热力分布应用单元，被配置为执行根据所述更新热力分布图调整目标区域的物品分布，或物品库存量中的一项或多项。
  14. 根据权利要求12所述的热力分析装置，还包括：
    测试单元，被配置为根据所述更新热力分布图测试调整目标区域的物品分布，获取调整后的更新热力分布图；
    热力分布应用单元，被配置为在所述更新热力分布图在测试前后的变化比例超过预定门限的情况下，根据所述更新热力分布图调整所述目标区域的物品库存量；在所述更新热力分布图在测试前后的变化比例未超过预定门限的情况下，根据需求调整目标区域的物品分布。
  15. 一种热力分析装置，包括：
    存储器；以及
    耦接至所述存储器的处理器，所述处理器被配置为基于存储在所述存储器的指令执行如权利要求1至11任一项所述的方法。
  16. 一种计算机可读存储介质，其上存储有计算机程序指令，该指令被处理器执行时实现权利要求1至11任意一项所述的方法的步骤。
  17. 一种热力分析系统，包括：
    权利要求12～15任意一项所述的热力分析装置；和
    图像采集设备，被配置为监控目标区域，获取监控视频。
PCT/CN2020/080781 2019-05-22 2020-03-24 热力分析方法、装置和系统 WO2020233221A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910427547.2 2019-05-22
CN201910427547.2A CN112070623A (zh) 2019-05-22 2019-05-22 热力分析方法、装置和系统

Publications (1)

Publication Number Publication Date
WO2020233221A1 true WO2020233221A1 (zh) 2020-11-26

Family

ID=73458383

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/080781 WO2020233221A1 (zh) 2019-05-22 2020-03-24 热力分析方法、装置和系统

Country Status (2)

Country Link
CN (1) CN112070623A (zh)
WO (1) WO2020233221A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112488913A (zh) * 2020-11-27 2021-03-12 杭州海康威视数字技术股份有限公司 数据处理方法、装置及电子设备
CN113657925A (zh) * 2021-07-28 2021-11-16 黄淮学院 基于人工智能的土木工程造价管理方法
CN116227777A (zh) * 2023-05-08 2023-06-06 浙江飞猪网络技术有限公司 行程信息处理方法及电子设备
CN116236993A (zh) * 2023-05-12 2023-06-09 台昌树脂(佛山)有限公司 丙烯酸共聚乳液生产控制系统的优化方法及系统

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113743736B (zh) * 2021-08-11 2024-02-27 上海钧正网络科技有限公司 热力等级确定方法、热力图生成方法、装置和电子设备
CN113763045B (zh) * 2021-09-06 2024-02-23 武汉博创非凡智能科技有限公司 一种基于多源数据融合的门店选址可视化分析方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107256225A (zh) * 2017-04-28 2017-10-17 济南中维世纪科技有限公司 一种基于视频分析的热度图生成方法及装置
US20180329995A1 (en) * 2015-11-20 2018-11-15 Beijing Gridsum Technology Co., Ltd. Method and device for generating thermodynamic diagram
CN109146576A (zh) * 2018-09-10 2019-01-04 北京旷视科技有限公司 店铺货物摆放策略的确定方法、装置和电子设备
CN109213949A (zh) * 2017-06-19 2019-01-15 北京嘀嘀无限科技发展有限公司 热力图的绘制方法和装置
CN109697392A (zh) * 2017-10-23 2019-04-30 北京京东尚科信息技术有限公司 绘制目标对象热力图的方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180329995A1 (en) * 2015-11-20 2018-11-15 Beijing Gridsum Technology Co., Ltd. Method and device for generating thermodynamic diagram
CN107256225A (zh) * 2017-04-28 2017-10-17 济南中维世纪科技有限公司 一种基于视频分析的热度图生成方法及装置
CN109213949A (zh) * 2017-06-19 2019-01-15 北京嘀嘀无限科技发展有限公司 热力图的绘制方法和装置
CN109697392A (zh) * 2017-10-23 2019-04-30 北京京东尚科信息技术有限公司 绘制目标对象热力图的方法及装置
CN109146576A (zh) * 2018-09-10 2019-01-04 北京旷视科技有限公司 店铺货物摆放策略的确定方法、装置和电子设备

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LI, LU: "Design and Implementation of Visualization System Based on Indoor Positioning Data", ELECTRONIC TECHNOLOGY & INFORMATION SCIENCE, CHINA MASTER’S THESES FULL-TEXT DATABASE, no. 04, 15 April 2018 (2018-04-15), DOI: 20200610123352X *
LI, LU: "Design and Implementation of Visualization System Based on Indoor Positioning Data", ELECTRONIC TECHNOLOGY & INFORMATION SCIENCE, CHINA MASTER’S THESES FULL-TEXT DATABASE, no. 04, 15 April 2018 (2018-04-15), DOI: 20200610123532X *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112488913A (zh) * 2020-11-27 2021-03-12 杭州海康威视数字技术股份有限公司 数据处理方法、装置及电子设备
CN113657925A (zh) * 2021-07-28 2021-11-16 黄淮学院 基于人工智能的土木工程造价管理方法
CN113657925B (zh) * 2021-07-28 2023-08-22 黄淮学院 基于人工智能的土木工程造价管理方法
CN116227777A (zh) * 2023-05-08 2023-06-06 浙江飞猪网络技术有限公司 行程信息处理方法及电子设备
CN116227777B (zh) * 2023-05-08 2023-10-13 浙江飞猪网络技术有限公司 行程信息处理方法及电子设备
CN116236993A (zh) * 2023-05-12 2023-06-09 台昌树脂(佛山)有限公司 丙烯酸共聚乳液生产控制系统的优化方法及系统
CN116236993B (zh) * 2023-05-12 2023-08-08 台昌树脂(佛山)有限公司 丙烯酸共聚乳液生产控制系统的优化方法及系统

Also Published As

Publication number Publication date
CN112070623A (zh) 2020-12-11

Similar Documents

Publication Publication Date Title
WO2020233221A1 (zh) 热力分析方法、装置和系统
CN108647242B (zh) 一种热力图的生成方法和系统
CN109446883B (zh) 商品状态识别方法、装置、电子设备及可读存储介质
CN109977886B (zh) 货架空置率计算方法及装置、电子设备、存储介质
Liu et al. A smart unstaffed retail shop based on artificial intelligence and IoT
CN104424482B (zh) 图像处理设备和图像处理方法
US20140169639A1 (en) Image Detection Method and Device
CN110472486B (zh) 一种货架障碍物识别方法、装置、设备及可读存储介质
CN110991261A (zh) 交互行为识别方法、装置、计算机设备和存储介质
CN107194959A (zh) 基于切片进行图像配准的方法和装置
US9742992B2 (en) Non-uniform curve sampling method for object tracking
CN112102409A (zh) 目标检测方法、装置、设备及存储介质
WO2018235198A1 (ja) 情報処理装置、制御方法、及びプログラム
CN112883955A (zh) 货架布局检测方法、装置及计算机可读存储介质
Milella et al. Towards intelligent retail: Automated on-shelf availability estimation using a depth camera
US20230018877A1 (en) Image/video analysis with activity signatures
CN111428743B (zh) 商品识别方法、商品处理方法、装置及电子设备
JP5976126B2 (ja) ターゲットサイズを見積もるためのシステム及び方法
KR101982258B1 (ko) 오브젝트 검출 방법 및 오브젝트 검출 장치
CN116453061A (zh) 一种基于图像识别的远程卖猪监管方法、装置以及设备
US20180150966A1 (en) System and method for estimating object size
CN112598738B (zh) 一种基于深度学习的人物定位方法
JP5599228B2 (ja) 繁忙検知システム及び繁忙検知プログラム
US20150262378A1 (en) Systems and Methods for Tracking Points Within an Encasement
Pietrini et al. Embedded Vision System for Real-Time Shelves Rows Detection for Planogram Compliance Check

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: 20809059

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: 20809059

Country of ref document: EP

Kind code of ref document: A1

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 22/03/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20809059

Country of ref document: EP

Kind code of ref document: A1