CN117273251A - Intelligent planning method and system based on big data - Google Patents

Intelligent planning method and system based on big data Download PDF

Info

Publication number
CN117273251A
CN117273251A CN202311218574.1A CN202311218574A CN117273251A CN 117273251 A CN117273251 A CN 117273251A CN 202311218574 A CN202311218574 A CN 202311218574A CN 117273251 A CN117273251 A CN 117273251A
Authority
CN
China
Prior art keywords
pixel
image
pixels
label
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311218574.1A
Other languages
Chinese (zh)
Inventor
崔勇
林海
莫敷建
莫媛媛
王大鹏
叶雅欣
潘振皓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangxi Arts University
Guangxi Academy of Fishery Sciences
Original Assignee
Guangxi Arts University
Guangxi Academy of Fishery Sciences
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 Guangxi Arts University, Guangxi Academy of Fishery Sciences filed Critical Guangxi Arts University
Priority to CN202311218574.1A priority Critical patent/CN117273251A/en
Publication of CN117273251A publication Critical patent/CN117273251A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • 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
    • G06Q50/10—Services
    • G06Q50/12—Hotels or restaurants
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • G06V10/12—Details of acquisition arrangements; Constructional details thereof
    • G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
    • G06V10/143—Sensing or illuminating at different wavelengths
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/17—Terrestrial scenes taken from planes or by drones
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Tourism & Hospitality (AREA)
  • Multimedia (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Development Economics (AREA)
  • Remote Sensing (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses an intelligent planning method and system based on big data, comprising the following steps: s1: the unmanned aerial vehicle collects infrared images of outdoor leisure fishery tour areas at different heights in real time; s2: according to N infrared images of different heights of the current place shot by the unmanned aerial vehicle, calculating the number of tourists at the current place; s3: the path selection module is used for calculating the fitness value T_S of each place of the outdoor leisure fishery tour area; s4: selecting a place with the highest fitness value T_S of the outdoor leisure fishery tour area as a destination; s5: navigation to the destination is by GPS for the guest. According to the method, N infrared images of different heights of the current location are shot according to the unmanned aerial vehicle, the number of tourists at the current location is calculated, then the fitness value T_S of each location of the outdoor leisure fishery tour area is calculated, and the location with the highest fitness value T_S of the outdoor leisure fishery tour area is selected as a destination, so that the user satisfaction is enhanced.

Description

Intelligent planning method and system based on big data
Technical Field
The invention relates to the field of path planning of outdoor leisure fishing ground tourist areas, in particular to an intelligent planning method and system based on big data.
Background
With the rapid development of technology, big data and artificial intelligence technology are widely applied in various fields. Among other things, the leisure and fishery outdoor travel field has also begun to benefit from the assistance of these advanced technologies, especially in providing a more intelligent, convenient and personalized travel experience for visitors. Traditional outdoor limited fishery travel path planning relies primarily on human experience and fixed travel routes. This approach meets the basic needs of the tourist in most cases, but with the development of the tourist industry and the diversification of the needs of the tourist, the conventional approach is gradually inflexible and accurate. For example, when a tourist attraction is crowded or suddenly changed in weather, a fixed travel route may no longer be suitable, resulting in the tourist experience of the tourist being affected.
To address these issues, researchers have begun exploring how to optimize travel path planning using big data and artificial intelligence techniques. By collecting and analyzing a large amount of travel data, such as tourist location, destination, time, number of tourist attractions, weather, air temperature, ultraviolet light and the like, more intelligent and personalized travel advice can be provided for the tourist.
In addition, unmanned aerial vehicle technology also brings new possibilities for travel path planning. The unmanned aerial vehicle can collect real-time data of tourist attractions, such as infrared images, temperature information and the like, rapidly and at low cost. The data can help researchers to know the real-time situation of tourist attractions more accurately, so that more accurate tourist advice is provided for tourists. However, the existing scenic spot is inaccurate in infrared identification due to more people flow, and the possibility of overlapping counting exists; and how to efficiently integrate and analyze these large amounts of data remains a challenge. Traditional data analysis methods often cannot process such huge and complex data, resulting in limited accuracy and real-time travel advice. Therefore, there is a need to develop new data analysis methods and algorithms to improve the efficiency and accuracy of travel path planning.
In general, the leisure outdoor travel field is facing challenges in how to effectively utilize big data and artificial intelligence techniques to optimize travel path planning. In order to meet the diversified needs of tourists and to improve travel experience, new technologies and methods are required to be developed to realize more intelligent, convenient and personalized travel services.
Disclosure of Invention
Aiming at the problems mentioned in the prior art, the invention provides an intelligent planning method and system based on big data, the method calculates the number of tourists in the current location by adopting N infrared images with different heights according to the current location shot by an unmanned aerial vehicle, then calculates the fitness value T_S of each location of an outdoor leisure fishery tour area, selects the location with the highest fitness value T_S of the outdoor leisure fishery tour area as a destination, and greatly realizes the recommendation of the location of the real-time scenic area by automatic calculation processing, thereby enhancing the user satisfaction.
An intelligent planning method based on big data comprises the following steps:
s1: the unmanned aerial vehicle collects infrared images of outdoor leisure fishery tour areas at different heights in real time; the sensor module obtains wind speed, ultraviolet rays, humidity and temperature information data;
s2: according to N infrared images of different heights of the current place shot by the unmanned aerial vehicle, calculating the number of tourists at the current place;
s21: converting the infrared image into a binary image;
s22: performing a connected component analysis on the binary image to detect and count individual bright areas, each bright area representing a person;
s23: the highest frequency of occurrence of the number of persons detected in the N infrared images is the number K of tourists in the current shooting area;
s3: the path selection module calculates the adaptability value T_S of each place of the outdoor leisure fishery tour area,
S_t＝100-|25-T|
S_h＝100-|50-H|
S_wind＝100-|5-wind|
S_uv＝100-uv
wherein w_p, w-T, w _h, w_wind and w_uv are weight values corresponding to the number of people, temperature, humidity, wind speed and ultraviolet rays respectively, P_N is the maximum load number of tourists at the place of the outdoor leisure fishery tour area, and different places correspond to different values; t is the acquired temperature data, H is the acquired humidity data, wind is the acquired wind speed data, and uv is the ultraviolet data;
s4: selecting a place with the highest fitness value T_S of the outdoor leisure fishery tour area as a destination;
s5: navigation to the destination is by GPS for the guest.
Preferably, the unmanned aerial vehicle collects infrared images of outdoor leisure fishery tour areas in real time at different heights, and the unmanned aerial vehicle further comprises the step of denoising the images by adopting histogram equalization.
Preferably, the highest frequency of occurrence of the number of persons detected in the N infrared images is the number K of tourists in the current shooting area, and for each image with a height, one person count is provided, the number with the highest occurrence probability is selected as the final number, and when the probabilities are equal, the number of persons in the image with the middle height is selected as the final number.
Preferably, the communicating component analysis is performed on a binary image to detect and count individual bright areas, each bright area representing a person;
initializing, namely assigning a label to each pixel, and setting the labels of all pixels to 0 at the beginning to represent unlabeled pixels;
a first scanning pass, starting from the upper left corner of the image, scanning the whole image row by row and pixel by pixel; for each pixel, the pixels above and to the left of it are examined: skipping if the current pixel is a background pixel value of 0; if the upper pixel and the left pixel are background pixels, a new label is allocated to the current pixel; if one of the upper or left pixels is a foreground pixel value of 1, then the same label is assigned to the current pixel; if the upper and left pixels are foreground pixels but the labels are different, then the labels of the upper pixels are allocated to the current pixel, and the labels of the upper and left pixels are recorded to be equivalent;
combining the labels, namely combining the components with the same label according to the equivalent label relation recorded in the first scanning;
scanning the whole image again, distributing a final label for each pixel, and searching an equivalent label of each pixel label;
the number of unique tags in the image is calculated.
The application also provides an intelligent planning system based on big data, comprising:
the system comprises an unmanned aerial vehicle, a sensor, a processor and a memory, wherein the unmanned aerial vehicle comprises an infrared image camera for acquiring an infrared image;
the data acquisition module is used for acquiring infrared images of outdoor leisure fishery tour areas in real time at different heights by the unmanned aerial vehicle; the sensor module obtains wind speed, ultraviolet rays, humidity and temperature information data;
the tourist number determining module is used for calculating the number of tourists in the current place according to N infrared images of different heights of the current place shot by the unmanned aerial vehicle;
converting the infrared image into a binary image;
performing a connected component analysis on the binary image to detect and count individual bright areas, each bright area representing a person;
the highest frequency of occurrence of the number of persons detected in the N infrared images is the number K of tourists in the current shooting area;
the path selection module calculates the adaptability value T_S of each place of the outdoor leisure fishery tour area,
S_t＝100-|25-T|
S_h＝100-|50-H|
S_wind＝100-|5-wind|
S_uv＝100-uv
wherein w_p, w_ T, w _h, w_wind and w_uv are weight values corresponding to the number of people, temperature, humidity, wind speed and ultraviolet rays respectively, P_N is the maximum load number of tourists at the place of the outdoor leisure fishery tour area, and different places correspond to different values; t is the acquired temperature data, H is the acquired humidity data, wind is the acquired wind speed data, and uv is the ultraviolet data;
the destination selecting module is used for selecting a place with the highest fitness value T_S of the outdoor leisure fishery tour area as a destination;
and the path navigation module is used for navigating the tourist to the destination through the GPS.
Preferably, the unmanned aerial vehicle collects infrared images of outdoor leisure fishery tour areas in real time at different heights, and the unmanned aerial vehicle further comprises the step of denoising the images by adopting histogram equalization.
Preferably, the highest frequency of occurrence of the number of persons detected in the N infrared images is the number K of tourists in the current shooting area, and for each image with a height, one person count is provided, the number with the highest occurrence probability is selected as the final number, and when the probabilities are equal, the number of persons in the image with the middle height is selected as the final number.
Preferably, the communicating component analysis is performed on a binary image to detect and count individual bright areas, each bright area representing a person;
initializing, namely assigning a label to each pixel, and setting the labels of all pixels to 0 at the beginning to represent unlabeled pixels;
a first scanning pass, starting from the upper left corner of the image, scanning the whole image row by row and pixel by pixel; for each pixel, the pixels above and to the left of it are examined: skipping if the current pixel is a background pixel value of 0; if the upper pixel and the left pixel are background pixels, a new label is allocated to the current pixel; if one of the upper or left pixels is a foreground pixel value of 1, then the same label is assigned to the current pixel; if the upper and left pixels are foreground pixels but the labels are different, then the labels of the upper pixels are allocated to the current pixel, and the labels of the upper and left pixels are recorded to be equivalent;
combining the labels, namely combining the components with the same label according to the equivalent label relation recorded in the first scanning;
scanning the whole image again, distributing a final label for each pixel, and searching an equivalent label of each pixel label;
the number of unique tags in the image is calculated.
The invention provides an intelligent planning method and system based on big data, which can realize the following beneficial technical effects:
1. according to the method, the number of tourists at the current location is calculated according to N infrared images of different heights of the current location shot by the unmanned aerial vehicle; converting the infrared image into a binary image; performing a connected component analysis on the binary image to detect and count individual bright areas, each bright area representing a person; the highest frequency of occurrence of the number of persons detected in the N infrared images is the number K of tourists in the current shooting area; for each height image, the number of people is counted, the number of people with the highest occurrence probability is selected as the final number of people, when the probabilities are equal, the number of people with the middle height image is selected as the final number of people, the accuracy of people counting is greatly improved, the processing method is simple and quick, the calculated amount is small, and the processing efficiency is greatly improved.
2. The invention calculates the adaptability value T_S of each place of the outdoor leisure fishery tour area according to the path selection module,
S_t＝100-|25-T|
S_h＝100-|50-H|
S_wind＝100-|5-wind|
S_uv＝100-uv
wherein w_p, w_ T, w _h, w_wind and w_uv are weight values corresponding to the number of people, temperature, humidity, wind speed and ultraviolet rays respectively, P_N is the maximum load number of tourists at the place of the outdoor leisure fishery tour area, and different places correspond to different values; t is the acquired temperature data, H is the acquired humidity data, wind is the acquired wind speed data, and uv is the ultraviolet data; the destination selection module selects the place with the highest fitness value T_S of the outdoor leisure fishery tour area as a destination, and realizes automatic recommendation of the tour area by calculating the fitness value T_S of each place of the outdoor leisure fishery tour area, thereby greatly improving the automatic recommendation planning efficiency of the tour path and the user satisfaction.
3. According to the invention, through the analysis of the communicating component on the binary image, independent bright areas are detected and counted, and each bright area represents a person; initializing, namely assigning a label to each pixel, and setting the labels of all pixels to 0 at the beginning to represent unlabeled pixels; a first scanning pass, starting from the upper left corner of the image, scanning the whole image row by row and pixel by pixel; for each pixel, the pixels above and to the left of it are examined: skipping if the current pixel is a background pixel value of 0; if the upper pixel and the left pixel are background pixels, a new label is allocated to the current pixel; if one of the upper or left pixels is a foreground pixel value of 1, then the same label is assigned to the current pixel; if the upper and left pixels are foreground pixels but the labels are different, then the labels of the upper pixels are allocated to the current pixel, and the labels of the upper and left pixels are recorded to be equivalent; combining the labels, namely combining the components with the same label according to the equivalent label relation recorded in the first scanning; scanning the whole image again, distributing a final label for each pixel, and searching an equivalent label of each pixel label; the number of unique labels in the image is calculated, and the statistical efficiency of the number of people is greatly enhanced by scanning the marks.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of steps of an intelligent planning method based on big data.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1:
in order to solve the above-mentioned problems mentioned in the prior art, as shown in fig. 1: an intelligent planning method based on big data comprises the following steps:
s1: the unmanned aerial vehicle collects infrared images of outdoor leisure fishery tour areas at different heights in real time; the sensor module obtains wind speed, ultraviolet rays, humidity and temperature information data;
unmanned aerial vehicle gathers: unmanned aerial vehicle flies above the leisure fishery tourist area, and infrared images are acquired in real time. These images may show which areas on the travel zone are warmer, which areas are more heavily populated, and which areas may have potential safety hazards (e.g., areas submerged due to rising tidal water).
A sensor module: the sensors on the leisure fish tourism area can acquire the data of wind speed, ultraviolet rays, humidity and temperature in real time. These data can help the tourist to know in real time the conditions of the leisure fish tourism area, for example, which areas have stronger ultraviolet light and which areas have larger wind speed.
Intelligent planning: in combination with the data of the drone and the sensors, the system may provide personalized beach advice for the guest. For example, it is recommended that tourists choose areas with smaller wind speed to shine the sun in the morning, choose areas with weaker ultraviolet rays to avoid the sun in the noon, and choose areas with lower humidity to play in the afternoon.
S2: according to N infrared images of different heights of the current place shot by the unmanned aerial vehicle, calculating the number of tourists at the current place; shooting by an unmanned aerial vehicle: the unmanned aerial vehicle is located above the recreational fishing travel area site and captures infrared images from different elevations (e.g., 10 meters, 30 meters, 50 meters, 80 meters, 100 meters). This helps to more accurately detect and count the number of people because the size and distribution of people in images of different heights may be different.
Image processing: human body detection is carried out on the images at each height, and the number of people in each image is calculated. Then, the number of people with the highest probability of occurrence is selected as the final number of people in combination with the data of several heights.
S21: converting the infrared image into a binary image;
1. shooting by an unmanned aerial vehicle: the unmanned aerial vehicle carries an infrared camera to fly above the leisure fishery tourist area, and captures infrared images in real time. The infrared image may show the thermal radiation of the human body, and thus the human body may appear as a bright area in the infrared image.
2. Image preprocessing:
to reduce noise and other disturbances, the infrared image may be subjected to some basic pre-processing, such as filtering, contrast enhancement, etc.
3. Converting into a binary image:
a threshold is set, which is determined based on a temperature difference between the thermal radiation of the human body and the background.
For each pixel in the infrared image, if its brightness value is above the threshold, it is set to 1 (white), indicating that this is a human pixel; if its luminance value is below the threshold value, it is set to 0 (black), indicating that this is a background pixel.
4. Results:
the obtained binary image clearly shows the distribution of the human body on the lawn. The human body appears as a continuous white area, while the background is black.
S22: performing a connected component analysis on the binary image to detect and count individual bright areas, each bright area representing a person;
s23: the highest frequency of occurrence of the number of persons detected in the N infrared images is the number K of tourists in the current shooting area;
s3: the path selection module calculates the adaptability value T_S of each place of the outdoor leisure fishery tour area,
S_t＝100-|25-T|
S_h＝100-|50-H|
S_wind＝100-|5-wind|
S_uv＝100-uv
wherein w_p, w_ T, w _h, w_wind and w_uv are weight values corresponding to the number of people, temperature, humidity, wind speed and ultraviolet rays respectively, P_N is the maximum load number of tourists at the place of the outdoor leisure fishery tour area, and different places correspond to different values; t is the acquired temperature data, H is the acquired humidity data, wind is the acquired wind speed data, and uv is the ultraviolet data;
through the infrared image data collected by the unmanned aerial vehicle, the number of people at each place can be estimated. If the number of people at a location exceeds a preset threshold, the location will be marked as a "high people stream" area. Examples: assuming that attraction A is 500 people and the accommodation limit of the attraction is 400 people, then attraction A will be marked as a "high people stream" area and the system will suggest that the guest choose other paths or revisit when there is less people stream
And calculating a comfort index by combining the information such as temperature, humidity, wind speed, ultraviolet rays and the like. The index will take into account a number of factors, such as: high temperature, high humidity, strong wind, strong ultraviolet, etc. can reduce the comfort index.
Examples: the temperature at a certain place was assumed to be 35 ℃, the humidity was assumed to be 80%, the wind speed was assumed to be 2m/s, and the ultraviolet index was assumed to be 8 (high). In combination with this data we can conclude that the comfort of the venue is low and therefore the system will suggest that the guest visit during a more comfortable period.
S4: selecting a place with the highest fitness value T_S of the outdoor leisure fishery tour area as a destination;
s5: navigation to the destination is by GPS for the guest.
In some embodiments, the unmanned aerial vehicle collects infrared images of outdoor leisure fishery tour areas at different heights in real time, and further includes denoising the images using histogram equalization.
In some embodiments, the highest frequency of occurrence of the detected number of persons in the N infrared images is the number K of tourists in the current shooting area, and for each image with a height, there is a number count, and the number with the highest occurrence probability is selected as the final number, and when the probabilities are equal, the number of persons in the image with the middle height is selected as the final number.
1. Shooting by an unmanned aerial vehicle:
the drone takes ir images from four different heights (e.g., 5 meters, 10 meters, 15 meters, and 20 meters) above the recreational fishery area. These four height images can help detect and count the number of people, especially if people are clustered together or are occluded.
2. And (3) detecting the number of people:
in an image at a height of 5 meters, 120 people were detected.
In an image of 10 meters height, 125 people were detected.
In an image at a height of 15 meters, 123 people were detected.
In an image of 20 meters height, 125 people were detected.
3. Counting the number of people:
for an image at a height of 5 meters, the number of people is 120, which occurs 1 time.
For images at 10 and 20 meters height, the number of people is 125, which occurs 2 times.
For an image at a height of 15 meters, the number of people is 123, which occurs 1 time.
Since the number of persons detected in the images at the heights of 10 meters and 20 meters is 125, and the frequency of occurrence of this number of persons is highest (2 times), 125 is selected as the final number of persons.
In some embodiments, the communicating component analysis is performed on a binary image to detect and count individual bright areas, each bright area representing a person;
initializing, namely assigning a label to each pixel, and setting the labels of all pixels to 0 at the beginning to represent unlabeled pixels;
a first scanning pass, starting from the upper left corner of the image, scanning the whole image row by row and pixel by pixel; for each pixel, the pixels above and to the left of it are examined: skipping if the current pixel is a background pixel value of 0; if the upper pixel and the left pixel are background pixels, a new label is allocated to the current pixel; if one of the upper or left pixels is a foreground pixel value of 1, then the same label is assigned to the current pixel; if the upper and left pixels are foreground pixels but the labels are different, then the labels of the upper pixels are allocated to the current pixel, and the labels of the upper and left pixels are recorded to be equivalent;
combining the labels, namely combining the components with the same label according to the equivalent label relation recorded in the first scanning;
scanning the whole image again, distributing a final label for each pixel, and searching an equivalent label of each pixel label;
the number of unique tags in the image is calculated.
Example 2:
the application also provides an intelligent planning system based on big data, comprising:
the system comprises an unmanned aerial vehicle, a sensor, a processor and a memory, wherein the unmanned aerial vehicle comprises an infrared image camera for acquiring an infrared image;
the data acquisition module is used for acquiring infrared images of outdoor leisure fishery tour areas in real time at different heights by the unmanned aerial vehicle; the sensor module obtains wind speed, ultraviolet rays, humidity and temperature information data;
the tourist number determining module is used for calculating the number of tourists in the current place according to N infrared images of different heights of the current place shot by the unmanned aerial vehicle;
converting the infrared image into a binary image;
performing a connected component analysis on the binary image to detect and count individual bright areas, each bright area representing a person;
the highest frequency of occurrence of the number of persons detected in the N infrared images is the number K of tourists in the current shooting area;
the path selection module calculates the adaptability value T_S of each place of the outdoor leisure fishery tour area,
S_t＝100-|25-T|
S_h＝100-|50-H|
S_wind＝100-|5-wind|
S_uv＝100-uv
wherein w_p, w_ T, w _h, w_wind and w_uv are weight values corresponding to the number of people, temperature, humidity, wind speed and ultraviolet rays respectively, P_N is the maximum load number of tourists at the place of the outdoor leisure fishery tour area, and different places correspond to different values; t is the acquired temperature data, H is the acquired humidity data, wind is the acquired wind speed data, and uv is the ultraviolet data;
the destination selecting module is used for selecting a place with the highest fitness value T_S of the outdoor leisure fishery tour area as a destination;
and the path navigation module is used for navigating the tourist to the destination through the GPS.
In some embodiments, the unmanned aerial vehicle collects infrared images of outdoor leisure fishery tour areas at different heights in real time, and further includes denoising the images using histogram equalization.
In some embodiments, the highest frequency of occurrence of the detected number of persons in the N infrared images is the number K of tourists in the current shooting area, and for each image with a height, there is a number count, and the number with the highest occurrence probability is selected as the final number, and when the probabilities are equal, the number of persons in the image with the middle height is selected as the final number.
1. The drone takes ir images from three different elevations (e.g., 10 meters, 20 meters, and 30 meters) above the recreational fishery area. These three levels of images can help detect and count the number of people, especially if people are clustered together.
2. And (3) detecting the number of people:
in an image of 10 meters height, 50 people were detected.
In an image of 20 meters height, 48 people were detected.
In an image at a height of 30 meters, 49 people were detected.
3. Counting the number of people:
for an image at a height of 10 meters, the number of people is 50, which occurs 1 time.
For images at a height of 20 meters, the number of people is 48, which occurs 1 time.
For images at a height of 30 meters, the number of people is 49, which occurs 1 time.
Because the detected numbers of people in the three height images are all different, none of the numbers of people is the most frequent. Thus, according to the above method, the number of persons of the image at the intermediate height (20 meters) is selected as the final number of persons, namely, 48 persons.
In some embodiments, the communicating component analysis is performed on a binary image to detect and count individual bright areas, each bright area representing a person;
initializing, namely assigning a label to each pixel, and setting the labels of all pixels to 0 at the beginning to represent unlabeled pixels;
a first scanning pass, starting from the upper left corner of the image, scanning the whole image row by row and pixel by pixel; for each pixel, the pixels above and to the left of it are examined: skipping if the current pixel is a background pixel value of 0; if the upper pixel and the left pixel are background pixels, a new label is allocated to the current pixel; if one of the upper or left pixels is a foreground pixel value of 1, then the same label is assigned to the current pixel; if the upper and left pixels are foreground pixels but the labels are different, then the labels of the upper pixels are allocated to the current pixel, and the labels of the upper and left pixels are recorded to be equivalent;
combining the labels, namely combining the components with the same label according to the equivalent label relation recorded in the first scanning;
scanning the whole image again, distributing a final label for each pixel, and searching an equivalent label of each pixel label;
the number of unique tags in the image is calculated.
Because people may be clustered together, resulting in overlapping human bodies in an image, it is necessary to use a connected component analysis to detect and count the number of people.
1. Image preprocessing:
first, the color image captured by the camera is converted into a gray-scale image, which is then converted into a binary image using an appropriate threshold. In the binary image, the human body appears white (value 1) and the background is black (value 0).
2. Initializing:
each pixel in the binary image is assigned a label. Initially, the labels for all pixels are set to 0, indicating unlabeled.
3. First pass scanning:
starting from the upper left corner of the image, the entire image is scanned row by row and pixel by pixel. For each pixel, the pixels above and to the left are inspected and assigned corresponding labels according to the steps described above.
4. Tag combination:
and merging the components with the same label according to the equivalent label relation recorded in the first scanning pass. For example, if label 2 and label 5 are equivalent, then all pixels labeled 5 will be re-labeled 2.
5. Second pass scanning:
the entire image is scanned again and a final label is assigned to each pixel. This is done by looking up an equivalent label for each pixel label.
6. Counting:
the number of unique tags in the image is calculated. This number is the number of people at the entrance.
The invention provides an intelligent planning method and system based on big data, which can realize the following beneficial technical effects:
1. according to the method, the number of tourists at the current location is calculated according to N infrared images of different heights of the current location shot by the unmanned aerial vehicle; converting the infrared image into a binary image; performing a connected component analysis on the binary image to detect and count individual bright areas, each bright area representing a person; the highest frequency of occurrence of the number of persons detected in the N infrared images is the number K of tourists in the current shooting area; for each height image, the number of people is counted, the number of people with the highest occurrence probability is selected as the final number of people, when the probabilities are equal, the number of people in the middle height image is selected as the final number of people, the accuracy of people counting is greatly improved, the processing method is simple and rapid, the calculated amount is small, and the processing efficiency is greatly improved.
2. The invention calculates the adaptability value T_S of each place of the outdoor leisure fishery tour area according to the path selection module,
S_t＝100-|25-T|
S_h＝100-|50-H|
S_wind＝100-|5-wind|
S_uv＝100-uv
wherein w_p, w_ T, w _h, w_wind and w_uv are weight values corresponding to the number of people, temperature, humidity, wind speed and ultraviolet rays respectively, P_N is the maximum load number of tourists at the place of the outdoor leisure fishery tour area, and different places correspond to different values; t is the acquired temperature data, H is the acquired humidity data, wind is the acquired wind speed data, and uv is the ultraviolet data; the destination selection module selects the place with the highest fitness value T_S of the outdoor leisure fishery tour area as a destination, and realizes automatic recommendation of the tour area by calculating the fitness value T_S of each place of the outdoor leisure fishery tour area, thereby greatly improving the automatic recommendation planning efficiency of the tour path and the user satisfaction.
3. According to the invention, through the analysis of the communicating component on the binary image, independent bright areas are detected and counted, and each bright area represents a person; initializing, namely assigning a label to each pixel, and setting the labels of all pixels to 0 at the beginning to represent unlabeled pixels; a first scanning pass, starting from the upper left corner of the image, scanning the whole image row by row and pixel by pixel; for each pixel, the pixels above and to the left of it are examined: skipping if the current pixel is a background pixel value of 0; if the upper pixel and the left pixel are background pixels, a new label is allocated to the current pixel; if one of the upper or left pixels is a foreground pixel value of 1, then the same label is assigned to the current pixel; if the upper and left pixels are foreground pixels but the labels are different, then the labels of the upper pixels are allocated to the current pixel, and the labels of the upper and left pixels are recorded to be equivalent; combining the labels, namely combining the components with the same label according to the equivalent label relation recorded in the first scanning; scanning the whole image again, distributing a final label for each pixel, and searching an equivalent label of each pixel label; the number of unique labels in the image is calculated, and the statistical efficiency of the number of people is greatly enhanced by scanning the marks.
The foregoing has described in detail a method and system for intelligent planning based on big data, and specific examples have been used herein to illustrate the principles and embodiments of the present invention, the above examples being for the purpose of helping to understand the core idea of the present invention; also, as will be apparent to those skilled in the art in light of the present teachings, the present disclosure should not be limited to the specific embodiments and applications described herein.

Claims (8)

1. An intelligent planning method based on big data is characterized by comprising the following steps:
s1: the unmanned aerial vehicle collects infrared images of outdoor leisure fishery tour areas at different heights in real time; the sensor module obtains wind speed, ultraviolet rays, humidity and temperature information data;
s2: according to N infrared images of different heights of the current place shot by the unmanned aerial vehicle, calculating the number of tourists at the current place;
s21: converting the infrared image into a binary image;
s22: performing a connected component analysis on the binary image to detect and count individual bright areas, each bright area representing a person;
s23: the highest frequency of occurrence of the number of persons detected in the N infrared images is the number K of tourists in the current shooting area;
s3: the path selection module calculates the adaptability value T_S of each place of the outdoor leisure fishery tour area,
S_t＝100-|25-T|
S_h＝100-|50-H|
S_wind＝100-|5-wind|
S_uv＝100-uv
wherein w_p, w_ T, w _h, w_wind and w_uv are weight values corresponding to the number of people, temperature, humidity, wind speed and ultraviolet rays respectively, P_N is the maximum load number of tourists at the place of the outdoor leisure fishery tour area, and different places correspond to different values; t is the acquired temperature data, H is the acquired humidity data, wind is the acquired wind speed data, and uv is the ultraviolet data;
s4: selecting a place with the highest fitness value T_S of the outdoor leisure fishery tour area as a destination;
s5: navigation to the destination is by GPS for the guest.
2. The intelligent planning method based on big data according to claim 1, wherein the unmanned aerial vehicle collects infrared images of outdoor leisure fishery tour areas at different heights in real time, and further comprises denoising the images by histogram equalization.
3. The intelligent planning method based on big data according to claim 1, wherein the highest occurrence frequency of the number of persons detected in the N infrared images is the number K of persons of the tourists in the current shooting area, for each image with a height, there is a number count, the number with the highest occurrence probability is selected as the final number, and when the probabilities are equal, the number of persons in the image with the middle height is selected as the final number.
4. The intelligent planning method according to claim 1, wherein the connected component analysis is performed on binary images to detect and count individual bright areas, each bright area representing a person;
initializing, namely assigning a label to each pixel, and setting the labels of all pixels to 0 at the beginning to represent unlabeled pixels;
a first scanning pass, starting from the upper left corner of the image, scanning the whole image row by row and pixel by pixel; for each pixel, the pixels above and to the left of it are examined: skipping if the current pixel is a background pixel value of 0; if the upper pixel and the left pixel are background pixels, a new label is allocated to the current pixel; if one of the upper or left pixels is a foreground pixel value of 1, then the same label is assigned to the current pixel; if the upper and left pixels are foreground pixels but the labels are different, then the labels of the upper pixels are allocated to the current pixel, and the labels of the upper and left pixels are recorded to be equivalent;
combining the labels, namely combining the components with the same label according to the equivalent label relation recorded in the first scanning;
scanning the whole image again, distributing a final label for each pixel, and searching an equivalent label of each pixel label;
the number of unique tags in the image is calculated.
5. An intelligent planning system based on big data, comprising:
the system comprises an unmanned aerial vehicle, a sensor, a processor and a memory, wherein the unmanned aerial vehicle comprises an infrared image camera for acquiring an infrared image;
the data acquisition module is used for acquiring infrared images of outdoor leisure fishery tour areas in real time at different heights by the unmanned aerial vehicle; the sensor module obtains wind speed, ultraviolet rays, humidity and temperature information data;
the tourist number determining module is used for calculating the number of tourists in the current place according to N infrared images of different heights of the current place shot by the unmanned aerial vehicle;
converting the infrared image into a binary image;
performing a connected component analysis on the binary image to detect and count individual bright areas, each bright area representing a person;
the highest frequency of occurrence of the number of persons detected in the N infrared images is the number K of tourists in the current shooting area;
the path selection module calculates the adaptability value T_S of each place of the outdoor leisure fishery tour area,
S_t＝100-|25-T|
S_h＝100-|50-H|
S_wind＝100-|5-wind|
S_uv＝100-uv
wherein w_p, w_ T, w _h, w_wind and w_uv are weight values corresponding to the number of people, temperature, humidity, wind speed and ultraviolet rays respectively, P_N is the maximum load number of tourists at the place of the outdoor leisure fishery tour area, and different places correspond to different values; t is the acquired temperature data, H is the acquired humidity data, wind is the acquired wind speed data, and uv is the ultraviolet data;
the destination selecting module is used for selecting a place with the highest fitness value T_S of the outdoor leisure fishery tour area as a destination;
and the path navigation module is used for navigating the tourist to the destination through the GPS.
6. The intelligent planning system based on big data of claim 5, wherein the unmanned aerial vehicle collects infrared images of outdoor leisure fishery tour areas at different heights in real time, and further comprising denoising the images by histogram equalization.
7. The intelligent planning system based on big data according to claim 5, wherein the highest occurrence frequency of the number of persons detected in the N infrared images is the number K of persons of the tourists in the current shooting area, and for each image with a height, there is a number count, the number with the highest occurrence probability is selected as the final number, and when the probabilities are equal, the number of persons in the image with the middle height is selected as the final number.
8. The intelligent data-based planning system of claim 5, wherein said communicating component analysis is performed on binary images to detect and count individual bright areas, each bright area representing a person;
initializing, namely assigning a label to each pixel, and setting the labels of all pixels to 0 at the beginning to represent unlabeled pixels;
a first scanning pass, starting from the upper left corner of the image, scanning the whole image row by row and pixel by pixel; for each pixel, the pixels above and to the left of it are examined: skipping if the current pixel is a background pixel value of 0; if the upper pixel and the left pixel are background pixels, a new label is allocated to the current pixel; if one of the upper or left pixels is a foreground pixel value of 1, then the same label is assigned to the current pixel; if the upper and left pixels are foreground pixels but the labels are different, then the labels of the upper pixels are allocated to the current pixel, and the labels of the upper and left pixels are recorded to be equivalent;
combining the labels, namely combining the components with the same label according to the equivalent label relation recorded in the first scanning;
scanning the whole image again, distributing a final label for each pixel, and searching an equivalent label of each pixel label;
the number of unique tags in the image is calculated.
CN202311218574.1A 2023-09-20 2023-09-20 Intelligent planning method and system based on big data Pending CN117273251A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311218574.1A CN117273251A (en) 2023-09-20 2023-09-20 Intelligent planning method and system based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311218574.1A CN117273251A (en) 2023-09-20 2023-09-20 Intelligent planning method and system based on big data

Publications (1)

Publication Number Publication Date
CN117273251A true CN117273251A (en) 2023-12-22

Family

ID=89208745

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311218574.1A Pending CN117273251A (en) 2023-09-20 2023-09-20 Intelligent planning method and system based on big data

Country Status (1)

Country Link
CN (1) CN117273251A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105574488A (en) * 2015-12-07 2016-05-11 北京航空航天大学 Low-altitude aerial infrared image based pedestrian detection method
CN111210369A (en) * 2019-12-19 2020-05-29 安徽逻根农业科技有限公司 Intelligent tourism service system based on Internet of things
CN111488522A (en) * 2020-04-07 2020-08-04 湘潭大学 Personalized multidimensional scenic spot recommendation method
CN111985466A (en) * 2020-08-19 2020-11-24 上海海事大学 Container dangerous goods mark identification method
CN113034399A (en) * 2021-04-01 2021-06-25 江苏科技大学 Binocular vision based autonomous underwater robot recovery and guide pseudo light source removing method
WO2022217685A1 (en) * 2021-04-13 2022-10-20 海南云端信息技术有限公司 Method and system for intelligent path planning of tourist attractions

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105574488A (en) * 2015-12-07 2016-05-11 北京航空航天大学 Low-altitude aerial infrared image based pedestrian detection method
CN111210369A (en) * 2019-12-19 2020-05-29 安徽逻根农业科技有限公司 Intelligent tourism service system based on Internet of things
CN111488522A (en) * 2020-04-07 2020-08-04 湘潭大学 Personalized multidimensional scenic spot recommendation method
CN111985466A (en) * 2020-08-19 2020-11-24 上海海事大学 Container dangerous goods mark identification method
CN113034399A (en) * 2021-04-01 2021-06-25 江苏科技大学 Binocular vision based autonomous underwater robot recovery and guide pseudo light source removing method
WO2022217685A1 (en) * 2021-04-13 2022-10-20 海南云端信息技术有限公司 Method and system for intelligent path planning of tourist attractions

Similar Documents

Publication Publication Date Title
CN110363140B (en) Human body action real-time identification method based on infrared image
CN110956094B (en) RGB-D multi-mode fusion personnel detection method based on asymmetric double-flow network
CN109858388A (en) A kind of intelligent tourism management system
CN109522793A (en) More people's unusual checkings and recognition methods based on machine vision
CN110246141B (en) Vehicle image segmentation method based on joint corner pooling under complex traffic scene
CN108334847A (en) A kind of face identification method based on deep learning under real scene
CN107622258A (en) A kind of rapid pedestrian detection method of combination static state low-level image feature and movable information
CN114049477B (en) Fish passing fishway system and dynamic identification and tracking method for fish quantity and fish type
CN110163041A (en) Video pedestrian recognition methods, device and storage medium again
CN113255589B (en) Target detection method and system based on multi-convolution fusion network
CN109145708A (en) A kind of people flow rate statistical method based on the fusion of RGB and D information
CN112347933A (en) Traffic scene understanding method and device based on video stream
CN112668375A (en) System and method for analyzing tourist distribution in scenic spot
CN111553321A (en) Mobile vendor target detection model, detection method and management method thereof
CN114241511A (en) Weak supervision pedestrian detection method, system, medium, equipment and processing terminal
CN113011371A (en) Target detection method, device, equipment and storage medium
CN112465854A (en) Unmanned aerial vehicle tracking method based on anchor-free detection algorithm
CN107045630B (en) RGBD-based pedestrian detection and identity recognition method and system
CN117593766B (en) Investigation method for wild animal population number based on unmanned aerial vehicle shooting image processing
CN117273251A (en) Intelligent planning method and system based on big data
CN116958643A (en) Air-borne pollen sensitized plant intelligent identification method based on YOLO network
CN110929739A (en) Automatic impervious surface range remote sensing iterative extraction method
CN114550016B (en) Unmanned aerial vehicle positioning method and system based on context information perception
CN116311357A (en) Double-sided identification method for unbalanced bovine body data based on MBN-transducer model
CN111950586B (en) Target detection method for introducing bidirectional attention

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination