Intelligent CCTV installed on Hoist at a construction site and Management System of the Number of Workers Including thereof

Abstract

A CCTV installed inside a hoist at a construction site comprises: a shooting unit that captures the interior of the hoist to generate hoist video data; a passenger count calculation model that outputs passenger count data, which is data regarding the number of passengers on board the hoist, using the hoist video data; a floor count calculation model that outputs floor count data, which is data regarding the floor number where the hoist is located, using the hoist video data; and a first communication unit that transmits the hoist video data, the passenger count data, and the floor count data to calculate the number of workers per floor at the construction site.

Description

Technology Field

[0001] This specification relates to an intelligent CCTV installed on a hoist at a construction site and a construction site worker management system including the same. Background Technology

[0002] In general, since various processes can proceed simultaneously at different locations with a large workforce at construction sites, management and safety management are required for the personnel deployed to each process or location.

[0003] In particular, large-scale construction sites employ workers from various fields to carry out processes; however, since the number of managers is relatively small compared to the number of workers, a system is required to more efficiently track the location of workers for safety management. The problem to be solved

[0004] The technical objective of the present invention is to provide an intelligent CCTV installed on a hoist at a construction site that identifies the number of workers on each floor of the construction site in real time and efficiently manages the number of workers at the construction site, and a construction site worker management system including the same. means of solving the problem

[0005] An intelligent CCTV installed on a hoist at a construction site according to one embodiment of the present invention comprises: a shooting unit that captures the interior of the hoist to generate hoist video data; a passenger count calculation model that generates passenger count data, which is data regarding the number of passengers on board the hoist, using the hoist video data; a floor count calculation model that calculates floor count data, which is data regarding the number of floors where the hoist is located, using the hoist video data; and a first communication unit that transmits the hoist video data, the passenger count data, and the floor count data to calculate the number of workers per floor at the construction site.

[0006] A construction site worker management system according to one embodiment of the present invention, comprising an intelligent CCTV installed on a hoist at a construction site, wherein the intelligent CCTV is installed on the upper interior of the hoist; and the intelligent CCTV comprises: a shooting unit that captures the interior of the hoist to generate hoist video data; a passenger calculation model that generates passenger data, which is data regarding the number of passengers on board the hoist, using the hoist video data; a floor calculation model that calculates floor data, which is data regarding the number of floors where the hoist is located, using the hoist video data; and a first communication unit that transmits the hoist video data, the passenger data, and the floor data. Effects of the invention

[0007] The intelligent CCTV installed on a hoist at a construction site according to the present invention and the construction site worker management system including the same can efficiently manage the workers at a construction site by calculating the number of personnel on the hoist based on the floor where the hoist is located and identifying the number of workers on each floor of the construction site in real time, and can identify the remaining personnel on each floor of the construction site in the event of an evacuation situation.

[0008] The intelligent CCTV installed on a hoist at a construction site according to the present invention and the construction site worker management system including the same capture the inside of the hoist through a fisheye lens having a field of view of 180 degrees or more, so that no blind spots occur inside the hoist, allowing for a more accurate calculation of the number of personnel on the hoist. Brief explanation of the drawing

[0009] FIG. 1 is a drawing showing a construction site worker management system including a hoist equipped with an intelligent CCTV according to one embodiment of the present invention. FIG. 2 is a block diagram showing the configuration of a worker management system including a hoist equipped with an intelligent CCTV according to one embodiment of the present invention. FIG. 3 is a drawing showing an intelligent CCTV according to one embodiment of the present invention. Figure 4a is a diagram showing hoist video data captured by an intelligent CCTV including a standard lens. FIG. 4b is a diagram showing hoist image data captured by an intelligent CCTV including a fisheye lens according to one embodiment of the present invention. FIG. 5 is a drawing showing an example of a screen displayed on a display unit of a construction site worker management system according to one embodiment of the present invention. FIG. 6 is a flowchart of a construction site worker management method according to one embodiment of the present invention. FIGS. 7a and 7b are exemplary drawings for explaining a method of managing workers by floor using a construction site worker management system according to an embodiment of the present invention. Specific details for implementing the invention

[0010] Throughout the specification, identical reference numbers denote substantially identical components. In the following description, detailed descriptions of components and functions known in the art may be omitted if they are not related to the core components of the invention. The meanings of the terms described in this specification should be understood as follows.

[0011] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims.

[0012] The shapes, sizes, ratios, angles, numbers, etc. disclosed in the drawings for explaining embodiments of the present invention are exemplary, and therefore the present invention is not limited to the depicted details. Throughout the specification, the same reference numerals refer to the same components. Furthermore, in describing the present invention, if it is determined that a detailed description of related known technology may unnecessarily obscure the essence of the present invention, such detailed description is omitted.

[0013] Where terms such as 'comprising,' 'having,' 'consisting of,' etc. are used in this specification, other parts may be added unless 'only' is used. Where a component is expressed in the singular, it includes cases where it is included in the plural unless specifically stated otherwise.

[0014] In interpreting the components, they are interpreted to include a margin of error even in the absence of a separate explicit statement.

[0015] In the case of an explanation of a temporal relationship, for example, when a temporal sequence is explained using 'after', 'following', 'next', 'before', etc., it may include cases where the sequence is not continuous unless 'immediately' or 'directly' is used.

[0016] Although terms such as "first," "second," etc. are used to describe various components, these components are not limited by these terms. These terms are used merely to distinguish one component from another. Accordingly, the first component mentioned below may be the second component within the technical scope of the present invention.

[0017] The term “at least one” should be understood to include all combinations that can be presented from one or more related items. For example, the meaning of “at least one of the first item, the second item and the third item” may mean not only the first item, the second item or the third item individually, but also all combinations of items that can be presented from two or more of the first item, the second item and the third item.

[0018] The features of each of the various embodiments of the present invention may be combined or combined with one another, either partially or wholly, and may technically enable various interlocking and operation. Each embodiment may be implemented independently of one another or may be implemented together in an associated relationship.

[0019] Hereinafter, a construction site worker management system according to an embodiment of the present invention will be described in detail with reference to FIGS. 1 to 5.

[0020] FIG. 1 is a drawing showing a construction site worker management system including a hoist equipped with an intelligent CCTV according to an embodiment of the present invention, and FIG. 2 is a block diagram showing the configuration of a worker management system including a hoist equipped with an intelligent CCTV according to an embodiment of the present invention. FIG. 3 is a drawing showing an intelligent CCTV according to an embodiment of the present invention. FIG. 4a is a drawing showing hoist video data captured by an intelligent CCTV including a standard lens, and FIG. 4b is a drawing showing hoist video data captured by an intelligent CCTV including a fisheye lens according to an embodiment of the present invention. FIG. 5 is a drawing showing a screen displaying the personnel status of a construction site worker management system according to an embodiment of the present invention.

[0021] Referring to FIGS. 1 and 2, a construction site worker management system (10) according to one embodiment of the present invention includes a hoist (100), an intelligent CCTV (200) installed inside the hoist (100), and a server (300) that processes information output from the intelligent CCTV.

[0022] A hoist (100) is a type of elevator installed on the outer wall of a construction site to move people or transport cargo. That is, the hoist (100) moves people or transports cargo to each floor of the construction site, and according to one embodiment of the present invention, an intelligent CCTV (200) to be described later is installed inside the hoist (100), and the number of people moving to each floor can be filmed and analyzed through the intelligent CCTV to identify the number of workers working on each floor of the construction site.

[0023] The intelligent CCTV (200) can photograph and analyze people moving to each floor of the construction site via the hoist (100), calculate the number of workers who have moved from the hoist (100) to each floor or from each floor to the hoist (100), and output this to the server (300). Specifically, as described above, the intelligent CCTV (200) is installed on the upper part of the inside of the hoist (100) to photograph the inside of the hoist (100) to generate hoist video data, and can output the number of people on board the hoist (100) and the number of floors where the hoist (100) is located using the generated hoist video data. To this end, as shown in FIGS. 2 and 3, the intelligent CCTV (200) includes a shooting unit (210), a number of people calculation model (220), a number of floors calculation model (230), and a first communication unit (240).

[0024] The shooting unit (210) includes a camera module and generates hoist image data that captures the interior of the hoist (100). In particular, according to one embodiment of the present invention, the camera module of the shooting unit (210) may include a fisheye lens so that no blind spot occurs inside the hoist (100). Since a standard lens has a field of view of 40 to 60 degrees and a wide-angle lens has a field of view of 60 to 80 degrees, when the interior of the hoist (100) is captured using the shooting unit (210) that includes a standard lens or a wide-angle lens, as shown in FIG. 4a, some of the passengers on the hoist (100) may be located in a blind spot and may not be captured by the shooting unit (210). Accordingly, when the inside of the hoist (100) is photographed using a shooting unit (210) including a standard lens or a wide-angle lens, the number of passengers calculated using the hoist image data generated by the shooting unit (210) may differ from the actual number of passengers. On the other hand, since a fisheye lens has a field of view of 180 degrees or more, when the inside of the hoist (100) is photographed using an intelligent CCTV (200) including a fisheye lens as shown in FIG. 4b, there are no blind spots, so the number of passengers on the hoist (100) can be calculated more accurately.

[0025] The passenger count calculation model (220) outputs passenger count data, which is data regarding the number of passengers on board the hoist (100), using hoist image data generated by the shooting unit (210). According to one embodiment of the present invention, the passenger count calculation model (220) receives a plurality of learned hoist image data captured by a fisheye lens and is trained to output passenger count data, which is data regarding the number of passengers captured as being on board each learned hoist image data. At this time, the passenger count calculation model (220) may include a learned real-time object detection model, and for example, the passenger count calculation model (220) may include a learned YOLOv4-tiny model.

[0026] The passenger count calculation model (220) receives hoist image data for each frame from a shooting unit (210) including a fisheye lens, detects at least one of a passenger (A1) or a safety helmet (A2) included in each frame as shown in FIG. 4b, calculates the number of passengers on board the hoist (100), and outputs the passenger count data. That is, the passenger count calculation model (220) can calculate the number of passengers on board the hoist (100) by detecting the passenger (A1) included in each frame and calculating the number of detected passengers, or by detecting the safety helmet (A2) included in each frame and calculating the number of detected safety helmets. Alternatively, to calculate the number of passengers on board the hoist (100) more accurately, the passenger count calculation model (220) calculates the number of detected passengers by detecting the passenger (A1) included in each frame, and calculates the number of detected safety helmets by detecting the safety helmet (A2) included in each frame. The passenger count calculation model (220) compares the calculated number of passengers with the calculated number of safety helmets, and if the number of passengers and the number of safety helmets have the same value, the value is determined as the passenger count data, and if the number of passengers and the number of safety helmets have different values, either the number of passengers or the number of safety helmets is determined as the passenger count data.

[0027] Alternatively, according to another embodiment of the present invention, the passenger count calculation model (220) may receive hoist image data from the shooting unit (210) for each frame to detect a passenger, determine whether the detected passenger is the same passenger as the passenger detected in the previous frame, and then object track the passenger to determine whether the passenger has crossed a specific boundary line based on a specific boundary line located adjacent to the entrance of the hoist (100) in each frame, thereby determining the passenger's entry into the hoist (100) and calculating the number of people on board the hoist (100).

[0028] The floor number calculation model (230) receives hoist image data generated by the shooting unit (210) and outputs floor number data, which is data regarding the floor where the hoist (100) is located. To this end, the floor number calculation model (230) receives multiple learning hoist image data captured by a fisheye lens and is trained to output floor number data, which is data regarding the floor where the hoist (100) is located in each learning hoist image data. At this time, the floor number calculation model (230) may include a learned real-time object detection model, and for example, the floor number calculation model (230) may include a learned YOLOv4-tiny model.

[0029] The learned floor number calculation model (230) receives hoist image data generated by the capturing unit (210) for each frame and, as shown in FIG. 4b, detects a number (B) included in each frame and determines it as floor number data. At this time, if two or more numbers are detected in one frame, the floor number calculation model (230) can determine the order of each detected number using the coordinates of each detected number. For example, the floor number calculation model (230) can combine each number in order from a number with a larger y-axis coordinate to a number with a smaller y-axis coordinate, or combine each number in order from a number with a smaller x-axis coordinate to a number with a larger x-axis coordinate and determine the combined number as floor number data.

[0030] The first communication unit (240) is wirelessly connected to a server (200) located at a distance and can wirelessly transmit hoist video data, passenger data, and floor number data to the server (200). The first communication unit (240) can be connected to the server (300) via LoRa, NB-IoT, RF, Wi-Fi, LTE 4G, and 5G communication networks. To this end, the first communication unit (240) may include at least one of a LoRa communication module, an NB-IoT communication module, an RF communication module, a Wi-Fi communication module, an LTE 4G communication module, and a 5G communication module. Accordingly, the passenger calculation model (220) and the floor number calculation model (230) can wirelessly transmit hoist video data, passenger data, and floor number data to the server (200) through the first communication unit (240).

[0031] The server (300) can receive hoist video data, passenger data, and floor number data output from the intelligent CCTV (200) and provide information related to the construction site. Specifically, the server (300) calculates the number of workers per floor located on each floor of the construction site using the passenger data and floor number data output from the intelligent CCTV (200), and provides information regarding the calculated number of workers per floor. To this end, the server (300) includes a floor-by-floor worker calculation unit (310), a display unit (320), and a second communication unit (330).

[0032] The floor personnel calculation unit (310) calculates the number of personnel per floor of a construction site using the number of passengers output from the passenger calculation model (220) and the number of floors output from the number of floors calculation model (230). To do this, the floor personnel calculation unit (310) compares the previous passenger data with the passenger data output from the passenger calculation model (220) to calculate the change in the number of passengers on the hoist (100) at the floor where the hoist (100) is located. Specifically, the number of workers changes by the amount of the change in the number of passengers at each floor. If the number of passengers at a corresponding floor increases by the amount of the change in the number of passengers, the number of workers on that floor decreases by the amount of the change in the number of passengers, and if the number of passengers decreases by the amount of the change in the number of passengers, the number of workers on that floor increases by the amount of the change in the number of passengers. For example, if the number of passengers decreases by 2 on a certain floor, resulting in a change in the number of passengers of -2, the number of workers on that floor increases by 2, resulting in a change in the number of workers of +2. In other words, if the previous number of passengers data is N1 (N1 is an integer), the current number of passengers data is N2 (N2 is an integer), and the current floor number data is F (F is an integer), the change in the number of passengers for floor F can be calculated as N2-N1, and the change in the number of workers can be calculated as -(N2-N1). When the previous number of workers for floor F is W1 (W1 is an integer) and the current number of workers data is W2 (W2 is an integer), the floor-specific personnel calculation unit (310) can calculate the current number of workers data W2 by adding the change in the number of workers -(N2-N1) to the previous number of workers data W1. That is, the current number of workers data W2 can be calculated as W1+(-(N2-N1)).

[0033] The display unit (320) can display information related to the construction site to the user. To this end, the display unit (320) may include a display device. In particular, according to one embodiment of the present invention, the display unit (320) displays hoist video data output from the shooting unit (210) and the number of workers per floor of the construction site calculated by the floor-by-floor personnel calculation unit (310) to the user. That is, as illustrated in FIG. 5, the display unit (320) displays the hoist video data output from the shooting unit (210) in real time and displays the number of workers per floor calculated in real time by the floor-by-floor personnel calculation unit (310) to provide the user with information regarding the status of the number of workers at the construction site.

[0034] Although the drawing shows the display unit (320) configured to be included in the server (300), it is not limited thereto, and the display unit (320) may be configured separately from the server (300) and may be connected to the server (300) via wired or wireless communication.

[0035] The second communication unit (330) is wirelessly connected to the intelligent CCTV (200) to receive hoist video data, passenger data, and floor number data. The second communication unit (330) can be wirelessly connected to the intelligent CCTV (200) via LoRa, NB-IoT, RF, Wi-Fi, LTE 4G, and 5G communication networks. To this end, the second communication unit (330) may include at least one of a LoRa communication module, an NB-IoT communication module, an RF communication module, a Wi-Fi communication module, an LTE 4G communication module, and a 5G communication module. Accordingly, the floor-by-floor passenger calculation unit (310) and the display unit (320) receive hoist video data, passenger data, and floor number data through the second communication unit (330).

[0036] Additionally, although not shown, the server (300) may further include a database that stores information related to the construction site. Specifically, the database may store hoist video data, current floor number data, data on the number of people currently on the hoist, data on the number of workers per floor, etc.

[0037] Hereinafter, with reference to FIGS. 6 to 7b, a method for managing construction site workers according to an embodiment of the present invention will be described in detail.

[0038] FIG. 6 is a flowchart of a method for managing construction site personnel according to an embodiment of the present invention, and FIG. 7a and FIG. 7b are example drawings for explaining a method for managing personnel by floor using a construction site personnel management system according to an embodiment of the present invention.

[0039] Referring to FIG. 6, a shooting unit (210) installed at the top inside the hoist (100) photographs the inside of the hoist (100) (s610). The shooting unit (210) photographs the inside of the hoist (100) to generate hoist image data. At this time, as described above, the shooting unit (210) includes a camera module equipped with a fisheye lens having a field of view of 180 degrees or more, so the inside of the hoist (100) can be photographed without blind spots. Accordingly, the shooting unit (210) can photograph all the people on board the hoist (100) and the floor where the hoist (100) is located, and generate hoist image data that includes all the people on board and the floor.

[0040] The passenger count calculation model (220) generates passenger count data on the hoist (100) using hoist video data (s621). Specifically, the passenger count calculation model (220) receives hoist video data from the shooting unit (210) for each frame, detects at least one of the passengers or safety helmets included in each frame, calculates the number of passengers on the hoist (100), and determines the number of passengers as passenger count data. That is, the passenger count calculation model (220) can calculate the number of passengers on the hoist (100) by detecting the passengers included in each frame and calculating the number of detected passengers, or by detecting the safety helmets included in each frame and calculating the number of detected safety helmets. Alternatively, the passenger count calculation model (220) detects the passenger (A1) included in each frame to calculate the number of detected passengers and detects the safety helmet (A2) included in each frame to calculate the number of detected safety helmets in order to calculate the number of passengers more accurately. The passenger count calculation model (220) compares the calculated number of passengers with the calculated number of safety helmets, and if the number of passengers and the number of safety helmets have the same value, it determines that value as passenger count data, and if the number of passengers and the number of safety helmets have different values, it determines either the number of passengers or the number of safety helmets as passenger count data. For example, in the case of the situation illustrated in FIG. 7a, the passenger count calculation model (220) of the intelligent CCTV (200) can detect a passenger (W) using frame-by-frame hoist video data received from the shooting unit (210) and determine the detected passenger number "1" as the passenger count data, and in the case of the situation illustrated in FIG. 7b, the passenger count calculation model (220) of the intelligent CCTV (200) can detect a passenger using frame-by-frame hoist video data received from the shooting unit (210) and determine the detected passenger number "0" as the passenger count data.

[0041] Additionally, according to another embodiment of the present invention, the passenger count calculation model (220) receives hoist image data from the shooting unit (210) for each frame, performs object tracking on the passenger to determine if it is the same passenger as the one detected in the previous frame, and then determines whether the passenger has crossed a specific boundary line based on the entrance / exit side of the hoist (100) in each frame to determine the entry / exit of the passenger (100), and using this, calculates the number of people riding on the hoist (100) as passenger count data.

[0042] The floor number calculation model (230) generates floor number data by calculating the floor where the hoist (100) is located using hoist image data (s622). Specifically, the floor number calculation model (230) receives hoist image data for each frame from the capturing unit (210), detects the number included in each frame, calculates the floor where the hoist (100) is located, and outputs floor number data. For example, in the situation illustrated in FIG. 7a, the floor number calculation model (230) can detect the number "2" (F1) in the hoist image data for each frame and determine the detected "2" as floor number data, and in the situation illustrated in FIG. 7b, the floor number calculation model (230) can detect "5" (F2) in the hoist image data for each frame and determine the detected "5" as floor number data. Meanwhile, when two or more numbers are detected in one frame, the floor number calculation model (230) can determine the order of each detected number using the coordinates of each detected number. For example, the floor number calculation model (230) can combine each number in order from the number with the larger y-axis coordinate to the number with the smaller y-axis coordinate, or combine each number in order from the number with the smaller x-axis coordinate to the number with the larger x-axis coordinate, and determine the combined number as floor number data.

[0043] Afterward, the floor personnel calculation unit (310) updates the floor number data with the floor number data output from the floor number calculation model (230) (s630). For example, if the situation shown in FIG. 7a changes to the situation shown in FIG. 7b, the floor personnel calculation unit (310) updates the floor number data, which was 2nd floor (F1), to 5th floor (F2) output from the floor number calculation model (230).

[0044] Afterward, the floor-by-floor personnel calculation unit (310) compares the previous passenger data with the passenger data output from the passenger calculation model (220) to calculate the change in the number of passengers on the hoist (100) at the current floor (s640). Specifically, if the previous passenger data is N1 (N1 is an integer), the current passenger data is N2 (N2 is an integer), and the current floor data is F (F is an integer), the change in the number of passengers for floor F can be calculated as N2-N1. For example, if the situation shown in FIG. 7a changes to the situation shown in FIG. 7b, the floor-by-floor personnel calculation unit (310) calculates the change in the number of passengers as -1 because the number of passengers on the hoist (100) at the 5th floor (F2) has changed from 1 to 0.

[0045] Afterward, the floor personnel calculation unit (310) calculates the number of workers for the hoist (100) on the corresponding floor using the calculated passenger change value (s650). The number of workers changes by the amount of the passenger change value at each floor. If the number of passengers at the corresponding floor increases by the amount of the passenger change value, the number of workers on that floor decreases by the amount of the passenger change value, and if the number of passengers decreases by the amount of the passenger change value, the number of workers on that floor increases by the amount of the passenger change value. Specifically, when the previous number of workers data for floor F is W1 (W1 is an integer) and the number of workers data is W2 (W2 is an integer), the floor personnel calculation unit (310) can calculate a number of workers change value that has the same amount as the passenger change value and has the opposite sign. In other words, if the previous passenger data is N1 (N1 is an integer), the current passenger data is N2 (N2 is an integer), and the current floor data is F (F is an integer), the passenger change value for floor F can be calculated as N2-N1, the work personnel change value can be calculated as -(N2-N1), and the floor personnel calculation unit (310) can calculate the current work personnel data W2 by adding the work personnel change value -(N2-N1) to the previous work personnel data W1. That is, the current work personnel data W2 can be calculated as W1+(-(N2-N1)). For example, when the situation shown in FIG. 7a changes to the situation shown in FIG. 7b, as described above, the floor personnel calculation unit (310) determines that the number of workers located on the 5th floor (F2) has increased by 1 (+1) as the number of workers on the hoist (100) has decreased by 1 (-1), and calculates the number of workers located on the 5th floor (F2) as the value of the previous number of workers plus (-(-1)) to update the number of workers on that floor.

[0046] By repeating steps s610 to s650, the number of workers on each floor can be determined in real time.

[0047] Afterwards, the number of workers per floor is updated in real time using the display unit (320), and the number of workers per floor is saved in the database (s660).

[0048] Those skilled in the art to which the present invention pertains will understand that the above-described invention may be implemented in other specific forms without altering its technical concept or essential features.

[0049] Additionally, the methods described herein may be implemented at least partially using one or more computer programs or components. These components may be provided as a series of computer instructions via a computer-readable or machine-readable medium including volatile and non-volatile memory. The instructions may be provided as software or firmware and may be implemented wholly or partially in hardware configurations such as ASICs, FPGAs, DSPs, or other similar devices. The instructions may be configured to be executed by one or more processors or other hardware configurations, which perform or are capable of performing all or part of the methods and procedures disclosed herein when executing the series of computer instructions.

[0050] Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. The scope of the invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the invention. Explanation of the symbols

[0051] 10: Construction Site Workforce Management System 100: Hoist 200: Intelligent CCTV 210: Camera Unit 220: Passenger Capacity Calculation Model 230: Floor Count Calculation Model 300: Server 310: Personnel Calculation by Floor 320: Display section

Claims

Claim 1 A CCTV installed inside a hoist at a construction site comprises: a shooting unit that captures the interior of the hoist through a fisheye lens to generate hoist image data; a passenger count calculation model that outputs passenger count data, which is data regarding the number of passengers on board the hoist, using the hoist image data captured through the fisheye lens; a floor count calculation model that outputs floor count data, which is data regarding the floor number where the hoist is located, using the hoist image data captured through the fisheye lens; and a first communication unit that transmits the passenger count data and the floor count data to a server to calculate the number of workers per floor at the construction site.The above passenger count calculation model includes, for each frame, detects passengers included in the hoist video data to calculate the number of passengers, detects safety helmets included in the hoist video data to calculate the number of safety helmets, and if the number of passengers and the number of safety helmets have the same value, outputs that value as the passenger count data; the above floor count calculation model outputs as the floor count data a number formed by combining numbers in the order from the number with the larger y-axis coordinate to the number with the smaller y-axis coordinate, or from the number with the smaller x-axis coordinate to the number with the larger x-axis coordinate, if two or more numbers are detected in the hoist video data for each frame; the above passenger count calculation model determines whether the passenger detected for each frame is the same passenger detected in the previous frame, then performs object tracking on the passenger to determine whether the passenger has crossed a specific boundary line based on a specific boundary line located adjacent to the hoist entrance in each frame, thereby determining the passenger's entry into the hoist; and the above passenger count calculation model and the above floor count calculation model An intelligent CCTV installed on a hoist at a construction site, characterized by receiving multiple learning hoist video data generated by capturing through the fisheye lens and being trained to output passenger data and floor number data, respectively. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete Claim 6 delete Claim 7 delete Claim 8 delete Claim 9 delete Claim 10 A construction site worker management system including a CCTV installed on a hoist at a construction site comprises: an intelligent CCTV that captures the interior of the hoist to generate hoist video data and outputs passenger data, which is data regarding personnel on the hoist, and floor data, which is data regarding the floor where the hoist is located; wherein the intelligent CCTV comprises: a shooting unit that captures the interior of the hoist through a fisheye lens to generate the hoist video data; a passenger calculation model that outputs the passenger data using the hoist video data captured through the fisheye lens; a floor calculation model that outputs the floor data using the hoist video data captured through the fisheye lens; and a first communication unit that transmits the passenger data and the floor data.The above passenger count calculation model includes, for each frame, detects passengers included in the hoist video data to calculate the number of passengers, detects safety helmets included in the hoist video data to calculate the number of safety helmets, and if the number of passengers and the number of safety helmets have the same value, outputs that value as the passenger count data; the above floor count calculation model outputs as the floor count data a number formed by combining numbers in the order from the number with the larger y-axis coordinate to the number with the smaller y-axis coordinate, or from the number with the smaller x-axis coordinate to the number with the larger x-axis coordinate, if two or more numbers are detected in the hoist video data for each frame; the above passenger count calculation model determines whether the passenger detected for each frame is the same passenger detected in the previous frame, then performs object tracking on the passenger to determine whether the passenger has crossed a specific boundary line based on a specific boundary line located adjacent to the hoist entrance in each frame, thereby determining the passenger's entry into the hoist; and the above passenger count calculation model and the above floor count calculation model A construction site worker management system characterized by receiving multiple learning hoist video data captured through the fisheye lens and learning to output passenger data and floor number data, respectively. Claim 11 A construction site worker management system characterized by further including, in claim 10, a server unit that calculates a change value of the passenger data corresponding to the floor number data using the passenger data and floor number data received from the first communication unit, and calculates the number of workers per floor of the construction site. Claim 12 A construction site worker management system including a hoist equipped with an intelligent CCTV, wherein, in claim 10, the server unit calculates a change value of the passenger data corresponding to the floor data using the passenger data and floor data received from the first communication unit, and calculates the number of workers per floor of the construction site; wherein, when the previous passenger data is N1 (N1 is an integer), the passenger data is N2 (N2 is an integer), the floor data is F (F is an integer), the previous worker data of floor F is W1 (W1 is an integer), and the worker data is W2 (W2 is an integer), the server unit calculates the change value of the passenger as N2-N1 and calculates the change value of the worker data of floor F as -(N2-N1), and calculates the worker data (W2) of floor F by adding the change value of the worker data -(N2-N1) to the previous worker data W1. Claim 13 delete Claim 14 delete Claim 15 delete Claim 16 delete Claim 17 delete

Images