CN117994915A

CN117994915A - AI activity tracking detection method and device for intelligent building site

Info

Publication number: CN117994915A
Application number: CN202410082237.2A
Authority: CN
Inventors: 陈丽芳; 杨伟健; 陆静霞; 阙炜华
Original assignee: Luban Guangdong Technology Co ltd
Current assignee: Luban Guangdong Technology Co ltd
Priority date: 2024-01-19
Filing date: 2024-01-19
Publication date: 2024-05-07

Abstract

The embodiment of the invention discloses an AI activity tracking detection method and device for an intelligent building site, comprising the following steps: collecting image data and equipment operation data of a target monitoring area; identifying object features and picture scenes in the image data based on the image data, acquiring corresponding image reference features according to the picture scenes, and comparing the object features with the image reference features; processing equipment operation data to obtain operation characteristics, and comparing the operation characteristics with preset operation reference characteristics; and generating early warning information or correction information when the information is inconsistent. According to the embodiment, the data are automatically collected through the equipment, the automatic supervision is realized, the intelligent processing, analysis and monitoring are carried out through the AI, the real-time observation of monitoring is not needed, manual patrol is not needed, the labor cost is greatly reduced, early warning information or correction information is timely given to abnormal conditions, timely prevention and control processing is facilitated for environmental safety and equipment operation safety, and the management efficiency is improved.

Description

AI activity tracking detection method and device for intelligent building site

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to an AI activity tracking detection method and device for an intelligent building site.

Background

At present, along with the continuous development of engineering construction, the scale of a construction site is larger and larger, a large number of personnel are needed to participate, the field environment is complex, and therefore the difficulty of control and security of the construction site is larger and larger. The field construction environment of the construction site is not separated from various construction operation behaviors of workers, and the operation of various equipment is not separated from manual supervision. The collection of the operation condition information of workers and the effective supervision of equipment are not only related to the construction efficiency, but also related to the construction safety. In the related art, the video monitoring can detect and identify the differences of vehicles, people or construction tools and the like on a construction site, but cannot identify dangerous operation and construction progress on the construction site, at present, workers are mainly used for carrying out patrol inspection on the construction site regularly, the efficiency is low, the first time cannot be found when a problem exists, and further the problem can not be solved in time, so that property loss is caused.

Disclosure of Invention

Aiming at the defects, the embodiment of the invention discloses an AI activity tracking detection method for an intelligent construction site, which is high in efficiency by AI intelligent monitoring of the construction site.

The first aspect of the embodiment of the invention discloses an AI activity tracking detection method for an intelligent building site, which comprises the following steps:

Collecting image data and equipment operation data of a target monitoring area;

Identifying object features and picture scenes in the image data based on the image data, acquiring corresponding image reference features according to the picture scenes, and comparing the object features with the image reference features;

processing the equipment operation data to obtain operation characteristics, and comparing the operation characteristics with preset operation reference characteristics;

and generating early warning information or correction information when the object characteristic is inconsistent with the image reference characteristic and/or when the operation characteristic is inconsistent with the operation reference.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, the object features include a character feature and an environmental feature; comparing the object features with image reference features, comprising:

Analyzing the environmental characteristics, checking whether the environmental characteristics contain at least one character characteristic, and comparing whether the image reference characteristics contain character characteristics;

And when the image reference feature contains the character feature, extracting a first feature point and a second feature point of the character feature in the picture feature, and comparing the first feature point and the second feature point with the image reference feature respectively.

In a first aspect of the embodiment of the present invention, when the picture scene is a tower crane hook, processing the device operation data to obtain an operation feature, and comparing the operation feature with a preset operation reference feature, where the method includes:

continuously acquiring hook azimuth information in equipment operation data, and generating a hook movement track and a variation amplitude value;

and predicting a lifting hook target destination based on the lifting hook moving track, the variation amplitude value and the lifting tower height in the lifting hook azimuth information, and comparing the lifting hook target destination with a preset operation reference characteristic.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, when the picture scene is an elevator, comparing the object feature with the image reference feature includes:

checking whether the object features have face features or not;

Acquiring the number of people when the face features exist, checking whether the operation authority is provided or not based on the face features, and stopping the operation of the lifter when the operation authority is not provided;

The number of people is compared with the number features in the image reference features, and the weight features in the object features are compared with the weight features in the image reference features.

In a first aspect of the embodiment of the present invention, the device operation data includes inclination angle data, altitude data, and wind speed data, the processing the device operation data to obtain an operation feature, and comparing the operation feature with a preset operation reference feature includes:

Processing the inclination angle data, the height data and the wind speed data to obtain operation characteristics of the elevator, wherein the operation characteristics comprise wind speed influence quantity and inclination characteristics of current height data and the inclination angle data;

And respectively comparing the wind speed influence quantity and the inclination characteristic with a preset operation reference characteristic.

In a first aspect of the embodiment of the present invention, when the picture scene is the unloading platform, the collected device operation data includes load data, operation state data, and energy consumption data; the processing the device operational data to obtain operational characteristics includes:

And processing the load data to obtain weight characteristics, and obtaining operation comparison data according to the operation state data and the energy consumption data when the weight characteristics accord with the load threshold range.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, the method further includes:

and acquiring open fire data through an open fire sensor, acquiring a temperature contour map of the supervision area when the open fire data is determined to be on fire, acquiring a target area meeting the temperature of a fire point in the supervision area based on the temperature contour map, and marking the target area as the fire point.

A second aspect of the embodiment of the present invention discloses an AI activity tracking and detecting device for an intelligent worksite, which is characterized by comprising:

And a data acquisition module: the device comprises a device and a monitoring unit, wherein the device is used for collecting image data and equipment operation data of a target monitoring area;

A first comparison module: the image processing method comprises the steps of identifying object features and picture scenes in image data based on the image data, acquiring corresponding image reference features according to the picture scenes, and comparing the object features with the image reference features;

A second comparison module: the device operation data processing module is used for processing the device operation data to obtain operation characteristics, and comparing the operation characteristics with preset operation reference characteristics;

an exception handling module: for generating pre-warning information or correction information when the object features are inconsistent with the image reference features and/or when the operating features are inconsistent with the operating reference.

As an alternative implementation manner, in the second aspect of the embodiment of the present invention, the object features include a character feature and an environmental feature; comparing the object features with image reference features, comprising:

In a second aspect of the embodiment of the present invention, when the picture scene is a tower crane hook, processing the device operation data to obtain an operation feature, and comparing the operation feature with a preset operation reference feature, where the processing includes:

In a second aspect of the present invention, when the picture scene is an elevator, comparing the object feature with the image reference feature includes:

checking whether the object features have face features or not;

In a second aspect of the embodiment of the present invention, the equipment operation data includes inclination angle data, altitude data and wind speed data, the processing the equipment operation data to obtain an operation feature, and comparing the operation feature with a preset operation reference feature includes:

In a second aspect of the embodiment of the present invention, when the picture scene is the unloading platform, the collected device operation data includes load data, operation state data, and energy consumption data; the processing the device operational data to obtain operational characteristics includes:

As an optional implementation manner, in the second aspect of the embodiment of the present invention, the method further includes:

A third aspect of an embodiment of the present invention discloses an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory for executing the AI activity tracking detection method for the intelligent worksite disclosed in the first aspect of the embodiment of the present invention.

A fourth aspect of the embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the AI activity tracking detection method of the smart worksite disclosed in the first aspect of the embodiment of the present invention.

Compared with the prior art, the embodiment of the invention has the following beneficial effects:

According to the embodiment of the invention, a site and equipment which are not stopped on a construction site are divided into different target monitoring areas according to set dividing conditions, a camera is arranged in each target monitoring area to collect image data, different sensors are arranged to collect equipment operation data, further, feature recognition and comparison are carried out based on the image data, processing and comparison of operation features are carried out based on the equipment operation data, whether the current target monitoring area is in an abnormal state or not is judged according to comparison results of the two operation features, the automatic supervision is realized through automatic acquisition of the data of the equipment, intelligent processing analysis and monitoring is carried out through AI, manual patrol is not needed, monitoring real-time observation is not needed, further, labor cost is greatly reduced, early warning information or correction information is timely given for abnormal conditions, timely prevention and control processing is facilitated for environmental safety and equipment operation safety, and management efficiency is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for detecting AI activity tracking at an intelligent worksite according to an embodiment of the invention;

FIG. 2 is a schematic flow chart of comparing object features with image reference features according to an embodiment of the present invention;

FIG. 3 is a schematic flow chart of processing equipment operation data to obtain operation characteristics, and comparing the operation characteristics with preset operation reference characteristics;

FIG. 4 is a schematic flow chart of comparing object features with image reference features according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of an AI activity tracking and detecting device for intelligent construction sites according to an embodiment of the invention;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

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.

It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present invention are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

The embodiment of the invention discloses an AI activity tracking detection method, an AI activity tracking detection device, an AI activity tracking detection electronic device and a storage medium for an intelligent construction site, wherein the construction site and the equipment are divided into different target monitoring areas according to set dividing conditions, a camera is arranged in each target monitoring area to collect image data, different sensors are arranged to collect equipment operation data, further, characteristic identification and comparison are carried out based on the image data, whether the current target monitoring area is in an abnormal state or not is judged based on the processing and comparison result of the equipment operation data, the automatic supervision is realized through the automatic acquisition data of the equipment, the intelligent processing analysis and the monitoring are carried out through AI, manual patrol is not needed, real-time monitoring is not needed, further, labor cost is greatly reduced, early warning information or correction information is timely given for abnormal conditions, timely prevention and control processing is facilitated for environmental safety and equipment operation safety, and management efficiency is improved.

Example 1

Referring to fig. 1, fig. 1 is a flowchart of an AI activity tracking detection method for an intelligent worksite according to an embodiment of the present invention. The execution main body of the method described in the embodiment of the invention is an execution main body composed of software or/and hardware, and the execution main body can receive related information in a wired or/and wireless mode and can send a certain instruction. Of course, it may also have certain processing and storage functions. The execution body may control a plurality of devices, such as a remote physical server or cloud server and related software, or may be a local host or server and related software that performs related operations on a device that is located somewhere, etc. In some scenarios, multiple storage devices may also be controlled, which may be located in the same location or in different locations than the devices. As shown in fig. 1, the AI activity tracking detection method for the intelligent construction site comprises the following steps:

101. Image data and equipment operation data of a target monitoring area are collected.

In the embodiment, the measurement and calculation can be performed on the construction site in advance according to the area of the site environment, and the target areas of different site areas are divided into different numbers of supervision areas. For example, the division of a relatively large target area into small areas for management can help with better and more accurate supervision. On the other hand, the functions of the construction site are divided into areas, and the areas with different functions are managed in a targeted and regional mode. For example, it is also possible to divide the area for different equipment, e.g. separate management for the elevators, separate management for the discharge platforms, etc. Instead of dividing the area, the entire worksite may be defined directly as the target monitoring area. At the moment, cameras and sensors are mainly applied to image acquisition and equipment operation data acquisition of a construction site. The target monitoring area at least comprises one camera, the number of the cameras is set according to the area size of the target monitoring area and the site arrangement condition, so that each place to be monitored is guaranteed to have no dead angle, manual naked eye patrol is replaced by the arrangement of the cameras, and digital, automatic and intelligent management is achieved.

102. And identifying object features and picture scenes in the image data based on the image data, acquiring corresponding image reference features according to the picture scenes, and comparing the object features with the image reference features.

The image data acquired by the camera typically contains the corresponding scene in the image, i.e. the shooting location, and different locations may correspond to different regulatory requirements, as well as object features, such as character features, device features, etc., for expressing for which type of device the monitored image is, or whether the scene is a person or animal, etc.

Specifically, in this step, the object features include a character feature and an environmental feature. At this time, as shown in fig. 2, comparing the object feature with the image reference feature includes:

201. analyzing the environmental characteristics, checking whether the environmental characteristics contain at least one character characteristic, and comparing whether the image reference characteristics contain character characteristics;

In the embodiment, although the picture information includes the environmental feature and the character feature, when the picture is processed and analyzed, the environmental feature is first analyzed to determine whether the character feature is included. When some supervision areas are regulated that personnel cannot enter privately, an alarm can be given if the character features appear. Or in the gate monitoring area of the scene, a large number of character features appear, possibly with risk of breeding, and the alarm can be given out as well, specifically according to the reference features set in different monitoring areas.

202. And when the image reference feature contains the character feature, extracting a first feature point and a second feature point of the character feature in the picture feature, and comparing the first feature point and the second feature point with the image reference feature respectively.

For construction sites, the wearing of workers often has strict requirements to ensure construction safety. The first feature point and the second feature point of the embodiment may each include one feature point, or may each include a plurality of feature points. Illustratively, the first feature point is the upper body garment and the second feature point is the head. The first characteristic points are used for comparing whether the worker is normal to wear the reflective clothing, and the second characteristic points are used for comparing whether the worker is normal to wear the safety helmet. In addition to the above feature points, the wearing and wearing may be used as the same first feature point, and the second feature point may be used to include whether or not the behavior of the worker is normal, for example, whether or not smoking is performed at the construction site, and so on.

In another example, when the picture scene is a tower crane hook, processing the device operation data to obtain an operation feature, and comparing the operation feature with a preset operation reference feature is shown in fig. 3, including:

301. Hook azimuth information in equipment operation data is continuously acquired, and a hook movement track and a variation amplitude value are generated. The hook azimuth information comprises a height position, a water level azimuth and the like, the current accurate position of the hook can be determined according to the hook azimuth information, further comparison is carried out according to the position to be actually operated, and a moving track and a moving change amplitude can be generated according to continuous position transformation of the current position of the hook and the last position and the like.

302. And predicting a lifting hook target destination based on the lifting hook moving track, the variation amplitude value and the lifting tower height in the lifting hook azimuth information, and comparing the lifting hook target destination with a preset operation reference characteristic.

In yet another example, when the picture scene is an elevator, as shown in fig. 4, comparing the object feature with the image reference feature includes:

401. and checking whether the face features exist in the object features.

The lifter on the construction site usually needs professional operators to control, so that potential safety hazards of equipment caused by misoperation of other people are avoided. The face features are checked, so that the face feature detection method can be used for counting the number of subsequent personnel and also can be used for checking the legality of operators.

402. And when the face features exist, the number of people is obtained, whether the operation authority is provided or not is checked based on the face features, and when the operation authority is not provided, the operation of the lifter is stopped.

403. The number of people is compared with the number features in the image reference features, and the weight features in the object features are compared with the weight features in the image reference features.

In an embodiment, for the control safety of the elevator, firstly, the operation is guaranteed to have operation authority, and secondly, the current operation safety of the elevator is considered from the number of people in the elevator and the whole weight. For example, it may be set that when one of the number of people or the weight exceeds a threshold, it is defined as unsafe.

In an embodiment, in monitoring an elevator, equipment operation data includes inclination angle data, altitude data, and wind speed data, and the processing the equipment operation data to obtain an operation feature, and comparing the operation feature with a preset operation reference feature includes: processing the inclination angle data, the height data and the wind speed data to obtain operation characteristics of the elevator, wherein the operation characteristics comprise wind speed influence quantity and inclination characteristics of current height data and the inclination angle data; and respectively comparing the wind speed influence quantity and the inclination characteristic with a preset operation reference characteristic. By carrying out AI automatic calculation and depth analysis on the collected parameters, whether the operation of the elevator is affected is analyzed by combining the current environmental factors. For example, when typhoons occur on a day, the inclination angle of the lifter is greatly larger than that of ordinary times, and is defined as abnormal, the lifter can be automatically controlled to stop running or descend to the bottom layer, and the like.

In another example, when the picture scene is a discharging platform, the collected equipment operation data comprises load data, operation state data and energy consumption data; the processing the device operational data to obtain operational characteristics includes: and processing the load data to obtain weight characteristics, and obtaining operation comparison data according to the operation state data and the energy consumption data when the weight characteristics accord with the load threshold range.

103. Processing the equipment operation data to obtain operation characteristics, and comparing the operation characteristics with preset operation reference characteristics.

104. And generating early warning information or correction information when the object characteristic is inconsistent with the image reference characteristic and/or when the operation characteristic is inconsistent with the operation reference.

In addition, the embodiment can monitor the environment of the target monitoring area, including collecting open fire data through an open fire sensor, collecting a temperature contour map of the monitoring area when the open fire data is determined to be on fire, and obtaining a target area meeting the temperature of the fire point in the monitoring area based on the temperature contour map, wherein the target area is marked as the fire point. The intelligent marking is carried out on the fire points, so that personnel can extinguish the fire more quickly, the property loss is reduced to the maximum extent, and the site can be saved most quickly.

Example two

Referring to fig. 5, fig. 5 is a schematic structural diagram of an AI activity tracking and detecting device for an intelligent worksite according to an embodiment of the present invention. As shown in fig. 5, the AI activity tracking detection apparatus of the smart worksite may include: the device comprises a data acquisition module 501, a first comparison module 502, a second comparison module 503 and an exception handling module 504, wherein the data acquisition module 501: the device comprises a device and a monitoring unit, wherein the device is used for collecting image data and equipment operation data of a target monitoring area; the first comparison module 502: the image processing method comprises the steps of identifying object features and picture scenes in image data based on the image data, acquiring corresponding image reference features according to the picture scenes, and comparing the object features with the image reference features; a second comparison module 503: the device operation data processing module is used for processing the device operation data to obtain operation characteristics, and comparing the operation characteristics with preset operation reference characteristics; exception handling module 504: for generating pre-warning information or correction information when the object features are inconsistent with the image reference features and/or when the operating features are inconsistent with the operating reference.

The object features include character features and environmental features. Comparing the object features with the image reference features, including: analyzing the environmental characteristics, checking whether the environmental characteristics contain at least one character characteristic, and comparing whether the image reference characteristics contain character characteristics; and when the image reference feature contains the character feature, extracting a first feature point and a second feature point of the character feature in the picture feature, and comparing the first feature point and the second feature point with the image reference feature respectively.

When the picture scene is a tower crane hook, processing the equipment operation data to obtain operation characteristics, and comparing the operation characteristics with preset operation reference characteristics, wherein the method comprises the following steps: continuously acquiring hook azimuth information in equipment operation data, and generating a hook movement track and a variation amplitude value; and predicting a lifting hook target destination based on the lifting hook moving track, the variation amplitude value and the lifting tower height in the lifting hook azimuth information, and comparing the lifting hook target destination with a preset operation reference characteristic.

When the picture scene is an elevator, comparing the object features with image reference features, including: checking whether the object features have face features or not; acquiring the number of people when the face features exist, checking whether the operation authority is provided or not based on the face features, and stopping the operation of the lifter when the operation authority is not provided; the number of people is compared with the number features in the image reference features, and the weight features in the object features are compared with the weight features in the image reference features.

When the target monitoring area is an elevator, the equipment operation data comprise inclination angle data, height data and wind speed data, the equipment operation data are processed to obtain operation characteristics, and the operation characteristics are compared with preset operation reference characteristics, and the method comprises the following steps: processing the inclination angle data, the height data and the wind speed data to obtain operation characteristics of the elevator, wherein the operation characteristics comprise wind speed influence quantity and inclination characteristics of current height data and the inclination angle data; and respectively comparing the wind speed influence quantity and the inclination characteristic with a preset operation reference characteristic.

When the picture scene is a discharging platform, the collected equipment operation data comprise load data, operation state data and energy consumption data; the processing the device operational data to obtain operational characteristics includes: and processing the load data to obtain weight characteristics, and obtaining operation comparison data according to the operation state data and the energy consumption data when the weight characteristics accord with the load threshold range.

Embodiments may also include an open flame processing module: and the monitoring device is used for acquiring open fire data through an open fire sensor, acquiring a temperature contour map of the monitoring area when the open fire data is determined to be on fire, acquiring a target area meeting the temperature of the fire point in the monitoring area based on the temperature contour map, and marking the target area as the fire point.

Example III

Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the invention. The electronic device may be a computer, a server, or the like, and of course, may also be an intelligent device such as a mobile phone, a tablet computer, a monitor terminal, or the like, and an image acquisition device having a processing function. As shown in fig. 6, the electronic device may include:

A memory 601 in which executable program codes are stored;

A processor 602 coupled to the memory 601;

Wherein the processor 602 invokes the executable program code stored in the memory 601 to perform some or all of the steps in the intelligent worksite AI activity tracking detection method in accordance with the first embodiment.

An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute some or all of the steps in the AI activity tracking detection method of the smart worksite in the first embodiment.

The embodiment of the invention also discloses a computer program product, wherein when the computer program product runs on a computer, the computer is caused to execute part or all of the steps in the intelligent worksite AI activity tracking detection method in the first embodiment.

The embodiment of the invention also discloses an application release platform, wherein the application release platform is used for releasing a computer program product, and the computer is caused to execute part or all of the steps in the intelligent worksite AI activity tracking detection method in the first embodiment when the computer program product runs on the computer.

In various embodiments of the present invention, it should be understood that the size of the sequence numbers of the processes does not mean that the execution sequence of the processes is necessarily sequential, and the execution sequence of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, or a part contributing to the prior art or all or part of the technical solution, may be embodied in the form of a software product stored in a memory, comprising several requests for a computer device (which may be a personal computer, a server or a network device, etc., in particular may be a processor in a computer device) to execute some or all of the steps of the method according to the embodiments of the present invention.

In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a, from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.

Those of ordinary skill in the art will appreciate that some or all of the steps of the various methods of the described embodiments may be implemented by hardware associated with a program that may be stored in a computer-readable storage medium, including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), one-time programmable Read-Only Memory (One-time Programmable Read-Only Memory, OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), or other optical disk Memory, magnetic disk Memory, tape Memory, or any other medium capable of being used to carry or store data.

The method, the device, the electronic equipment and the storage medium for detecting AI activity tracking of the intelligent construction site disclosed by the embodiment of the invention are described in detail, and specific examples are applied to the description of the principle and the implementation mode of the invention, and the description of the above embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims

1. An AI activity tracking and detecting method for an intelligent building site is characterized by comprising the following steps:

Collecting image data and equipment operation data of a target monitoring area;

2. The AI activity tracking detection method of claim 1, wherein the object features include a person feature and an environmental feature; comparing the object features with image reference features, comprising:

3. The AI activity tracking detection method of claim 1, wherein when the picture scene is a tower crane hook, processing the device operation data to obtain an operation feature, and comparing the operation feature with a preset operation reference feature, comprises:

4. The AI-activity-tracking detection method of claim 1, wherein comparing the object feature to an image reference feature when the picture scene is an elevator, comprises:

checking whether the object features have face features or not;

5. The AI-activity-tracking detection method of claim 4, wherein the device operational data includes pitch data, altitude data, and wind speed data, and wherein the processing the device operational data to obtain operational characteristics, comparing the operational characteristics to preset operational reference characteristics includes:

6. The AI activity tracking detection method of claim 1, wherein the collected device operation data includes load data, operation status data, energy consumption data when the picture scene is a discharge platform; the processing the device operational data to obtain operational characteristics includes:

7. The AI activity tracking detection method of claim 1, further comprising:

8. An AI activity tracking and detecting device for an intelligent building site, comprising:

9. An electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory for performing the AI-activity-tracking detection method of the smart worksite of any of claims 1-7.

10. A computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the AI activity tracking detection method of the smart worksite of any one of claims 1 to 7.