CN112489087A - Method for detecting shaking of suspension type operation platform for high-rise building construction - Google Patents
Method for detecting shaking of suspension type operation platform for high-rise building construction Download PDFInfo
- Publication number
- CN112489087A CN112489087A CN202011466111.3A CN202011466111A CN112489087A CN 112489087 A CN112489087 A CN 112489087A CN 202011466111 A CN202011466111 A CN 202011466111A CN 112489087 A CN112489087 A CN 112489087A
- Authority
- CN
- China
- Prior art keywords
- feature vector
- gravity center
- suspended
- platform
- trajectory
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The application discloses suspension type work platform's that is used for high-rise building construction rocks detection method, and it includes: acquiring a monitoring video of the suspension type operation platform through a camera arranged on the suspension type operation platform; determining a first gravity center track of the suspended operation platform and a second gravity center track of the construction operator in the monitoring video; performing one-dimensional convolution on the first gravity center track and the second gravity center track to obtain a first gravity center track feature vector and a second gravity center track feature vector; obtaining a classification feature vector by a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector; and inputting the classification feature vector into a classification function to obtain a classification result. In this way, the sway of the suspended work platform is detected based on the correlation between the temporal change in the gravity center locus of the suspended work platform, the temporal change in the gravity center locus of the construction worker, and the temporal change in the two.
Description
Technical Field
The present application relates to the field of artificial intelligence technology, and more particularly, to a method, system, and electronic device for detecting sway of a suspended work platform for high-rise building construction.
Background
The high-rise building has more floors and large height, and requires high continuity of construction. The stability of a suspended work platform for high-rise building construction is particularly important compared to a work platform disposed on the ground, because the stability is directly related to the safety of construction workers.
In order to improve the safety, on one hand, the fixing reliability of the suspension type operation platform is improved, on the other hand, the stability of the suspension type operation platform can be monitored in expectation, so that the situation that the stability of the suspension type operation platform is poor is found in time, the attention of construction operators is reminded, and safety accidents are avoided.
Therefore, a technical solution capable of monitoring the stability of the suspended type work platform in the high-rise building construction is desired.
At present, deep learning and neural networks have been widely applied in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks also exhibit a level close to or even exceeding that of humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
In recent years, deep learning and the development of neural networks provide new solutions and schemes for stability monitoring of suspended operation platforms for high-rise building construction.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. Embodiments of the present application provide a method, a system, and an electronic device for detecting a sway of a suspension work platform for high-rise building construction, which detect a sway of the suspension work platform based on a temporal change of a barycentric trajectory of the suspension work platform, a temporal change of a barycentric trajectory of a construction worker, and a correlation of the temporal changes of the barycentric trajectory and the construction worker.
According to an aspect of the present application, there is provided a sway detection method of a suspended type work platform for high-rise building construction, including:
acquiring a monitoring video of the suspended operation platform through a camera arranged on the suspended operation platform, wherein the monitoring video comprises the suspended operation platform and constructors on the suspended operation platform;
determining a first gravity center track of the suspended type operation platform and a second gravity center track of the construction operator in the monitoring video;
performing one-dimensional convolution on the first gravity center track and the second gravity center track to obtain a first gravity center track feature vector and a second gravity center track feature vector;
obtaining a classification feature vector by a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector; and
and inputting the classification characteristic vector into a classification function to obtain a classification result, wherein the classification result represents whether the stability of the suspension type operation platform meets a preset requirement or not.
In the above-mentioned sway detection method for a suspended work platform for high-rise building construction, obtaining a classification feature vector through a deep neural network based on the first gravity center trajectory feature vector and the second gravity center trajectory feature vector, the method includes: after the first gravity center track feature vector and the second gravity center track feature vector are cascaded, inputting the first gravity center track feature vector and the second gravity center track feature vector into a deep neural network to obtain a gravity center track correlation feature vector; and passing the barycentric trajectory-associated feature vector through one or more fully connected layers to obtain the classified feature vector.
In the above-mentioned sway detection method for a suspended work platform for high-rise building construction, obtaining a classification feature vector through a deep neural network based on the first gravity center trajectory feature vector and the second gravity center trajectory feature vector, the method includes: converting the first gravity center track characteristic vector and the second gravity center track characteristic vector into vectors with the same length through a transformation matrix; splicing the first gravity center track characteristic vector and the second gravity center track characteristic vector with the same length according to vectors, and then performing two-dimensional convolution to obtain a convolution characteristic diagram; and calculating the average value of each position of the convolution feature map according to vectors to obtain the classification feature vector.
In the above-mentioned shake detection method for a suspended work platform for high-rise building construction, the method of acquiring a surveillance video of the suspended work platform by a camera mounted on the suspended work platform includes: acquiring a first monitoring video taking the suspension type platform as a main body through a first camera arranged on the suspension type operation platform; and synchronously acquiring a second monitoring video which takes construction operators on the suspension type working platform as a main body through a second camera arranged on the suspension type working platform, wherein the first camera and the second camera have a preset position relation.
In the above method for detecting the sway of the suspended work platform for high-rise building construction, determining a first gravity center trajectory of the suspended work platform and a second gravity center trajectory of the construction worker in the surveillance video includes: converting the coordinate system of each image frame in the first monitoring video into a world coordinate system from a camera coordinate system; and using the change of the barycenter of each image frame in the first monitoring video on the world coordinate system as the first barycenter track.
In the above method for detecting the sway of the suspended work platform for high-rise building construction, determining a first gravity center trajectory of the suspended work platform and a second gravity center trajectory of the construction worker in the surveillance video includes: determining a suspended type operation platform object in the first monitoring video based on a video object detection method; and determining the change of the position of the center of gravity of the suspended type operation platform in the first monitoring video so as to obtain the first center of gravity track.
In the above method for detecting shaking of a suspended work platform for high-rise building construction, determining a first gravity center trajectory of the suspended work platform and a second gravity center trajectory of the construction worker in the surveillance video further includes: determining a construction worker object in the second monitoring video based on a video object detection method; and determining the change of the gravity center position of the construction worker object in the second monitoring video to obtain the second gravity center trajectory.
According to another aspect of the present application, there is provided a sway detection system of a suspended type work platform for high-rise building construction, including:
the monitoring video acquisition unit is used for acquiring a monitoring video of the suspended operation platform through a camera installed on the suspended operation platform, and the monitoring video comprises the suspended operation platform and constructors on the suspended operation platform;
a gravity center trajectory determination unit configured to determine a first gravity center trajectory of the suspended operation platform and a second gravity center trajectory of the construction worker in the surveillance video acquired by the surveillance video acquisition unit;
a barycentric trajectory feature vector generation unit configured to perform one-dimensional convolution on the first barycentric trajectory and the second barycentric trajectory obtained by the barycentric trajectory determination unit to obtain a first barycentric trajectory feature vector and a second barycentric trajectory feature vector;
a classification feature vector generation unit configured to obtain a classification feature vector by passing through a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector obtained by the barycentric trajectory feature vector generation unit; and
and the classification unit is used for inputting the classification characteristic vectors obtained by the classification characteristic vector generation unit into a classification function to obtain a classification result, wherein the classification result represents whether the stability of the suspension type operation platform meets a preset requirement or not.
In the above-mentioned shake detection system for a suspended type work platform for high-rise building construction, the classification feature vector generation unit includes: the gravity center track association feature vector generation subunit is used for cascading the first gravity center track feature vector and the second gravity center track feature vector and then inputting the cascaded first gravity center track feature vector and second gravity center track feature vector into a deep neural network to obtain a gravity center track association feature vector; and the full-connection subunit is used for enabling the gravity center track associated feature vector to pass through one or more full-connection layers to obtain the classification feature vector.
In the above-mentioned shake detection system for a suspended type work platform for high-rise building construction, the classification feature vector generation unit includes: the length coordination subunit is used for converting the first gravity center track characteristic vector and the second gravity center track characteristic vector into vectors with the same length through a transformation matrix; the two-dimensional convolution processing subunit is used for splicing the first gravity center track characteristic vector and the second gravity center track characteristic vector with the same length according to vectors and then performing two-dimensional convolution to obtain a convolution characteristic diagram; and the per-position averaging subunit is used for calculating the average value of each position of the convolution feature map according to vectors to obtain the classification feature vector.
In the shake detection system for a suspended work platform for high-rise building construction, the surveillance video acquisition unit further acquires a first surveillance video using the suspended work platform as a main body through a first camera mounted on the suspended work platform; and synchronously acquiring a second monitoring video which takes construction operators on the suspension type working platform as a main body through a second camera arranged on the suspension type working platform, wherein the first camera and the second camera have a preset position relation.
In the above-mentioned shake detection system for a suspended work platform for high-rise building construction, the center-of-gravity trajectory determination unit is further configured to: converting the coordinate system of each image frame in the first monitoring video into a world coordinate system from a camera coordinate system; and using the change of the barycenter of each image frame in the first monitoring video on the world coordinate system as the first barycenter track.
In the above-mentioned shake detection system for a suspended work platform for high-rise building construction, the center-of-gravity trajectory determination unit is further configured to: determining a suspended type operation platform object in the first monitoring video based on a video object detection method; and determining the change of the position of the center of gravity of the suspended type operation platform in the first monitoring video so as to obtain the first center of gravity track.
In the above-mentioned shake detection system for a suspended work platform for high-rise building construction, the center-of-gravity trajectory determination unit is further configured to: determining a construction worker object in the second monitoring video based on a video object detection method; and determining the change of the gravity center position of the construction worker object in the second monitoring video to obtain the second gravity center trajectory.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory in which computer program instructions are stored, which, when executed by the processor, cause the processor to perform the sway detection method for an overhead working platform for high-rise building construction as described above.
According to yet another aspect of the present application, there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to execute the sway detection method of an suspended work platform for high-rise building construction as described above.
According to the suspension type operation platform shaking detection method, system and electronic equipment for high-rise building construction, shaking of the suspension type operation platform is detected through the deep neural network based on the change of the gravity center track of the suspension type operation platform along with time, the change of the gravity center track of construction workers along with time and the mutual correlation of the change of the gravity center track of the suspension type operation platform along with time.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.
Fig. 1 illustrates a scene diagram of a sway detection method of a suspended type work platform for high-rise building construction according to an embodiment of the present application.
Fig. 2 illustrates a flowchart of a sway detection method of a suspended work platform for high-rise building construction according to an embodiment of the present application.
Fig. 3 illustrates an architecture diagram of a sway detection method of a suspended work platform for high-rise building construction according to an embodiment of the present application.
Fig. 4 is a flowchart illustrating the determination of a first barycentric trajectory of the suspended working platform and a second barycentric trajectory of the construction worker in the surveillance video according to the sway detection method for the suspended working platform for high-rise building construction according to the embodiment of the present application.
Fig. 5 is another flowchart illustrating the determination of the first barycentric trajectory of the suspended working platform and the second barycentric trajectory of the construction worker in the surveillance video according to the sway detection method for the suspended working platform for high-rise building construction according to the embodiment of the present application.
Fig. 6 is a flowchart illustrating a determination of a first barycentric trajectory of the suspended working platform and a second barycentric trajectory of the construction worker in the surveillance video according to the sway detection method for the suspended working platform for high-rise building construction according to the embodiment of the present application.
Fig. 7 illustrates a flowchart of obtaining classification feature vectors by a deep neural network based on the first gravity center trajectory feature vector and the second gravity center trajectory feature vector in the sway detection method for a suspended working platform for high-rise building construction according to an embodiment of the present application.
Fig. 8 illustrates another flowchart of obtaining classification feature vectors by a deep neural network based on the first gravity center trajectory feature vector and the second gravity center trajectory feature vector in the sway detection method for a suspended working platform for high-rise building construction according to an embodiment of the present application.
Fig. 9 illustrates a block diagram of a sway detection system for a suspended work platform for high-rise building construction according to an embodiment of the present application.
Fig. 10 illustrates a block diagram of a classification feature vector generation unit in the sway detection system of the suspended work platform for high-rise building construction according to an embodiment of the present application.
Fig. 11 illustrates another block diagram of a classification feature vector generation unit in the sloshing detection system of a suspended working platform for high-rise building construction according to an embodiment of the present application.
FIG. 12 illustrates a block diagram of an electronic device in accordance with an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and that the present application is not limited by the example embodiments described herein.
Overview of a scene
As described above, the stability of the suspended type work platform for high-rise building construction is particularly important compared to the work platform installed on the ground because the stability is directly related to the safety of the construction worker. Therefore, a technical solution capable of monitoring the stability of the suspended type work platform in the high-rise building construction is desired.
In recent years, deep learning and the development of neural networks provide new solutions and schemes for stability monitoring of suspended operation platforms for high-rise building construction.
The applicant of the present application has noted that when monitoring the stability of the suspended working platform, the current posture detection and posture recognition scheme based on computer vision may be adopted, so as to perform posture recognition with the suspended working platform as a target object, for example, determine the gravity center track of the target object to determine whether it is in a posture with better stability. However, in practice, it has been found that gesture recognition only for suspended work platforms remains problematic.
In fact, there are constructors working on the suspended working platform, and the constructors working can affect the posture of the suspended working platform. That is, when a worker is on the suspended work platform, the suspended work platform inevitably shakes, and the shaking cannot be used as an important determination factor affecting the stability of the suspended work platform.
Therefore, in the scheme of the application, the suspension type operation platform and the construction operator are considered separately, the gravity center track of the suspension type operation platform and the gravity center track of the construction operator are respectively determined to be used as characteristic vectors, the time sequence relation of the gravity center tracks of the suspension type operation platform and the construction operator along with time is respectively extracted through one-dimensional convolution, then the correlation characteristics between the characteristic vectors representing the time sequence relation of the gravity center tracks of the suspension type operation platform and the construction operator are extracted through a neural network consisting of a plurality of full connection layers, the classification is made based on the characteristic vectors of the gravity center tracks of the suspension type operation platform and the construction operator along with time sequence correlation, so that the classification result which not only considers the gravity center tracks of the suspension type operation platform along with time change, but also considers the gravity center tracks of the construction operator along with time change and the mutual correlation of the gravity center tracks of the construction operator along with time change is obtained, so as to improve the accuracy of stability monitoring of the final suspension type operation platform.
Based on this, the present application proposes a sway detection method for a suspended work platform for high-rise building construction, which includes: acquiring a monitoring video of the suspended operation platform through a camera arranged on the suspended operation platform, wherein the monitoring video comprises the suspended operation platform and constructors on the suspended operation platform; determining a first gravity center track of the suspended type operation platform and a second gravity center track of the construction operator in the monitoring video; performing one-dimensional convolution on the first gravity center track and the second gravity center track to obtain a first gravity center track feature vector and a second gravity center track feature vector; obtaining a classification feature vector by a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector; and inputting the classification feature vectors into a classification function to obtain a classification result, wherein the classification result indicates whether the stability of the suspension type operation platform meets a preset requirement.
Fig. 1 illustrates a scene diagram of a sway detection method of a suspended type work platform for high-rise building construction according to an embodiment of the present application.
As shown in fig. 1, in this application scenario, the monitoring video of the suspended working platform is captured by a camera (e.g., C as illustrated in fig. 1) of the suspended working platform, for example, the monitoring video of the suspended working platform is captured by the camera mounted on the suspended working platform; then, the surveillance video is input into a server (e.g., S as illustrated in fig. 1) deployed with a shake detection algorithm of the suspended working platform for high-rise building construction, wherein the server can process the surveillance video based on the shake detection algorithm of the suspended working platform for high-rise building construction to generate a detection result of whether the stability of the suspended working platform meets a preset requirement.
Having described the general principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.
Exemplary method
Fig. 2 illustrates a flowchart of a sway detection method of a suspended work platform for high-rise building construction according to an embodiment of the present application. As shown in fig. 2, a sway detection method for a suspended work platform for high-rise building construction according to an embodiment of the present application includes: s110, acquiring a monitoring video of the suspended operation platform through a camera mounted on the suspended operation platform, wherein the monitoring video comprises the suspended operation platform and constructors on the suspended operation platform; s120, determining a first gravity center track of the suspended type operation platform and a second gravity center track of the construction operator in the monitoring video; s130, performing one-dimensional convolution on the first gravity center track and the second gravity center track to obtain a first gravity center track feature vector and a second gravity center track feature vector; s140, obtaining a classification feature vector through a deep neural network based on the first gravity center trajectory feature vector and the second gravity center trajectory feature vector; and S150, inputting the classification feature vectors into a classification function to obtain a classification result, wherein the classification result indicates whether the stability of the suspension type operation platform meets a preset requirement.
Fig. 3 illustrates an architecture diagram of a sway detection method of a suspended work platform for high-rise building construction according to an embodiment of the present application. As shown in fig. 3, in the network architecture, first, a first barycentric trajectory (e.g., V1 as illustrated in fig. 3) of the suspended work platform and a second barycentric trajectory (e.g., V2 as illustrated in fig. 3) of the construction worker in a monitoring video of the suspended work platform are respectively subjected to one-dimensional convolution to obtain a first barycentric trajectory feature vector (e.g., Vt1 as illustrated in fig. 3) and a second barycentric trajectory feature vector (e.g., Vt2 as illustrated in fig. 3); then, passing through a deep neural network (e.g., DN as illustrated in fig. 3) based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector to obtain a classification feature vector (e.g., Vc as illustrated in fig. 3); the classification feature vectors are then input into a classification function (e.g., circle S as illustrated in fig. 3) to obtain a classification result, wherein the classification result indicates whether the stability of the suspended working platform meets a preset requirement.
In step S110, a surveillance video of the suspended working platform is obtained through a camera mounted on the suspended working platform, where the surveillance video includes the suspended working platform and a constructor on the suspended working platform. That is, in this application embodiment, gather through installing suspension type work platform's camera the surveillance video of suspension type work platform, like this, on the one hand, can solve the installation problem of the camera that is used for acquireing suspension type work platform's video, can be along with suspension type work platform reciprocate real-time detection suspension type work platform's rocking moreover.
In a specific example of the present application, a monitoring video including a construction worker who uses the suspended work platform as a background may be collected by a camera installed on the suspended work platform, so that it is ensured that the suspended work platform and the construction worker on the suspended work platform are included in the monitoring video.
Of course, in other examples of the present application, a plurality of cameras mounted on the suspended working platform may respectively collect a first surveillance video mainly based on the suspended working platform and a second surveillance video mainly based on the construction worker, for example, the first camera mounted on the suspended working platform is used to obtain the first surveillance video mainly based on the suspended working platform; and synchronously acquiring a second monitoring video which takes construction workers on the suspension type working platform as a main body by using a second camera installed on the suspension type working platform, wherein the first camera and the second camera have a preset position relation. That is, in other examples of the present application, the monitoring videos include a first monitoring video mainly based on the suspended work platform and a second monitoring video mainly based on the construction worker, and the two monitoring videos are used as source data of data processing. It should be understood that the first surveillance video mainly includes the suspended working platform, and the second surveillance video mainly includes the construction worker, so that the detection accuracy of the first gravity center trajectory of the suspended working platform and the second gravity center trajectory of the construction worker in the surveillance video can be improved.
In step S120, a first barycentric trajectory of the suspended work platform and a second barycentric trajectory of the construction worker in the surveillance video are determined. As described above, in practice, a worker is working on the suspended work platform, and the worker who is working affects the posture of the suspended work platform. That is, when a worker is on the suspended work platform, the suspended work platform inevitably shakes, and the shaking cannot be used as an important determination factor affecting the stability of the suspended work platform. Therefore, in the present application, the suspension work platform and the construction worker are considered separately, the gravity center trajectory of the suspension work platform and the gravity center trajectory of the construction worker are determined as feature vectors, and the sway characteristic of the suspension work platform is monitored by the correlation between the gravity center trajectory conversion of the suspension work platform and the construction worker, that is, the stability of the suspension work platform is monitored based on the temporal change of the gravity center trajectory of the suspension work platform, the temporal change of the gravity center trajectory of the construction worker, and the correlation between the temporal changes of the two.
Specifically, in a specific example of the present application, when the surveillance video includes a first surveillance video mainly based on the suspended platform and a second surveillance video mainly based on a construction worker on the suspended platform, the process of determining a first gravity center locus of the suspended platform in the surveillance video includes: firstly, converting a coordinate system of each image frame in the first monitoring video from a camera coordinate system to a world coordinate system; then, the change of the barycenter of each image frame in the first monitoring video on the world coordinate system is used as the first barycenter track.
Fig. 4 is a flowchart illustrating the determination of a first barycentric trajectory of the suspended working platform and a second barycentric trajectory of the construction worker in the surveillance video according to the sway detection method for the suspended working platform for high-rise building construction according to the embodiment of the present application. As shown in fig. 4, determining a first center of gravity trajectory of the suspended work platform in the surveillance video includes: s210, converting the coordinate system of each image frame in the first monitoring video from a camera coordinate system to a world coordinate system; and S220, using the change of the barycenter of each image frame in the first monitoring video on the world coordinate system as the first barycenter track.
In this specific example, in order to reduce the data processing amount, a plurality of image frames may be captured from the monitoring video at preset time intervals, and the preset time interval value is not too large, otherwise, two adjacent frames may not well reflect the time sequence relationship of the change of the center of gravity of the suspended type work platform; of course, the predetermined time interval is not too small, which wastes computing resources.
In other examples of the present application, the first barycentric trajectory of the suspended work platform in the surveillance video may also be determined in other manners, for example, based on a video object detection method. The process specifically includes, first, determining a suspended work platform object in the first surveillance video based on a video object detection method, for example, determining the suspended work platform object in the first surveillance video by a video object detection method using an optical flow; next, a change in the position of the center of gravity of the suspended work platform in the first surveillance video is determined to obtain the first center of gravity trajectory, which is generated, for example, by a feature point recognition algorithm to identify the center of gravity of the suspended work platform object.
Fig. 5 is another flowchart illustrating the determination of the first barycentric trajectory of the suspended working platform and the second barycentric trajectory of the construction worker in the surveillance video according to the sway detection method for the suspended working platform for high-rise building construction according to the embodiment of the present application. As shown in fig. 5, determining a first center of gravity trajectory of the suspended work platform in the surveillance video includes: s310, determining a suspended type operation platform object in the first monitoring video based on a video object detection method; and S320, determining the change of the gravity center position of the suspended type operation platform in the first monitoring video so as to obtain the first gravity center track.
Further, in the two specific examples, a second gravity center trajectory of the construction worker in the monitoring video is further included. Accordingly, a video-based object detection method may also be utilized to determine a second center of gravity trajectory for the construction worker in the surveillance video. Specifically, the process of determining the second gravity center trajectory of the construction worker in the monitoring video includes: first, a construction worker object in the second monitoring video is determined based on a video object detection method, for example, a construction worker object in the construction worker video is determined based on a video object detection method using an optical flow method; next, a change in the position of the center of gravity of the construction worker object in the second monitoring video is determined to obtain the second center of gravity trajectory, which is generated by, for example, identifying the center of gravity of the construction worker object through a feature point recognition algorithm.
Fig. 6 is a flowchart illustrating a determination of a first barycentric trajectory of the suspended working platform and a second barycentric trajectory of the construction worker in the surveillance video according to the sway detection method for the suspended working platform for high-rise building construction according to the embodiment of the present application. As shown in fig. 6, determining a second barycentric trajectory for the construction worker includes: s410, determining a construction worker object in the second monitoring video based on a video object detection method; and S420, determining the change of the gravity center position of the construction operator object in the second monitoring video to obtain the second gravity center track.
In step S130, a one-dimensional convolution is performed on the first barycentric trajectory and the second barycentric trajectory to obtain a first barycentric trajectory feature vector and a second barycentric trajectory feature vector. Namely, the time sequence relation of the gravity center tracks of the suspension type operation platform and the construction operator along with the time is respectively extracted through one-dimensional convolution.
In step S140, a classification feature vector is obtained through a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector. That is, the correlation features between the feature vectors representing the time-series relationship of the gravity center trajectories of the suspended work platform and the construction worker are extracted by the deep neural network.
In a specific example of the present application, a process of obtaining a classification feature vector through a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector includes: firstly, the first gravity center track characteristic vector and the second gravity center track characteristic vector are cascaded and then input into a deep neural network to obtain a gravity center track association characteristic vector, the deep neural network can be used for connecting the first gravity center track characteristic vector and the second gravity center track characteristic with the same node to a certain extent through the cascade connection, so that the gravity center track of the suspended type operation platform in the first gravity center track characteristic vector and the second gravity center track characteristic changes with time and the gravity center track of a construction operator changes with time, and the mutual association of the first gravity center track characteristic vector and the second gravity center track characteristic with the time change is also ensured.
Then, the barycentric trajectory-associated feature vector is passed through one or more fully connected layers to obtain the classified feature vector. It can be understood that the overall mining by using the deep neural network has the advantages of fully extracting information and the disadvantages of slow calculation speed and easy noise interference due to excessive correlation among vectors and overfitting by the deep neural network.
Fig. 7 illustrates a flowchart of obtaining classification feature vectors by a deep neural network based on the first gravity center trajectory feature vector and the second gravity center trajectory feature vector in the sway detection method for a suspended working platform for high-rise building construction according to an embodiment of the present application. As shown in fig. 7, obtaining a classification feature vector through a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector, includes: s510, cascading the first gravity center track feature vector and the second gravity center track feature vector and then inputting the concatenated vectors into a deep neural network to obtain a gravity center track correlation feature vector; and S520, passing the gravity center track associated feature vector through one or more fully connected layers to obtain the classification feature vector.
In another specific example of the present application, the process of obtaining a classification feature vector through a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector includes: firstly, converting the first gravity center track characteristic vector and the second gravity center track characteristic vector into vectors with the same length through a transformation matrix; then, splicing the first gravity center track characteristic vector and the second gravity center track characteristic vector with the same length according to the vectors, and then performing two-dimensional convolution to obtain a convolution characteristic diagram; then, the convolution feature map is vector-calculated to obtain the classification feature vector.
That is, in this other specific example, a hierarchical convolution mechanism is used to extract a temporal change in the barycentric trajectory of the suspended work platform and a temporal change in the barycentric trajectory of the construction operator among the first barycentric trajectory feature vector and the second barycentric trajectory feature, and a correlation of the temporal changes of both, wherein a one-dimensional convolution is used to extract the temporal change in the barycentric trajectory of the suspended work platform and the temporal change in the barycentric trajectory of the construction operator among the first barycentric trajectory feature vector and the second barycentric trajectory feature, and a two-dimensional convolution is used to extract a correlation of the temporal changes of both.
More specifically, in this specific example, the process of vector-splicing the first barycentric trajectory feature vector and the second barycentric trajectory feature vector with the same length and then performing two-dimensional convolution to obtain a convolution feature map includes: firstly, splicing the first gravity center track characteristic vector and the second gravity center track characteristic vector with the same length according to vectors to obtain a spliced characteristic vector; then, the spliced feature vector is subjected to a first convolution layer to obtain a first convolution feature map; then, the first convolution feature map passes through a first pooling layer to obtain a first pooling feature map; then, a second convolved feature map, i.e. the convolved feature map, is obtained from a second convolution layer based on the first pooled feature map. That is, in this other specific example, extracting the associated feature between the first barycentric trajectory feature vector and the second barycentric trajectory feature vector by two convolution layers can ensure sufficient feature extraction.
Fig. 8 illustrates another flowchart of obtaining classification feature vectors by a deep neural network based on the first gravity center trajectory feature vector and the second gravity center trajectory feature vector in the sway detection method for a suspended working platform for high-rise building construction according to an embodiment of the present application. As shown in fig. 8, obtaining a classification feature vector through a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector, includes: s610, converting the first gravity center trajectory feature vector and the second gravity center trajectory feature vector into vectors with the same length through a transformation matrix; s620, splicing the first gravity center trajectory feature vector and the second gravity center trajectory feature vector with the same length according to vectors, and then performing two-dimensional convolution to obtain a convolution feature map; and S630, calculating the average value of each position of the convolution feature map according to vectors to obtain the classification feature vector.
In step S150, the classification feature vectors are input into a classification function to obtain a classification result, where the classification result indicates whether the stability of the suspended work platform meets a preset requirement. In an embodiment of the present application, the classification function is a Softmax classification function, and an output value of the classification function indicates a probability value of whether a sway characteristic of the suspended type work platform meets a preset requirement.
In summary, a sway detection method for a suspended work platform for high-rise building construction based on an embodiment of the present application is elucidated, which monitors the suspended work platform based on a temporal change in the gravity center trajectory of the suspended work platform, a temporal change in the gravity center trajectory of a construction worker, and a correlation of the temporal changes of the two.
Exemplary System
Fig. 9 illustrates a block diagram of a sway detection system for a suspended work platform for high-rise building construction according to an embodiment of the present application.
As shown in fig. 9, the sway detection system 900 of the suspended type work platform for high-rise building construction according to the embodiment of the present application includes: a surveillance video acquiring unit 910, configured to acquire a surveillance video of a suspended working platform through a camera mounted on the suspended working platform, where the surveillance video includes the suspended working platform and a constructor on the suspended working platform; a barycentric trajectory determination unit 920, configured to determine a first barycentric trajectory of the suspended operation platform and a second barycentric trajectory of the construction worker in the surveillance video obtained by the surveillance video acquisition unit 910; a barycentric trajectory feature vector generation unit 930 configured to perform one-dimensional convolution on the first barycentric trajectory and the second barycentric trajectory obtained by the barycentric trajectory determination unit 920 to obtain a first barycentric trajectory feature vector and a second barycentric trajectory feature vector; a classification feature vector generation unit 940 configured to pass through a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector obtained by the barycentric trajectory feature vector generation unit 930 to obtain a classification feature vector; and a classifying unit 950, configured to input the classification feature vector obtained by the classification feature vector generating unit 940 into a classification function to obtain a classification result, where the classification result indicates whether the stability of the suspension type work platform meets a preset requirement.
In an example, in the detection system 900, as shown in fig. 10, the classification feature vector generation unit 940 includes: a barycentric trajectory associated feature vector generation subunit 941, configured to cascade the first barycentric trajectory feature vector and the second barycentric trajectory feature vector, and input the cascade result to a deep neural network to obtain a barycentric trajectory associated feature vector; and a fully-connected subunit 942, configured to pass the barycentric trajectory-associated feature vector through one or more fully-connected layers to obtain the classification feature vector.
In an example, in the detection system 900, as shown in fig. 11, the classification feature vector generation unit 940 includes: a length co-integration subunit 943, configured to convert the first barycentric trajectory eigenvector and the second barycentric trajectory eigenvector into vectors with the same length through a transformation matrix; a two-dimensional convolution processing subunit 944, configured to perform two-dimensional convolution on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector of the same length after vector splicing to obtain a convolution feature map; and a per-location averaging subunit 945, configured to calculate an average value of each location of the convolution feature map by vector to obtain the classification feature vector.
In an example, in the above detection system 900, the surveillance video acquiring unit 910 further acquires a first surveillance video with the suspended platform as a main body through a first camera mounted on the suspended work platform; and synchronously acquiring a second monitoring video which takes construction operators on the suspension type working platform as a main body through a second camera arranged on the suspension type working platform, wherein the first camera and the second camera have a preset position relation.
In an example, in the above detection system 900, the gravity center trajectory determination unit 920 is further configured to: converting the coordinate system of each image frame in the first monitoring video into a world coordinate system from a camera coordinate system; and using the change of the barycenter of each image frame in the first monitoring video on the world coordinate system as the first barycenter track.
In an example, in the above detection system 900, the gravity center trajectory determination unit 920 is further configured to: determining a suspended type operation platform object in the first monitoring video based on a video object detection method; and determining the change of the position of the center of gravity of the suspended type operation platform in the first monitoring video so as to obtain the first center of gravity track.
In an example, in the above detection system 900, the gravity center trajectory determination unit 920 is further configured to: determining a construction worker object in the second monitoring video based on a video object detection method; and determining the change of the gravity center position of the construction worker object in the second monitoring video to obtain the second gravity center trajectory.
Here, it can be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the above-described detection system 900 have been described in detail in the above description of the sloshing detection method of a suspended type working platform for high-rise building construction with reference to fig. 1 to 8, and thus, a repetitive description thereof will be omitted.
As described above, the detection system 900 according to the embodiment of the present application can be implemented in various terminal devices, such as a monitoring server of a suspended type work platform. In one example, the detection system 900 according to embodiments of the present application may be integrated into a terminal device as a software module and/or a hardware module. For example, the detection system 900 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the detection system 900 may also be one of many hardware modules of the terminal device.
Alternatively, in another example, the detection system 900 and the terminal device may be separate devices, and the detection system 900 may be connected to the terminal device through a wired and/or wireless network and transmit the interaction information according to an agreed data format.
Exemplary electronic device
Next, an electronic apparatus according to an embodiment of the present application is described with reference to fig. 12.
FIG. 12 illustrates a block diagram of an electronic device in accordance with an embodiment of the present application.
As shown in fig. 12, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The input device 13 may include, for example, a keyboard, a mouse, and the like.
The output device 14 can output various information including the classification result to the outside. The output devices 14 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.
Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present application are shown in fig. 12, and components such as buses, input/output interfaces, and the like are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the above-described methods and apparatus, embodiments of the present application may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the method of sway detection of an overhead work platform for high-rise building construction according to various embodiments of the present application described in the "exemplary methods" section above of this specification.
The computer program product may be written with program code for performing the operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the sway detection method for an overhead work platform for high-rise building construction according to various embodiments of the present application described in the "exemplary methods" section above in this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present application in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present application are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present application. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the foregoing disclosure is not intended to be exhaustive or to limit the disclosure to the precise details disclosed.
The block diagrams of devices, apparatuses, systems referred to in this application are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that in the devices, apparatuses, and methods of the present application, the components or steps may be decomposed and/or recombined. These decompositions and/or recombinations are to be considered as equivalents of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (10)
1. A shake detection method of a suspension type working platform for high-rise building construction is characterized by comprising the following steps:
acquiring a monitoring video of the suspended operation platform through a camera arranged on the suspended operation platform, wherein the monitoring video comprises the suspended operation platform and constructors on the suspended operation platform;
determining a first gravity center track of the suspended type operation platform and a second gravity center track of the construction operator in the monitoring video;
performing one-dimensional convolution on the first gravity center track and the second gravity center track to obtain a first gravity center track feature vector and a second gravity center track feature vector;
obtaining a classification feature vector by a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector; and
and inputting the classification characteristic vector into a classification function to obtain a classification result, wherein the classification result represents whether the stability of the suspension type operation platform meets a preset requirement or not.
2. The sway detection method of a suspended work platform for high-rise building construction of claim 1, wherein obtaining a classification feature vector by a deep neural network based on the first and second barycentric trajectory feature vectors comprises:
after the first gravity center track feature vector and the second gravity center track feature vector are cascaded, inputting the first gravity center track feature vector and the second gravity center track feature vector into a deep neural network to obtain a gravity center track correlation feature vector; and
passing the barycentric trajectory-associated feature vector through one or more fully connected layers to obtain the classified feature vector.
3. The sway detection method of a suspended work platform for high-rise building construction of claim 1, wherein obtaining a classification feature vector by a deep neural network based on the first and second barycentric trajectory feature vectors comprises:
converting the first gravity center track characteristic vector and the second gravity center track characteristic vector into vectors with the same length through a transformation matrix;
splicing the first gravity center track characteristic vector and the second gravity center track characteristic vector with the same length according to vectors, and then performing two-dimensional convolution to obtain a convolution characteristic diagram; and
calculating the average value of each position of the convolution feature map according to vectors to obtain the classification feature vector.
4. The sway detection method for a suspended work platform for high-rise building construction as claimed in claim 1, wherein acquiring a surveillance video of the suspended work platform by a camera mounted on the suspended work platform comprises:
acquiring a first monitoring video taking the suspension type platform as a main body through a first camera arranged on the suspension type operation platform; and
and a second monitoring video which takes construction workers on the suspension type working platform as a main body is synchronously acquired through a second camera arranged on the suspension type working platform, and the first camera and the second camera have a preset position relation.
5. The sway detection method of an overhead working platform for high-rise building construction of claim 4, wherein determining a first locus of center of gravity of the overhead working platform and a second locus of center of gravity of the construction worker in the surveillance video comprises:
converting the coordinate system of each image frame in the first monitoring video into a world coordinate system from a camera coordinate system; and
and using the gravity center change of each image frame in the first monitoring video on the world coordinate system as the first gravity center track.
6. The sway detection method of an overhead working platform for high-rise building construction of claim 4, wherein determining a first locus of center of gravity of the overhead working platform and a second locus of center of gravity of the construction worker in the surveillance video comprises:
determining a suspended type operation platform object in the first monitoring video based on a video object detection method; and
determining a change in a position of a center of gravity of the suspended work platform in the first surveillance video to obtain the first center of gravity trajectory.
7. The sway detection method of an overhead working platform for high-rise building construction of claim 5 or 6, wherein determining a first locus of center of gravity of the overhead working platform and a second locus of center of gravity of the construction worker in the surveillance video further comprises:
determining a construction worker object in the second monitoring video based on a video object detection method; and
determining a change in a position of a center of gravity of the construction worker object in the second surveillance video to obtain the second center of gravity trajectory.
8. A system for detecting the shaking of a suspended working platform for high-rise building construction, comprising:
the monitoring video acquisition unit is used for acquiring a monitoring video of the suspended operation platform through a camera installed on the suspended operation platform, and the monitoring video comprises the suspended operation platform and constructors on the suspended operation platform;
a gravity center trajectory determination unit configured to determine a first gravity center trajectory of the suspended operation platform and a second gravity center trajectory of the construction worker in the surveillance video acquired by the surveillance video acquisition unit;
a barycentric trajectory feature vector generation unit configured to perform one-dimensional convolution on the first barycentric trajectory and the second barycentric trajectory obtained by the barycentric trajectory determination unit to obtain a first barycentric trajectory feature vector and a second barycentric trajectory feature vector;
a classification feature vector generation unit configured to obtain a classification feature vector by passing through a deep neural network based on the first barycentric trajectory feature vector and the second barycentric trajectory feature vector obtained by the barycentric trajectory feature vector generation unit; and
and the classification unit is used for inputting the classification characteristic vectors obtained by the classification characteristic vector generation unit into a classification function to obtain a classification result, wherein the classification result represents whether the stability of the suspension type operation platform meets a preset requirement or not.
9. The sway detection system of a suspended work platform for high-rise building construction of claim 8, wherein the classification feature vector generation unit comprises:
the gravity center track association feature vector generation subunit is used for cascading the first gravity center track feature vector and the second gravity center track feature vector and then inputting the cascaded first gravity center track feature vector and second gravity center track feature vector into a deep neural network to obtain a gravity center track association feature vector; and
and the full-connection subunit is used for enabling the gravity center track associated feature vector to pass through one or more full-connection layers so as to obtain the classification feature vector.
10. An electronic device, comprising:
a processor; and
a memory having stored therein computer program instructions which, when executed by the processor, cause the processor to perform a method of sloshing detection of an overhead work platform for high-rise building construction according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011466111.3A CN112489087A (en) | 2020-12-13 | 2020-12-13 | Method for detecting shaking of suspension type operation platform for high-rise building construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011466111.3A CN112489087A (en) | 2020-12-13 | 2020-12-13 | Method for detecting shaking of suspension type operation platform for high-rise building construction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112489087A true CN112489087A (en) | 2021-03-12 |
Family
ID=74916419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011466111.3A Withdrawn CN112489087A (en) | 2020-12-13 | 2020-12-13 | Method for detecting shaking of suspension type operation platform for high-rise building construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489087A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800912A (en) * | 2021-01-20 | 2021-05-14 | 江苏天幕无人机科技有限公司 | Dynamic feature based label-based migration feature neural network training method |
| CN115520786A (en) * | 2022-08-25 | 2022-12-27 | 江苏广坤铝业有限公司 | Aluminum material discharging auxiliary transfer equipment and transfer control method |
| CN116311005A (en) * | 2023-05-25 | 2023-06-23 | 成都睿瞳科技有限责任公司 | Apparatus, method and storage medium for moving image processing |
-
2020
- 2020-12-13 CN CN202011466111.3A patent/CN112489087A/en not_active Withdrawn
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800912A (en) * | 2021-01-20 | 2021-05-14 | 江苏天幕无人机科技有限公司 | Dynamic feature based label-based migration feature neural network training method |
| CN112800912B (en) * | 2021-01-20 | 2024-07-16 | 浙江宇众环境科技有限公司 | Training method of neural network based on dynamic characteristics and migration characteristics of labels |
| CN115520786A (en) * | 2022-08-25 | 2022-12-27 | 江苏广坤铝业有限公司 | Aluminum material discharging auxiliary transfer equipment and transfer control method |
| CN115520786B (en) * | 2022-08-25 | 2024-02-27 | 江苏广坤铝业有限公司 | Aluminum product discharging auxiliary transfer equipment and transfer control method |
| CN116311005A (en) * | 2023-05-25 | 2023-06-23 | 成都睿瞳科技有限责任公司 | Apparatus, method and storage medium for moving image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112489087A (en) | Method for detecting shaking of suspension type operation platform for high-rise building construction | |
| KR102409204B1 (en) | Method, apparatus and computer program for providing modularized artificial intelligence model platform service | |
| US20170344832A1 (en) | System and method for event monitoring and detection | |
| CN111523559B (en) | Abnormal behavior detection method based on multi-feature fusion | |
| CN111931862B (en) | Method and system for detecting illegal posted advertisements and electronic equipment | |
| CN115731513B (en) | Intelligent park management system based on digital twinning | |
| US20200342215A1 (en) | Model learning device, model learning method, and recording medium | |
| CN112037279A (en) | Article position identification method and device, storage medium and electronic equipment | |
| CN112270246A (en) | Video behavior identification method and device, storage medium and electronic equipment | |
| CN115783919A (en) | Electric vehicle monitoring system and method for elevator | |
| CN113874877A (en) | Neural network and classifier selection system and method | |
| CN113281780B (en) | Method and device for marking image data and electronic equipment | |
| CN112418198B (en) | Method for detecting fluctuation defects of floor tiles of pedestrian walkways based on gray scale map energy values | |
| CN116959099B (en) | Abnormal behavior identification method based on space-time diagram convolutional neural network | |
| CN117274926A (en) | Control method and system of traffic signal equipment | |
| CN116994209A (en) | Image data processing system and method based on artificial intelligence | |
| CN116977129A (en) | Intelligent property management system and method thereof | |
| CN116385962A (en) | Personnel monitoring system in corridor based on machine vision and method thereof | |
| CN114943873B (en) | Method and device for classifying abnormal behaviors of staff on construction site | |
| CN112584108B (en) | Line physical damage monitoring method for unmanned aerial vehicle inspection | |
| CN113762017B (en) | Action recognition method, device, equipment and storage medium | |
| CN111680674B (en) | Hall personnel monitoring method based on self-integrated attention mechanism | |
| CN114937261A (en) | Image recognition method, apparatus, medium, and device | |
| CN114842183A (en) | Convolutional neural network-based switch state identification method and system | |
| CN114663972A (en) | Target marking method and device based on motion difference |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210312 |
|
| WW01 | Invention patent application withdrawn after publication |