CN111561915A

CN111561915A - Building construction state monitoring feedback device, system and method

Info

Publication number: CN111561915A
Application number: CN202010458399.3A
Authority: CN
Inventors: 彭珍
Original assignee: Yongkang Longpiao Sensing Technology Co ltd
Current assignee: Yongkang Longpiao Sensing Technology Co ltd
Priority date: 2020-05-27
Filing date: 2020-05-27
Publication date: 2020-08-21

Abstract

The invention discloses a building construction state monitoring feedback device, a system and a method, wherein the device comprises a camera, a mounting plate, a sleeve column and a sleeve, a fixed rod is fixedly arranged on the surface of one side of the mounting plate, a turntable is fixedly arranged at one end of the fixed rod, a rotating shaft is rotatably arranged on the surface of the turntable, the camera is fixedly arranged on the surface of the rotating shaft, first notches are formed in two ends of the mounting plate, the sleeve column is rotatably arranged inside the first notch, an inner column is inserted into the sleeve column, a second notch is formed in one end of the inner column, and the sleeve is rotatably arranged inside the second notch. The invention provides two fixing and mounting methods, one is to screw in a screw by utilizing a fixing hole which is arranged in a mounting plate in a penetrating way, and the other is to use an extensible inner column and a sleeve column to fix a columnar object, such as: and objects such as a street lamp post are clamped and fixed, so that the applicability is improved, and the effect of the monitoring camera installation by workers is facilitated.

Description

Building construction state monitoring feedback device, system and method

Technical Field

The invention relates to the technical field of monitoring equipment, in particular to a building construction state monitoring feedback device, system and method.

Background

The monitoring camera is a semiconductor imaging device, has the advantages of high sensitivity, strong light resistance, small distortion, small volume, long service life, vibration resistance and the like, is visible everywhere in life, and has higher and higher requirements on the camera along with the improvement of science and technology.

Present building site need utilize the surveillance camera head to come remote data acquisition when the construction, but the most not convenient for of current surveillance camera head is installed fixedly, wastes time and energy during the installation, and the mounting means is single, can not adapt to the multiple condition and install.

In addition, nowadays of rapid development of science and technology, large-scale equipment such as buildings, vehicles and the like in life are more and more, and society and city construction also need more and more manpower and material resources. In the field of construction worker management, the traditional management method needs people to detect and supervise, and is low in efficiency and high in cost. In order to solve the above problems, the present invention proposes an event detection system and method based on image video, which is intended to generally require site personnel and management personnel to supervise and detect a work project occurring on a site such as a construction site, and to timely record and report events and accidents that may occur, and when a dispute relating to a project problem occurs, daily reports and photographs are the best record of the event, which is important for prosecuting or deeming a claim related to a contractor. Therefore, the system and the method for detecting the events based on the image video can save labor, time cost and improve. The invention is not limited to simple data processing, can utilize the received data more effectively, can train the model through the yolo target detection algorithm model, can monitor the data in real time, and can directly detect the data by the algorithm model and report and record the data in time when a worker has a special event. Labor cost and time cost are reduced.

Disclosure of Invention

The invention aims to provide a building construction state monitoring feedback device to solve the problems in the background technology.

Another object of the present invention is to provide a building construction state monitoring and feedback system applied to the building construction state monitoring and feedback device.

Still another object of the present invention is to provide a building construction state monitoring and feedback method applied to the building construction state monitoring and feedback system.

In order to achieve the purpose, the invention provides the following technical scheme: the utility model provides a building construction state monitoring feedback device, includes camera, mounting panel, cover post and sleeve, a side fixed surface of mounting panel installation dead lever, the one end fixed mounting of dead lever has the carousel, and the surface of carousel rotates installs the pivot, and the fixed surface of pivot installs the camera, first breach has been seted up at the both ends of mounting panel, and the cover post is installed in the internal rotation of first breach, and the interior post has been inserted to the inside of cover post, and the second breach has been seted up to the one end inside of interior post, and the sleeve is installed in the internal rotation of second breach.

Preferably, one side of the camera is connected with a cable, the top end of the camera is fixedly provided with a top cover, and the top end of the top cover is provided with an antenna.

Preferably, the inside of mounting panel runs through and has seted up the fixed orifices, and the fixed orifices is equipped with four, and four fixed orifices are the rectangle and distribute.

Preferably, the sleeve is equipped with four, and four sleeves are two sets of to be the opposite direction distribution, and the inside of two sets of sleeves all inserts and is connected with the bolt.

Preferably, a screw is screwed into one end surface of the sleeve column, and one end of the screw abuts against one end surface of the inner column.

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

1. according to the invention, through arranging the camera, a worker can remotely collect data on a construction site, the effect of shooting video collection data for feedback is achieved, and through arranging the screw, the distance of the inner column in the sleeve column can be fixed, so that the effect of screwing and fixing the current distance of the inner column in the sleeve column is achieved.

2. The invention can enlarge and reduce the clamping and mounting position through the matching of the inner columns and the sleeve columns, achieves the effect of adjusting according to the diameter of the current cylinder to be fixed, and can tightly attach the four inner columns and the four sleeve columns to the surface of the cylinder to be mounted through the matching of the sleeves and the bolts, thereby achieving the effect of screwing, clamping and fixing.

In order to achieve another purpose, the invention provides the following building construction state monitoring feedback system: in the data processing process of the system, the yolo detection network is set to comprise 24 convolutional layers and 2 full-connection layers for processing.

In order to achieve the above further object, the present invention provides the following building construction state monitoring feedback method: processing the detected video data into images according to frames, wherein the images are data to be trained and processed; the method comprises the following specific steps: step 102, preprocessing a video frame extraction picture; step 104, processing data through a Yolo algorithm; step 106 reports the success of the connection through the algorithm model.

Drawings

FIG. 1 is a schematic front view of the present invention;

FIG. 2 is a schematic top-down non-expanded structure of the present invention;

FIG. 3 is a schematic top view of the expanded configuration of the present invention;

FIG. 4 is a front view of the mounting plate of the present invention;

FIG. 5 is a flow chart of a method for monitoring feedback according to the present invention.

In the figure: 1. a top cover; 2. a camera; 3. a rotating shaft; 4. a turntable; 5. fixing the rod; 6. mounting a plate; 7. a first notch; 8. sleeving a column; 9. a screw; 10. an inner column; 11. a sleeve; 12. a second notch; 13. an antenna; 14. a cable; 15. a bolt; 16. and (7) fixing holes.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "front", "rear", "both ends", "one end", "the other end", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "connected," and the like are to be construed broadly, such as "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.

Example one

Referring to fig. 1 to 4, an embodiment of the present invention includes: a building construction state monitoring feedback device comprises a camera 2, a mounting plate 6, a sleeve column 8 and a sleeve 11, wherein a fixing rod 5 is fixedly mounted on the surface of one side of the mounting plate 6, a rotary plate 4 is fixedly mounted at one end of the fixing rod 5, the left and right angles of the camera 2 can be adjusted in a rotating mode through mounting of the rotary plate 4, a rotary shaft 3 is rotatably mounted on the surface of the rotary plate 4, the upper and lower angles of the camera 2 can be adjusted in a rotating mode through mounting of the rotary shaft 3, the rotary shaft 3 and the rotary plate 4 have damping performance, the existing state of the camera 2 cannot be automatically changed under the condition of no manual force application, the camera 2 is fixedly mounted on the surface of the rotary shaft 3, through arranging the camera 2, a worker can remotely collect data on a construction site, the effect of shooting video collection data for feedback is achieved, a cable 14 is connected and mounted on one side of, top cap 1 is fixed mounting to the top of camera 2, and the installation of top cap 1 makes camera 2 avoid the influence of the day rainwater that falls, prolongs camera 2's life, and top cap 1's top is equipped with antenna 13.

The mounting plate 6 is internally provided with four fixing holes 16 in a penetrating manner, the four fixing holes 16 are distributed in a rectangular manner, the mounting of the four fixing holes 16 enables the mounting plate to be mounted in a traditional mounting manner, two ends of the mounting plate 6 are provided with first notches 7, a sleeve column 8 is rotatably mounted inside the first notches 7, one end surface of the sleeve column 8 is screwed with a screw 9, one end of the screw 9 abuts against one end surface of an inner column 10, the distance of the inner column 10 in the sleeve column 8 can be fixed by arranging the screw 9, the effect of screwing and fixing the distance of the current inner column 10 in the sleeve column 8 is achieved, the inner column 10 is inserted into the sleeve column 8, the clamping and mounting position of the mounting plate can be enlarged and reduced by matching the inner column 10 and the sleeve column 8, the effect of adjusting according to the diameter of the current column to be fixed is achieved, one end of the inner column 10 is internally provided with a second notch 12, sleeve 11 is installed in the internal rotation of second breach 12, and sleeve 11 is equipped with four, and four sleeves 11 are the subtend distribution with two sets of, and the inside of two sets of sleeves 11 all inserts and is connected with bolt 15, through sleeve 11 and bolt 15's cooperation, makes four interior posts 10 and four sleeve posts 8 can tightly paste on the cylinder surface of treating the installation, has reached and has screwed up and has carried fixed effect.

The invention needs to be installed before using, firstly, which method is used for installing the invention is decided according to the current situation, the invention is suitable for the construction site, so the clamping and fixing method is suitable, the installing plate 6 of the invention is attached to the surface of the street lamp pole or the upright post body on other construction sites, then the worker manually elongates the inner post 10 contracted in the sleeve post 8 to ensure that the length of the inner post 10 exceeds the diameter of the current post body to be fixed, when the length exceeds the diameter, the worker screws the bolts 15 into the two groups of sleeves 11 to fix the four sleeve posts 8 and the four inner posts 10, at the moment, the worker forcibly pushes the installing plate 6 and the bolts 15 to be attached to the surface of the post body with two hands, and when the worker screws the bolts 9 on the sleeve post 8 after attaching, the worker screws the sleeve post 8 to fix the position of the current inner post 10 in the sleeve post 8 to prevent the inner post 10 from loosening, thus the post installation of the invention is completed, certainly, if a preset hole is formed, the preset hole can be directly fixed by screwing a screw 9 into a fixing hole 16 formed in the surface of the mounting plate 6 in a penetrating mode, after the mounting is finished, a worker supplies power to the camera 2 by using a cable 14 for wiring, then the worker debugs the camera in a terminal control room remotely, after the debugging is finished, the worker can remotely acquire data on a construction site by using the camera 2, and the data are transmitted to the terminal control room through the antenna 13.

Example two:

in the present embodiment, a building construction state monitoring feedback system is constructed. The building construction state monitoring and feedback system can be applied to a building construction state monitoring and feedback device in the first embodiment, and the building construction state monitoring and feedback device is as described in the first embodiment and is not repeated herein.

In this example, a system adopted in the present embodiment will be further described.

In the data processing process, the system sets the yolo detection network to comprise 24 convolutional layers and 2 full-connection layers for processing. The convolutional layer is used for extracting image features, and the full-link layer is used for predicting image position and class probability values.

When the monitoring feedback device with the monitoring feedback system is used, the camera 2 in the monitoring feedback device is used for recording videos of an object to be monitored, then videos in the camera 2 are collected, the videos are converted into images, 24 convolutional layers in the yolo detection network are used for extracting features on the images, meanwhile, the full-connection layer is used for identifying positions and types of the features in the images, finally, monitored actual information is output to workers in a terminal control room through the antenna 13, the workers can record and arrange the obtained information, and real-time monitoring of construction states is achieved.

Example three:

in the present embodiment, a building construction state monitoring feedback method is constructed. The building construction state monitoring and feedback method can be applied to the building construction state monitoring and feedback system in the second embodiment, and the building construction state monitoring and feedback device and the building construction state monitoring and feedback system are as described in the first embodiment and the second embodiment, and are not described herein again.

In this example, the method employed in the present example will be further described.

In order to illustrate the method for monitoring and feeding back the building construction state provided by the present invention, fig. 5 shows a flowchart of the method for monitoring and feeding back the building construction state according to the embodiment of the present invention.

As shown in fig. 5, the building construction state monitoring and feedback method provided by the present invention includes:

step 102, preprocessing a video frame extraction picture;

video acquisition is performed on a camera 2 deployed on a building site, and then frames of the video are extracted into one-frame-by-one-frame images as training data.

And step 104, processing data through a Yolo algorithm.

The method for processing data by the Yolo algorithm comprises three steps, and specifically comprises the following steps: (1) the image in step 102 is cut into small components, for example, the input image is divided into 7 × 7 grids, and an object falling' into the grid is detected through the grids; (2) optimizing the object model detected by the grid by taking the mean square sum error as a loss function; (3) and (4) loss correction, namely further correcting the model after mean square and error optimization to obtain a more accurate model.

And step 106, reporting the result through the algorithm model.

And (4) outputting the model obtained in the step (104) to a terminal control room through an antenna 13, so that a worker obtains a detection result.

By the monitoring feedback method, the working personnel can remotely acquire the data on the construction site, and the real-time monitoring of the data on the construction site is realized. When a worker has a special event, the worker can directly detect the event by using the algorithm model, and the detection result is reported and recorded in time, so that the efficiency of monitoring the construction site can be effectively improved, and the labor cost and the time cost are reduced.

Example four:

an embodiment of the present invention further includes a building construction state monitoring system as shown in fig. 5. Firstly, processing the detected video data into images according to frames, wherein the images are data to be trained and processed. 24 convolutional layers and 2 fully-connected layers were set by the yolo inspection network.

The yolo network mirrors the structure of the GoogLeNet classification network. Except that yolo does not use an open-ended module, but simply replaced with 1x1 convolutional layer +3x3 convolutional layer.

Further, the input image is divided into SxS grids, each grid being responsible for detecting objects 'falling' into the grid. If the coordinates of the center position of an object fall into a certain grid, the grid is responsible for detecting the object.

Further, the mean square sum error is used as a loss function to optimize the model parameters, i.e., the mean square sum error of the S × S (B × 5+ C) dimensional vector of the network output and the corresponding S × S (B × 5+ C) dimensional vector of the real image. As shown in the following formula. Wherein iouError and classror represent coordinate error, IOU error and classification error between the predicted data and the calibration data, respectively.

Further, the calculation of the above expression loss is corrected as follows.

(1) The contribution of the location-related error and the classification error to the network loss is different, so YOLO uses a correction when calculating the loss.

(2) When calculating the IOU error, the lattice containing the object and the lattice not containing the object have different IOU error contributions to the network loss. If the same weight value is adopted, the confidence value of the lattice not containing the object is approximate to 0, and the influence of the confidence error of the lattice containing the object in calculating the network parameter gradient is amplified through phase change. To solve this problem yolo uses a correction.

(3) For equal error values, the effect of large object errors on detection should be less than the effect of small object errors on detection. This is because the proportion of the same positional deviation to large objects is much smaller than the proportion of the same deviation to small objects. YOLO takes the square root of the object size information to improve this problem.

Example five:

an embodiment of the present invention further includes a method for detecting a building construction state monitoring system as shown in fig. 5. Video acquisition is carried out on a camera deployed on a building site, and then the video is extracted into a frame-by-frame image as training data. Video data is processed into images according to frames, a yolo target detection algorithm model in the field of artificial intelligence computer vision algorithms is disclosed, model training and statistics are performed through pictures extracted by a camera detection system, and finally accurate event monitoring and reporting are achieved.

Further, a series of object detection algorithms incorporating deep learning algorithms can roughly fall into two broad categories. 1. Two-step (two-stage) algorithm: candidate regions are generated and then CNN classification (RCNN series) is performed, 2. one-step (one-stage) algorithm: applying algorithms directly to the input image and outputting the classes and corresponding localizations (YOLO series)

Further, for classification, a separate logical classifier is used with a binary cross entropy loss function. The Darknet neural network framework will be used for training and testing. The framework employs multi-scale training, massive data expansion and batch normalization. It is an open source neural network framework written by C and CUDA. The method is high in speed and easy to install, and the CPU and the GPU are supported for calculation. yolo solves the object detection as a regression problem. The input from the original image to the output of the object position and classification is done based on a single end-to-end network.

Further, yolo training and testing are performed in a single network. yolo solves the object detection as a regression problem, and the positions of all objects in the image, the categories of the objects and the corresponding confidence probabilities can be obtained by once verifying the input image.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Claims

1. The utility model provides a building construction state monitoring feedback device, includes camera (2), mounting panel (6), cover post (8) and sleeve (11), its characterized in that: one side fixed surface of mounting panel (6) installs dead lever (5), and the one end fixed mounting of dead lever (5) has carousel (4), and the surface rotation of carousel (4) installs pivot (3), and the fixed surface of pivot (3) installs camera (2), first breach (7) have been seted up at the both ends of mounting panel (6), and the internal rotation of first breach (7) installs sleeve post (8), and the inside of sleeve post (8) has inserted interior post (10), and second breach (12) have been seted up to the one end inside of interior post (10), and sleeve (11) are installed in the internal rotation of second breach (12).

2. The building construction state monitoring and feedback device according to claim 1, wherein: one side of camera (2) is connected and is installed cable (14), and the top fixed mounting of camera (2) has top cap (1), and the top of top cap (1) is equipped with antenna (13).

3. The building construction state monitoring and feedback device according to claim 1, wherein: the inside of mounting panel (6) is run through and is seted up fixed orifices (16), and fixed orifices (16) are equipped with four, and four fixed orifices (16) are the rectangle and distribute.

4. The building construction state monitoring and feedback device according to claim 1, wherein: the sleeve (11) are provided with four, the four sleeves (11) are distributed in an opposite mode in two groups, and bolts (15) are inserted into the two groups of sleeves (11) and connected with the two groups of sleeves.

5. The building construction state monitoring and feedback device according to claim 1, wherein: and a screw (9) is screwed into one end surface of the sleeve column (8), and one end of the screw (9) abuts against one end surface of the inner column (10).

6. A building construction state monitoring feedback system is applied to the feedback device of any one of claims 1 to 5, and is characterized in that the system sets the yolo detection network to comprise 24 convolutional layers and 2 fully-connected layers for processing in the data processing process.

7. A building construction state monitoring feedback method is applied to the feedback system as claimed in claim 6, and is characterized in that detected video data is processed into images according to frames, and the images are data to be trained and processed; the method comprises the following specific steps: step 102, preprocessing a video frame extraction picture; step 104, processing data through a Yolo algorithm; step 106 reports the success of the connection through the algorithm model.