Building construction intelligent supervision method and system

Abstract

The invention discloses a building construction intelligent supervision method and system. And removing the building areas which do not need to be monitored. And displaying the time duration used by each construction machine category by using a punctuation point on a circle with different radiuses, and judging by adopting a category detection network. When the category detection network is trained, a similar comparison image is extracted. And during real-time monitoring, judging the time duration used by each construction machine category and the time duration used by the construction machine category in the similar comparison image so as to judge whether the use mode of the construction machine is similar to the use mode of the construction machine at ordinary times or not. The technical effect that whether the construction machine breaks down or not is monitored more accurately in the mode of monitoring the running path and the residence time of the construction machine is achieved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and system for intelligent supervision of building construction. Background Art

[0002] At present, intelligent building supervision is often used in construction and building management, which usually refers to the use of advanced technologies such as the Internet of Things, big data analysis and artificial intelligence to improve the management efficiency and sustainability of the construction industry. By deploying sensor networks and connecting devices, data about the operating status of buildings can be collected, including energy consumption, environmental conditions, facility maintenance needs, etc. However, since automated or semi-automated construction machines are often used in construction, the working status of construction machines needs to be supervised. And for construction machines used by humans, it is necessary to monitor whether there is abuse of the machine or theft, so as to supervise the construction machines. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for intelligent supervision of building construction, so as to solve the above-mentioned problems existing in the prior art.

[0004] In a first aspect, an embodiment of the present invention provides a method for intelligent supervision of building construction, comprising:

[0005] A construction map, a plurality of construction machine categories and corresponding construction machine positions at a plurality of time points are obtained; the construction machine positions represent positions where the construction machines move in the construction map; the construction map represents a map of an area including construction;

[0006] Based on the construction machine category, the use status of the construction machine is determined through a category detection network to obtain the category of the machine to be detected; the category of the machine to be detected represents the category of the construction machine that needs to be fault detected;

[0007] Based on the type of machine to be detected and the location of the construction machine at multiple time points, the fault is predicted through the location path network, and the faulty machine number is obtained;

[0008] A signal is sent to stop the construction machine corresponding to the faulty machine number.

[0009] Optionally, based on the category of the construction machine, the use status of the construction machine is determined through a category detection network to obtain the category of the machine to be detected, including:

[0010] The total working time of a construction machine category in a day is obtained as the construction machine time length; multiple construction machine categories are correspondingly obtained with multiple construction machine time lengths;

[0011] Divide 360 ​​by the construction machine category to get the gap angle;

[0012] The center point of the construction map is used as the judgment point;

[0013] According to the gap angle, the construction machine categories are sequentially filled into the positions of the distance determination dots in the construction map as the time length of the construction machines, and a construction association image is obtained; the construction association image represents the closeness of the association of the construction machines when constructing the building;

[0014] Based on the construction-related image, the category of the machine to be detected is obtained through a category detection network.

[0015] The construction-related image and the similarity comparison image are input into a category detection network to obtain a predicted construction category similarity value. If the predicted construction category similarity value is greater than a similarity threshold, the construction machine category corresponding to the construction-related image is used as the machine category to be detected.

[0016] Optionally, the method of determining the use status of the construction machine based on the type of the machine to be detected and the location of the construction machine at multiple time points through a location path network to obtain the faulty machine number includes:

[0017] Marking the positions of the construction machines at the multiple time points on the construction map, and if a position is repeatedly passed, subtracting 1 from the gray value to obtain a construction machine position map;

[0018] Acquire a building location; the building location indicates a location of a building under construction;

[0019] Marking the building location in the construction machine location map to obtain a marked building image;

[0020] A circle is drawn with the building position in the marked building image as the center and a fixed distance as the radius to obtain a building area; the building area represents an area where the construction machine can stay for a long time;

[0021] Based on the marked building image including the building area, the use status of the construction machine is judged through the location path network to obtain an error judgment value; the error judgment value of 1 indicates that the path of the construction machine does not conform to the path of the construction machine in normal operation; the error judgment value of 0 indicates that the path of the construction machine conforms to the path of the construction machine in normal operation;

[0022] The number corresponding to the construction machine with the error judgment value of 1 is used as the number of the machine to be detected.

[0023] Optionally, the training method of the category detection network includes:

[0024] Acquire a plurality of training construction-related images; the training construction-related images represent a plurality of construction machine categories and corresponding construction machine time lengths;

[0025] Acquire annotation data; if the annotation data is 1, it indicates that the construction is normal, and if the annotation data is 0, it indicates that an error occurs during the construction;

[0026] Input two training construction-related images into the category detection network, judge the similarity of the images, and obtain the construction category similarity value; n training construction-related images correspond to (n-1)n / 2 construction category similarity values;

[0027] Based on the construction category similarity values, the category detection network is trained by back propagation to obtain a trained category detection network.

[0028] Optionally, the back-propagation training of the category detection network based on the construction category similarity value to obtain the trained category detection network includes:

[0029] The training construction-related images corresponding to the construction category similarity values ​​greater than the similarity threshold are used as the training set;

[0030] Annotating the training construction-related images in the training set as similar to obtain annotated data;

[0031] The construction machine time length corresponding to the same angle of the corresponding training construction-related images in the training set is averaged to obtain a similarity comparison image; the similarity comparison image represents a benchmark for similarity judgment;

[0032] Inputting the training construction-related image and the similarity comparison image into a category detection network to obtain a training similarity value;

[0033] The training similarity value and the representation data are used to calculate the loss, and the training category detection network is back-propagated to obtain a trained category detection network.

[0034] Optionally, the method of determining the use status of the construction machine based on the marked building image containing the building area through the location path network to obtain the error determination value includes:

[0035] Acquire a road image; the road image represents an image marking a road in the construction image on which the construction machine can travel;

[0036] Based on the marked building image including the building area, removing the building area portion to obtain a driving path image;

[0037] Input the driving path image and the road image into the position path network, determine the driving path of the construction machine, and obtain a path similarity value; the path similarity value indicates whether the driving path of the construction machine has gone out of the position of the path in the road image;

[0038] Based on the driving path image, the length of the stay time is determined to obtain a stay time similarity value; the stay time similarity value indicates whether the stay time of the construction machine at different locations complies with regulations;

[0039] Based on the path similarity value and the stay time similarity value, an error determination value is obtained.

[0040] Optionally, judging the length of stay time based on the driving path image to obtain a stay time similarity value includes:

[0041] Obtaining a dwell time value; the dwell time value represents a fixed dwell time length;

[0042] Converting the grayscale value in the driving path image that is equal to the length of the stay time into the grayscale value of the length of the stay time minus 1 to obtain a long-term stay position for construction;

[0043] Obtaining the number of fixed positions; the number of fixed positions indicates limiting the number of times the construction machine stays for a long time;

[0044] The construction long-term stay position is divided by the number of fixed positions to obtain the stay time similarity value.

[0045] Optionally, obtaining an error discrimination value based on the path similarity value and the stay time similarity value includes:

[0046] If the path similarity value is less than or equal to the path threshold, and the stay time similarity value is less than or equal to the stay threshold, the error discrimination value is set to 1;

[0047] If the path similarity value is greater than the path threshold, or the stay time similarity value is greater than the stay threshold, the error judgment value is set to 0.

[0048] Optionally, the removing the building area portion based on the marked building image including the building area to obtain the driving path image includes:

[0049] Converting the labeled building image containing the building area into a binary image to obtain a binary construction machine path image;

[0050] The value of the building area in the binary construction machine path image is set to 255 to obtain a driving path image; the driving path image represents an image without the influence of the construction machine staying in the construction area.

[0051] In a second aspect, an embodiment of the present invention provides a construction intelligent supervision system, including:

[0052] An acquisition module, used to obtain a construction map, a plurality of construction machine categories and corresponding construction machine positions at a plurality of time points; the construction machine positions represent positions where the construction machines move in the construction map; the construction map represents a map of an area including construction;

[0053] A category detection module, used to determine the use status of the construction machine based on the construction machine category through a category detection network to obtain the category of the machine to be detected; the category of the machine to be detected represents the category of the construction machine that needs to be fault detected;

[0054] A fault detection module is used to predict faults and obtain fault machine numbers through a location path network based on the type of machine to be detected and the location of the construction machine at multiple time points;

[0055] The signal sending module is used to send a signal to stop the construction machine corresponding to the faulty machine number.

[0056] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects:

[0057] The embodiments of the present invention also provide a method and system for intelligent supervision of building construction.

[0058] In the present invention, since the construction machine stays in the construction area, it is convenient for construction, or the construction machine is being used for construction, the construction area does not need to be monitored. The different lengths of time used for each construction machine category outside the construction area indicate that the use of the construction machine is different from the usual efficient use method. The length of time used for each construction machine category is displayed with a punctuation point on a circle with different radius, and a category detection network is used for judgment. During training, the category detection network extracts a similar comparison image. During real-time monitoring, the length of time used for each construction machine category is distinguished from the length of time used for the construction machine category in the similar comparison image, so as to judge whether it is similar to the usual use method of the construction machine. The driving path of the construction machine without the construction area is used to judge whether it is different from the set driving path. A two-dimensional grayscale image is used to jointly represent the stop position of the construction machine and the length of time corresponding to the stop position, and the one-dimensional data representing the length of time the construction machine stays is converted into a grayscale value on the two-dimensional image. A more accurate technical effect of monitoring whether the construction machine fails by monitoring the driving path and the stop time of the construction machine is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flow chart of a method for intelligent supervision of building construction provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0061] Example 1

[0062] like Figure 1 As shown, an embodiment of the present invention provides a method for intelligent supervision of building construction, the method comprising:

[0063] S101: Obtain a construction map, a plurality of construction machine categories and corresponding construction machine positions at a plurality of time points; the construction machine positions represent positions where construction machines move in the construction map; the construction map represents a map of an area including construction.

[0064] The position of the construction machine is recorded by a positioning device fixed on the construction machine.

[0065] The construction machine category indicates the category to which the construction machine belongs, such as an excavator and a mixer belong to two different construction machine categories.

[0066] The construction map is a grayscale image, and the initial grayscale value of the construction map is 255. The grayscale value of the grayscale image means that the grayscale image is initially white.

[0067] In this embodiment, the length and width of the construction map are the same, which is 512*512.

[0068] S102: Based on the construction machine category, the use status of the construction machine is determined through a category detection network to obtain the category of the machine to be detected; the category of the machine to be detected indicates the category of the construction machine that needs to be detected for faults;

[0069] S103: Based on the type of the machine to be detected and the location of the construction machine at multiple time points, predict the fault through the location path network and obtain the faulty machine number;

[0070] S104: Send a signal to stop the construction machine corresponding to the faulty machine number.

[0071] Among them, if reuse is required, manual approval is required.

[0072] Optionally, the predicting faults based on the construction machine category through a category detection network to obtain the category of the machine to be detected includes:

[0073] The total working time of a construction machine category in a day is obtained as the construction machine time length; multiple construction machine categories correspond to multiple construction machine time lengths.

[0074] The unit of the construction machine time length is minute.

[0075] Divide 360 ​​by the construction machine category to get the gap angle.

[0076] The center point of the construction map is used as the judgment point.

[0077] According to the gap angle, the construction machine categories are sequentially filled into the positions of the distance judgment dots in the construction map as the time length of the construction machines to obtain a construction association image; the construction association image represents the closeness of the association between the construction machines when constructing a building.

[0078] The construction machine time length is divided by (24*60) multiplied by the width of the grayscale image to obtain the construction machine radius.

[0079] The bottom corner of the grayscale image is used as the origin, the length of the grayscale image is used as the horizontal coordinate, and the width of the grayscale image is used as the vertical coordinate.

[0080] Among them, as in this embodiment, the construction machine category is 36, 360 / 36=10. The direction parallel to the horizontal axis and the horizontal axis value from small to large is regarded as 0 degrees. In the direction of 0 degrees, find the position where the cluster discrimination circle center is the construction machine radius of a construction machine category and mark it. Rotate 10 degrees clockwise, find the position where the cluster discrimination circle center is the construction machine radius corresponding to another construction machine category, and mark it.

[0081] Among them, the construction machine category corresponding to each angle is fixed.

[0082] Based on the construction-related image, the category of the machine to be detected is obtained through a category detection network.

[0083] Optionally, the method of determining the use status of the construction machine based on the type of the machine to be detected and the location of the construction machine at multiple time points through a location path network to obtain the faulty machine number includes:

[0084] The positions of the construction machines at the multiple time points are marked on the construction map. If a position is passed through repeatedly for 5 times, the gray value is reduced by 1 to obtain a construction machine position map.

[0085] If a position is repeatedly passed for 5 times, the gray value will be reduced by 1 until the gray value is equal to 0.

[0086] Among them, because (256*5)>(24*60), the grayscale value is increased by 1 only after 5 times of random use.

[0087] Acquire a building location; the building location indicates a location of a building under construction;

[0088] Marking the building location in the construction machine location map to obtain a marked building image;

[0089] A circle is drawn with the building position in the marked building image as the center and a fixed distance as the radius to obtain a building area; the building area represents an area where the construction machine can stay for a long time.

[0090] In this embodiment, the fixed distance is 5, the unit is pixel value, corresponding to 512*512 of the construction map.

[0091] Based on the marked building image containing the building area, the usage status of the construction machine is judged through the location path network to obtain an error judgment value; the error judgment value of 1 indicates that the path of the construction machine does not conform to the path of the construction machine in normal operation; the error judgment value of 0 indicates that the path of the construction machine conforms to the path of the construction machine in normal operation.

[0092] The number corresponding to the construction machine with the error judgment value of 1 is used as the number of the machine to be detected.

[0093] Optionally, the training method of the category detection network includes:

[0094] Acquire a plurality of training construction-related images; the training construction-related images represent a plurality of construction machine categories and corresponding construction machine time lengths;

[0095] Obtain the annotation data; if the annotation data is 1, it indicates that the construction is normal; if the annotation data is 0, it indicates that an error occurs during the construction.

[0096] Among them, normal construction means that the construction is carried out according to the construction machines of the fixed construction machine category, and errors in the construction mean that the construction machines are used randomly.

[0097] Two training construction-related images are input into the category detection network to judge the similarity of the images and obtain the construction category similarity value; n training construction-related images correspond to (n-1)n / 2 construction category similarity values.

[0098] Wherein, n is a natural number greater than 0.

[0099] Among them, the similarity recognition network is the discriminator of the generative adversarial network (GAN).

[0100] Based on the construction category similarity values, the category detection network is trained by back propagation to obtain a trained category detection network.

[0101] Optionally, the back-propagation training of the category detection network based on the construction category similarity value to obtain the trained category detection network includes:

[0102] The training construction-related images corresponding to the construction category similarity values ​​greater than the similarity threshold are used as the training set.

[0103] In this embodiment, the similarity threshold is 0.8.

[0104] The training construction-related images in the training set are marked as similar, and the training construction-related images that are not in the training set are marked as dissimilar, so as to obtain marked data.

[0105] In this embodiment, the labeled data marked as similar is 1, and the labeled data marked as dissimilar is 0.

[0106] The construction machine time length corresponding to the same angle of the corresponding training construction-related images in the training set is averaged to obtain a similarity comparison image; the similarity comparison image represents a benchmark for similarity judgment;

[0107] The training construction-related image and the similarity comparison image are input into a category detection network to obtain a training similarity value.

[0108] Among them, the category detection network is used twice, the first time is equivalent to clustering, and the second time is to obtain a network that can distinguish similar contrast images after clustering.

[0109] The training similarity value and the representation data are used to calculate the loss, and the training category detection network is back-propagated to obtain a trained category detection network.

[0110] Optionally, the method of determining the use status of the construction machine based on the marked building image containing the building area through the location path network to obtain the error determination value includes:

[0111] Acquire a road image; the road image represents an image marking a road in the construction image on which the construction machine can travel;

[0112] Based on the marked building image including the building area, the building area portion is removed to obtain a driving path image.

[0113] Wherein, removing the construction area portion means that there is no limit on the length of time the construction machine stays in the construction area.

[0114] The driving path image and the road image are input into the position path network to determine the driving path of the construction machine and obtain a path similarity value; the path similarity value indicates whether the driving path of the construction machine has gone out of the position of the path in the road image.

[0115] Among them, in this embodiment, the position path network is the structure of the discriminator of the generative adversarial network (GAN).

[0116] Based on the driving path image, the length of the stay time is determined to obtain a stay time similarity value; the stay time similarity value indicates whether the stay time of the construction machine at different locations complies with regulations.

[0117] Based on the path similarity value and the stay time similarity value, an error determination value is obtained.

[0118] Through the above method, the driving route is different from the set route, and the location and duration of the stay are different from usual, indicating that someone has stolen and abused the driving machine.

[0119] Optionally, judging the length of stay time based on the driving path image to obtain a stay time similarity value includes:

[0120] A dwell time value is obtained; the dwell time value indicates a fixed dwell time length.

[0121] In this embodiment, the time dwell value is set to 2.

[0122] Converting the grayscale value in the driving path image that is equal to the length of the stay time into the grayscale value of the length of the stay time minus 1 to obtain a long-term stay position for construction;

[0123] Obtaining the number of fixed positions; the number of fixed positions indicates limiting the number of times the construction machine stays for a long time;

[0124] The construction long-term stay position is divided by the number of fixed positions to obtain the stay time similarity value.

[0125] Optionally, obtaining an error discrimination value based on the path similarity value and the stay time similarity value includes:

[0126] If the path similarity value is less than or equal to the path threshold, and the stay time similarity value is less than or equal to the stay threshold, the error judgment value is set to 1.

[0127] The stay threshold is 0.85.

[0128] If the path similarity value is greater than the path threshold, or the stay time similarity value is greater than the stay threshold, the error judgment value is set to 0.

[0129] The path threshold is 0.9.

[0130] Optionally, the removing the building area portion based on the marked building image including the building area to obtain the driving path image includes:

[0131] Converting the labeled building image containing the building area into a binary image to obtain a binary construction machine path image;

[0132] The value of the building area in the binary construction machine path image is set to 255 to obtain a driving path image; the driving path image represents an image without the influence of the construction machine staying in the construction area.

[0133] Example 2

[0134] Based on the above-mentioned intelligent construction supervision method, an embodiment of the present invention further provides an intelligent construction supervision system, which includes an acquisition module, a category detection module, a fault detection module and a signal sending module.

[0135] An acquisition module is used to obtain a construction map, multiple construction machine categories and corresponding construction machine positions at multiple time points; the construction machine positions represent the positions where the construction machines move in the construction map; and the construction map represents a map of an area containing construction.

[0136] The category detection module is used to determine the use status of the construction machine based on the construction machine category through the category detection network to obtain the category of the machine to be detected; the category of the machine to be detected represents the category of the construction machine that needs to be fault detected.

[0137] The fault detection module is used to predict faults and obtain the faulty machine number through the location path network based on the machine category to be detected and the location of the construction machine at multiple time points.

[0138] The signal sending module is used to send a signal to stop the construction machine corresponding to the faulty machine number.

Claims

1. A method for intelligent supervision of building construction, characterized in that: include: A construction map, a plurality of construction machine categories and corresponding construction machine positions at a plurality of time points are obtained; the construction machine positions represent positions where the construction machines move in the construction map; the construction map represents a map of an area including construction; Based on the construction machine category, the use status of the construction machine is determined through a category detection network to obtain the category of the machine to be detected; the category of the machine to be detected represents the category of the construction machine that needs to be fault detected; Based on the type of machine to be detected and the location of the construction machine at multiple time points, the fault is predicted through the location path network, and the faulty machine number is obtained; A signal is sent to stop the construction machine corresponding to the faulty machine number.

2. The intelligent construction supervision method according to claim 1 is characterized in that: Based on the category of the construction machine, the use status of the construction machine is determined through a category detection network to obtain the category of the machine to be detected, including: The total working time of a construction machine category in a day is obtained as the construction machine time length; multiple construction machine categories are correspondingly obtained with multiple construction machine time lengths; Divide 360 ​​by the construction machine category to get the gap angle; The center point of the construction map is used as the judgment point; According to the gap angle, the construction machine categories are sequentially filled into the positions of the distance determination dots in the construction map as the time length of the construction machines, and a construction association image is obtained; the construction association image represents the closeness of the association of the construction machines when constructing the building; Based on the construction-related image, the category of the machine to be detected is obtained through a category detection network.

3. The intelligent construction supervision method according to claim 1 is characterized in that: The method of determining the use status of the construction machine based on the type of the machine to be detected and the location of the construction machine at multiple time points through the location path network to obtain the faulty machine number includes: Marking the positions of the construction machines at the multiple time points on the construction map, and if a position is repeatedly passed, subtracting 1 from the gray value to obtain a construction machine position map; Acquire a building location; the building location indicates a location of a building under construction; Marking the building location in the construction machine location map to obtain a marked building image; A circle is drawn with the building position in the marked building image as the center and a fixed distance as the radius to obtain a building area; the building area represents an area where the construction machine can stay for a long time; Based on the marked building image including the building area, the use status of the construction machine is judged through the location path network to obtain an error judgment value; the error judgment value of 1 indicates that the path of the construction machine does not conform to the path of the construction machine in normal operation; the error judgment value of 0 indicates that the path of the construction machine conforms to the path of the construction machine in normal operation; The number corresponding to the construction machine with the error judgment value of 1 is used as the number of the machine to be detected.

4. The intelligent construction supervision method according to claim 2 is characterized in that: The training method of the category detection network comprises: Acquire a plurality of training construction-related images; the training construction-related images represent a plurality of construction machine categories and corresponding construction machine time lengths; Acquire annotation data; if the annotation data is 1, it indicates that the construction is normal, and if the annotation data is 0, it indicates that an error occurs during the construction; Input two training construction-related images into the category detection network, judge the similarity of the images, and obtain the construction category similarity value; n training construction-related images correspond to (n-1)n / 2 construction category similarity values; Based on the construction category similarity values, the category detection network is trained by back propagation to obtain a trained category detection network.

5. The intelligent construction supervision method according to claim 4 is characterized in that: The back propagation training of the category detection network based on the construction category similarity value to obtain the trained category detection network includes: The training construction-related images corresponding to the construction category similarity values ​​greater than the similarity threshold are used as the training set; Annotating the training construction-related images in the training set as similar to obtain annotated data; The construction machine time length corresponding to the same angle of the corresponding training construction-related images in the training set is averaged to obtain a similarity comparison image; the similarity comparison image represents a benchmark for similarity judgment; Inputting the training construction-related image and the similarity comparison image into a category detection network to obtain a training similarity value; The training similarity value and the representation data are used to calculate the loss, and the training category detection network is back-propagated to obtain a trained category detection network.

6. The intelligent construction supervision method according to claim 3 is characterized in that: The method of determining the use status of the construction machine based on the marked building image including the building area through the location path network to obtain the error determination value includes: Acquire a road image; the road image represents an image marking a road in the construction image on which the construction machine can travel; Based on the marked building image including the building area, removing the building area portion to obtain a driving path image; Input the driving path image and the road image into the position path network, determine the driving path of the construction machine, and obtain a path similarity value; the path similarity value indicates whether the driving path of the construction machine has gone out of the position of the path in the road image; Based on the driving path image, the length of the stay time is determined to obtain a stay time similarity value; the stay time similarity value indicates whether the stay time of the construction machine at different locations complies with regulations; Based on the path similarity value and the stay time similarity value, an error determination value is obtained.

7. The intelligent construction supervision method according to claim 6 is characterized in that: The step of determining the length of stay time based on the driving path image and obtaining a stay time similarity value includes: Obtaining a dwell time value; the dwell time value represents a fixed dwell time length; Converting the grayscale value in the driving path image that is equal to the length of the stay time into the grayscale value of the length of the stay time minus 1 to obtain a long-term stay position for construction; Obtaining the number of fixed positions; the number of fixed positions indicates limiting the number of times the construction machine stays for a long time; The construction long-term stay position is divided by the number of fixed positions to obtain the stay time similarity value.

8. The intelligent construction supervision method according to claim 6 is characterized in that: The step of obtaining an error discrimination value based on the path similarity value and the residence time similarity value includes: If the path similarity value is less than or equal to the path threshold, and the stay time similarity value is less than or equal to the stay threshold, the error discrimination value is set to 1; If the path similarity value is greater than the path threshold, or the stay time similarity value is greater than the stay threshold, the error judgment value is set to 0.

9. The intelligent construction supervision method according to claim 6 is characterized in that: The step of removing the building area portion based on the marked building image including the building area to obtain the driving path image includes: Converting the labeled building image containing the building area into a binary image to obtain a binary construction machine path image; The value of the building area in the binary construction machine path image is set to 255 to obtain a driving path image; the driving path image represents an image without the influence of the construction machine staying in the construction area.

10. An intelligent construction supervision system, characterized in that: include: An acquisition module, used to obtain a construction map, a plurality of construction machine categories and corresponding construction machine positions at a plurality of time points; the construction machine positions represent positions where the construction machines move in the construction map; the construction map represents a map of an area including construction; A category detection module, used to determine the use status of the construction machine based on the construction machine category through a category detection network to obtain the category of the machine to be detected; the category of the machine to be detected represents the category of the construction machine that needs to be fault detected; A fault detection module is used to predict faults and obtain fault machine numbers through a location path network based on the type of machine to be detected and the location of the construction machine at multiple time points; The signal sending module is used to send a signal to stop the construction machine corresponding to the faulty machine number.

Images