Construction safety information transmission method and system based on intelligent safety helmet

Abstract

The invention relates to the technical field of target detection and face recognition, in particular to a construction safety information transmission method based on an intelligent safety helmet, and the method comprises the steps: firstly determining a feature point location on a target image, and drawing a circular region according to the feature point location; marking each circular region according to the coincidence condition of the shadow contour line in the circular region and the pre-stored shadow contour line in the preset target image, marking the region with a higher coincidence degree as a first-level region, marking the region with an extremely low coincidence degree as a third-level region, and considering that a constructor may wear a mask and the like, marking the contours of the circular regions in the first-level region and the contours of the second-level region as the contours of the third-level region; therefore, whether a face shielding condition exists is analyzed according to the distribution condition of the third-level areas, the number of the various areas is counted, whether matching exists is preliminarily analyzed according to the number proportion of the first-level areas, if the number proportion of the first-level areas is large, matching is judged to be successful, and a recognition qualification signal is sent, so that authorized personnel enter the working area, and the working efficiency is improved. Irrelevant personnel are effectively prevented from entering dangerous places, and the safety risk is reduced from the source.

Description

Technical Field

[0001] The present invention relates to the technical fields of target detection and face recognition, and particularly to a construction safety information transmission method and system based on a smart safety helmet. Background Art

[0002] In recent years, with the development of smart technologies, the application of smart safety helmets in fields such as construction sites has also been studied in China. The research mainly focuses on aspects such as safety management, positioning and tracking, voice control, video control, gas detection, and alarm. Currently, in principle, closed management is implemented at the construction site, an access control system for entry and exit is set up, and biometric recognition technologies such as face, fingerprint, and iris are used for electronic punching. For engineering projects that do not have the conditions for closed management, mobile positioning, electronic fence and other technologies should be used to implement attendance management. The existing technology obtains the construction site information through surveillance cameras, further analyzes whether construction workers wear safety helmets, and identifies the identities of violators, so as to timely grasp the construction safety situation. However, due to the complexity of the construction site, traditional identity recognition methods (such as work permits, card swiping, etc.) are prone to problems such as being misused or lost, and it is easy to generate safety hazards when non-construction personnel enter the construction site.

[0003] Chinese Patent Application No.: CN202410128218.9 discloses a method for detecting safety helmet wearing and identity recognition at a construction site, including: providing a server, as well as a plurality of terminal display devices, a plurality of surveillance cameras and a monitoring system that are communicatively connected to the server. Each surveillance camera obtains the construction site information of its corresponding monitoring area; inputs the construction site information into the monitoring system through the server, analyzes the construction site information, and extracts the image information of construction workers; conducts a safety helmet wearing detection on the construction workers to determine whether there are construction workers not wearing safety helmets. If so, determines the construction workers not wearing safety helmets as violators and obtains the image information of the violators; conducts an identity recognition on the violators to generate an alarm message; and the monitoring system transmits the alarm message to the terminal display device through the server for display. The present invention can detect and alarm the violation behavior of not wearing a safety helmet at the construction site in real time, and can timely and conveniently grasp the construction safety situation.

[0004] However, the existing technology still has the following problems:

[0005] Due to the complexity of the construction site, traditional identity recognition methods are prone to problems such as being misused or lost, and it is easy to generate safety hazards when non-construction personnel enter the construction site. Summary of the Invention

[0006] To this end, the present invention provides a construction safety information transmission method and system based on a smart safety helmet, so as to overcome the problems in the prior art that due to the complexity of the construction site, traditional identity recognition methods are prone to problems such as being misused or lost, and non-construction personnel entering the construction site are prone to safety hazards.

[0007] To achieve the above object, the present invention provides a construction safety information transmission method based on a smart safety helmet. The method includes:

[0008] Step S1, irradiate a target with a plurality of light sources at different positions to collect a plurality of pre-stored target images of a single target and input the pre-stored target images.

[0009] Step S2, the user scans the identification code of the safety helmet with a mobile terminal. When the signal receiving module finishes scanning, it sends an image acquisition signal to the image acquisition module. When the image acquisition module receives the image acquisition signal, it acquires a target image and issues an image analysis instruction, determines the characteristic points of the target image, and draws circular regions with a preset length as the radius centered on each characteristic point.

[0010] Step S3, obtain the shadow contour lines of each of the circular regions, determine the matching pre-stored target image corresponding to the target image based on the shadow contour lines, calculate the coincidence degree between the shadow contour lines of each circular region of the target image and the matching pre-stored target image, and mark each circular region according to the coincidence degree.

[0011] Step S4, count the number of various types of circular regions marked, analyze whether it meets the information transmission standard according to the proportion of the number of primary regions, and send an identification pass signal when it is determined that the information transmission standard is met.

[0012] When it is preliminarily determined that the information transmission standard is not met,

[0013] Based on the distribution of the tertiary regions, make a secondary determination. When it is determined that the face is blocked, re-acquire the target image, and re-analyze whether it meets the information transmission standard based on the re-acquired target image.

[0014] Or, analyze the reason for not meeting the information transmission standard based on the coincidence degree of each tertiary region.

[0015] Further, in step S3, marking each circular region according to the coincidence degree includes:

[0016] Determine the shadow contour lines of each circular region of the target image to obtain the target shadow contour lines.

[0017] Determine the characteristic points corresponding to the pre-stored target image and the target image and the shadow contour lines within each circular region to obtain the comparison shadow contour lines.

[0018] Compare the target shadow contour line with the comparison shadow contour line.

[0019] Determine the contour line length of the overlapping part between the target shadow contour line and the comparison shadow contour line.

[0020] Calculate the ratio of the contour line length of the overlapping part to the total length of the comparison shadow contour line to obtain the matching degree.

[0021] Record the pre-stored target image with the highest matching degree as the matching pre-stored target image.

[0022] Determine the shadow contour line of a single circular area of the target image to obtain the first feature.

[0023] Determine the shadow contour line of the circular area in the matching pre-stored target image corresponding to this circular area to obtain the second feature.

[0024] Compare the first feature with the second feature.

[0025] Determine the contour line length of the overlapping part between the first feature and the second feature.

[0026] Calculate the ratio of the contour line length of the overlapping part to the total length of the first feature to obtain the overlapping degree.

[0027] If the overlapping degree is greater than or equal to the first preset overlapping degree, then determine to mark the circular area as a first-level area.

[0028] If the overlapping degree is less than the first preset overlapping degree and greater than or equal to the second preset overlapping degree, then determine to re-determine the category of the circular area based on the contour line of the non-overlapping part between the first feature and the second feature.

[0029] If the overlapping degree is less than the second preset overlapping degree, then determine to mark the circular area as a third-level area.

[0030] Further, the re-determining the category of the circular area based on the contour line of the non-overlapping part between the first feature and the second feature includes:

[0031] Determine the contour line of the non-overlapping part between the first feature and the second feature.

[0032] Determine the minimum distance between the contour line of the non-overlapping part and the center point of the circular area.

[0033] If the minimum distance is less than or equal to the preset minimum distance, then determine to mark the circular area as a third-level area.

[0034] If the minimum distance is greater than the preset minimum distance, then determine to mark the circular area as a second-level area.

[0035] Further, in step S4, analyzing whether it meets the information transmission standard according to the proportion of the number of first-level regions includes:

[0036] Calculate the ratio of the number of first-level regions to the total number of each circular region to obtain the proportion of the number of first-level regions.

[0037] If the proportion of the number of first-level regions is greater than or equal to the first preset proportion of the number of first-level regions, it is determined that the information transmission standard is met, and an identification pass signal is sent.

[0038] If the proportion of the number of first-level regions is less than the first preset proportion of the number of first-level regions and greater than or equal to the second preset proportion of the number of first-level regions, it is preliminarily determined that the information transmission standard is not met, and it is determined whether the information transmission standard is met again based on the distribution of the third-level regions.

[0039] If the proportion of the number of first-level regions is less than the second preset proportion of the number of first-level regions, it is determined that the information transmission standard is not met, and the reason for not meeting the information transmission standard is analyzed based on the overlap degree of each third-level region.

[0040] Further, the secondary determination of whether it meets the information transmission standard based on the distribution of the third-level regions includes:

[0041] Determine the positions of the marked third-level regions.

[0042] If the distribution of the third-level regions is concentrated, it is determined that there is occlusion on the face, and an occlusion removal signal is sent.

[0043] If the distribution of the third-level regions is dispersed, it is determined that the information transmission standard is not met, and the reason for not meeting the information transmission standard is analyzed based on the overlap degree of each third-level region.

[0044] Further, in step S4, analyzing the reason for not meeting the information transmission standard based on the overlap degree of each third-level region includes:

[0045] Calculate the average overlap degree of each third-level region.

[0046] If the average overlap degree is less than or equal to the preset average overlap degree, it is determined that the reason for not meeting the information transmission standard is based on the proportion of the number of second-level regions.

[0047] If the average overlap degree is greater than the preset average overlap degree, it is determined that the reason for not meeting the information transmission standard is the offset of feature points, and the target image is acquired again.

[0048] Further, the analysis of the reason for not meeting the information transmission standard based on the proportion of the number of second-level regions includes:

[0049] If the proportion of the number of secondary regions is less than or equal to the preset proportion of the number of secondary regions, it is determined that the reason for not meeting the information transmission standard is unqualified target matching, and a warning signal is issued;

[0050] If the proportion of the number of the secondary regions is greater than the preset proportion of the number of secondary regions, it is determined that the reason for not meeting the information transmission standard is unqualified illumination.

[0051] Further, under the condition of determining unqualified illumination, the number of feature points is adjusted based on the proportion of the number of secondary regions, wherein the increase in the number of feature points is positively correlated with the proportion of the number of secondary regions.

[0052] Further, when the adjustment of the number of feature points is completed, new circular regions of the target image are re-determined, step S3 is repeated, the number of various circular regions marked is counted, and whether it meets the information transmission standard is re-analyzed according to the proportion of the number of primary regions re-counted, including:

[0053] If the proportion of the number of primary regions re-counted is greater than or equal to the first preset proportion of the number of primary regions, it is determined that the information transmission standard is met, and an identification pass signal is issued;

[0054] If the proportion of the number of primary regions re-counted is less than the first preset proportion of the number of primary regions, it is determined that the reason for not meeting the information transmission standard is unqualified target matching, and a warning signal is issued.

[0055] The present invention provides a construction safety information transmission system based on a smart safety helmet. It includes:

[0056] An image pre-storage module for storing a number of pre-stored target images and data information of each pre-stored target image;

[0057] A signal receiving module for receiving a scanning qualified signal sent by a signal sending end and sending an image acquisition signal;

[0058] An image acquisition module connected to the signal receiving module for receiving the image acquisition signal sent by the signal receiving module, acquiring a target image, and sending an image analysis instruction;

[0059] An image processing module connected to the image acquisition module for receiving the image analysis instruction sent by the image acquisition module, determining a number of feature points of the target image, and drawing circular regions with a preset length as the radius centered on each feature point;

[0060] The data analysis module is respectively connected to the image pre-storage module, the signal receiving module, the image acquisition module, and the image processing module, and is used to obtain the shadow contour lines in each circular area of the target image, determine the matching pre-stored target image corresponding to the target image based on the shadow contour lines, calculate the coincidence degree between the shadow contour lines of each circular area of the target image and the matching pre-stored target image to mark each circular area, count the number of various types of circular areas marked, and analyze whether it meets the information transmission standard.

[0061] Compared with the prior art, the beneficial effects of the present invention are as follows. In the present invention, the characteristic points on the target image are first determined, circular areas are drawn according to the characteristic points, and each circular area is marked according to the coincidence situation between the shadow contour lines in the circular areas and the pre-stored shadow contour lines in the preset target image. The areas with a higher coincidence degree are recorded as first-level areas, and the areas with a very low coincidence degree are recorded as third-level areas. The number of various types of areas is counted, and it is preliminarily analyzed whether they match according to the proportion of the number of first-level areas. If the proportion of the number of first-level areas is large, it is determined that the match is successful, and an identification qualified signal is sent, so that authorized personnel can enter the working area, effectively preventing unauthorized personnel from entering dangerous places and reducing safety risks from the source.

[0062] Further, in the present invention, the contour lines of the non-coincident parts between the target image and the preset target image are first determined, and the category of the circular area is secondarily analyzed according to the minimum distance between the contour lines of the non-coincident parts and the center point of the circular area. The present invention takes into account that the selected characteristic point position is a relatively protruding point on the face. The farther away from the characteristic point, the more obvious the influence of light, and the greater the interference degree of the shadow contour line. Therefore, when the distance is small, the interference degree of light is small, and the circular area is marked as a third-level area, thereby improving the control accuracy for each area and the analysis accuracy.

[0063] Further, in the present invention, the areas with a low coincidence degree between the target image and the preset target image are marked as third-level areas. Considering the complexity of the construction area and that construction workers may wear masks, etc., it is analyzed whether there is a facial occlusion situation according to the distribution of the third-level areas. When the third-level areas are concentrated, it is determined that the face is occluded, and an occlusion elimination signal is sent to re-acquire the facial image, thereby improving the analysis accuracy of facial recognition. Description of the Drawings

[0064] Figure 1 It is a flowchart of the construction safety information transmission method based on the intelligent safety helmet of the present invention;

[0065] Figure 2 It is a determination flowchart for marking each circular area;

[0066] Figure 3It is a decision flow chart for analyzing whether it meets the information transmission standard;

[0067] Figure 4 It is a decision flow chart for secondary determination of whether it meets the information transmission standard. Specific implementation manners

[0068] In order to make the purpose and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0069] It should be noted that the data in this embodiment are all obtained through comprehensive analysis and evaluation of the historical data in the 6 months before this determination by the system described in the present invention and the corresponding historical determination results. Those skilled in the art can understand that the determination method of the above single parameter by the system described in the present invention can be to select the value with the highest proportion according to the data distribution as the preset standard parameter, use weighted summation to take the obtained value as the preset standard parameter, substitute each historical data into a specific formula and take the value obtained by using this formula as the preset standard parameter or other selection methods, as long as it meets that the system described in the present invention can clearly define different specific situations in the single determination process through the obtained values.

[0070] The preferred implementation manners of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principle of the present invention and do not limit the protection scope of the present invention.

[0071] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention.

[0072] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0073] Please refer to Figure 1 As shown, it is a flow chart of the construction safety information transmission method based on a smart safety helmet of the present invention.

[0074] The construction safety information transmission method based on a smart safety helmet provided in this embodiment includes:

[0075] Step S1: Irradiate the target with light sources at several different positions to collect several pre-stored target images of a single target and input the pre-stored target images.

[0076] Step S2: The user scans the identification code of the safety helmet using a mobile terminal. When the signal receiving module finishes scanning, it sends an image acquisition signal to the image acquisition module. When the image acquisition module receives the image acquisition signal, it acquires a target image and issues an image analysis instruction, determines the characteristic points of the target image, and draws circular regions with a preset length as the radius centered on each characteristic point.

[0077] Step S3: Obtain the shadow contour lines of each of the circular regions, determine the matching pre-stored target images corresponding to the target image based on the shadow contour lines, calculate the coincidence degree between the shadow contour lines of each circular region of the target image and the matching pre-stored target images, and mark each circular region according to this coincidence degree.

[0078] Step S4: Count the number of various types of marked circular regions, analyze whether it meets the information transmission standard based on the proportion of the number of first-level regions. When it is determined that the information transmission standard is met, an identification pass signal is sent.

[0079] When it is preliminarily determined that the information transmission standard is not met,

[0080] Make a secondary determination based on the distribution of the third-level regions. When it is determined that there is an occlusion on the face, re-acquire the target image, and re-analyze whether it meets the information transmission standard based on the re-acquired target image.

[0081] Or analyze the reasons for not meeting the information transmission standard based on the coincidence degree of each third-level region.

[0082] Specifically, in this embodiment, the target is irradiated with light sources at several different positions to collect several pre-stored target images of a single target.

[0083] In the present invention, first, the characteristic points on the target image are determined, circular regions are drawn according to the characteristic points, and each circular region is marked according to the coincidence situation between the shadow contour line in the circular region and the pre-stored shadow contour line in the preset target image. The region with a higher coincidence degree is recorded as the first-level region, and the region with an extremely low coincidence degree is recorded as the third-level region. The number of various types of regions is counted, and it is preliminarily analyzed whether they match according to the proportion of the number of first-level regions. If the proportion of the number of first-level regions is relatively large, it is determined that the matching is successful, and an identification qualified signal is sent, so that authorized personnel can enter the work area, effectively preventing unauthorized personnel from entering dangerous places and reducing safety risks from the source.

[0084] Please refer to Figure 2 as shown, which is a decision flow chart for marking each circular area.

[0085] Specifically, marking each circular area according to the degree of coincidence in step S3 includes:

[0086] Determine the shadow contour lines of each circular area of the target image to obtain the target shadow contour line,

[0087] Determine the characteristic points corresponding to the pre-stored target image and the target image, as well as the shadow contour lines within each circular area, to obtain the comparison shadow contour line,

[0088] Compare the target shadow contour line with the comparison shadow contour line,

[0089] Determine the contour line length of the overlapping part between the target shadow contour line and the comparison shadow contour line,

[0090] Calculate the ratio of the contour line length of the overlapping part to the total length of the comparison shadow contour line to obtain the matching degree,

[0091] Record the pre-stored target image with the highest matching degree as the matching pre-stored target image,

[0092] Determine the shadow contour line of a single circular area of the target image to obtain the first feature,

[0093] Determine the shadow contour line of the circular area in the matching pre-stored target image corresponding to this circular area to obtain the second feature,

[0094] Compare the first feature with the second feature,

[0095] Determine the contour line length of the overlapping part between the first feature and the second feature,

[0096] Calculate the ratio of the contour line length of the overlapping part to the total length of the first feature to obtain the degree of coincidence,

[0097] If the degree of coincidence is greater than or equal to the first preset degree of coincidence, it is determined that the circular area is marked as a first-level area;

[0098] If the degree of coincidence is less than the first preset degree of coincidence and greater than or equal to the second preset degree of coincidence, it is determined to re-determine the category of the circular area based on the contour line of the non-overlapping part between the first feature and the second feature;

[0099] If the degree of coincidence is less than the second preset degree of coincidence, it is determined that the circular area is marked as a third-level area.

[0100] Specifically, in this embodiment, the first preset coincidence degree is selected within the interval [0.9, 0.95], and the second preset coincidence degree is selected within the interval [0.7, 0.75].

[0101] Specifically, the step of secondarily determining the category of the circular region based on the contour line of the non - coincident part between the first feature and the second feature includes:

[0102] Determine the contour line of the non - coincident part between the first feature and the second feature.

[0103] Determine the minimum distance between the contour line of the non - coincident part and the center point of the circular region.

[0104] If the minimum distance is less than or equal to the preset minimum distance, then determine that the circular region is marked as a third - level region.

[0105] If the minimum distance is greater than the preset minimum distance, then determine that the circular region is marked as a second - level region.

[0106] Specifically, in this embodiment, each feature point selects a protruding position in the target image, such as the tip of the nose.

[0107] Specifically, in this embodiment, the preset minimum distance is obtained by pre - measurement. Obtain a plurality of preset target images of the same target at different angles. Arbitrarily select two target images, respectively record the shadow contour lines of the single circular regions of the two target images as the first feature and the second feature, determine the contour line of the non - coincident part, solve the minimum distance between the contour line of the non - coincident part and the center point of the circular region, solve the average value of the minimum distances of the circular regions of the two target images, and the preset minimum distance is 0.8 - 1.05 times of this minimum distance average value.

[0108] In the present invention, first determine the contour line of the non - coincident part between the target image and the preset target image, and perform a secondary analysis on the category of the circular region according to the minimum distance between the contour line of the non - coincident part and the center point of the circular region. The present invention takes into account that the selected feature point positions are relatively protruding points on the face. The farther away from the feature point, the more obvious the influence of light, and the greater the degree of interference of the shadow contour line. Therefore, when the distance is small, the degree of interference by light is small, and the circular region is marked as a third - level region, thereby improving the control accuracy for each region and the analysis accuracy.

[0109] Please refer to Figure 3 as shown, which is a decision flow chart for analyzing whether it meets the information transmission standard.

[0110] Specifically, in step S4, analyzing whether it meets the information transmission standard according to the proportion of the number of first - level regions includes:

[0111] Calculate the ratio of the number of first-level regions to the total number of circular regions to obtain the proportion of the number of first-level regions.

[0112] If the proportion of the number of first-level regions is greater than or equal to the first preset proportion of the number of first-level regions, it is determined that the information transmission standard is met, and an identification pass signal is sent.

[0113] If the proportion of the number of first-level regions is less than the first preset proportion of the number of first-level regions and greater than or equal to the second preset proportion of the number of first-level regions, it is preliminarily determined that the information transmission standard is not met, and it is secondarily determined whether the information transmission standard is met based on the distribution of the third-level regions.

[0114] If the proportion of the number of first-level regions is less than the second preset proportion of the number of first-level regions, it is determined that the information transmission standard is not met, and the reason for not meeting the information transmission standard is analyzed based on the overlap degree of each third-level region.

[0115] Specifically, in this embodiment, the first preset proportion of the number of first-level regions is selected in the interval [0.85, 0.88], and the second preset proportion of the number of first-level regions is selected in the interval [0.72, 0.75].

[0116] Please refer to Figure 4 As shown, it is a determination flowchart for secondarily determining whether the information transmission standard is met.

[0117] Specifically, the secondary determination of whether the information transmission standard is met based on the distribution of the third-level regions includes:

[0118] Determine the positions of the marked third-level regions.

[0119] If the distribution of the third-level regions is concentrated, it is determined that there is a facial occlusion, and an occlusion removal signal is sent.

[0120] If the distribution of the third-level regions is dispersed, it is determined that the information transmission standard is not met, and the reason for not meeting the information transmission standard is analyzed based on the overlap degree of each third-level region.

[0121] In the present invention, the regions with a low overlap degree between the target image and the preset target image are marked as third-level regions. Considering the complexity of the construction area and that construction workers may wear masks, etc., it is analyzed whether there is a facial occlusion situation based on the distribution of the third-level regions. When the distribution of the third-level regions is concentrated, it is determined that the face is occluded, and an occlusion removal signal is sent to re-acquire the facial image, thereby improving the analysis accuracy of facial recognition.

[0122] Specifically, in step S4, analyzing the reason for not meeting the information transmission standard based on the overlap degree of each third-level region includes:

[0123] Calculate the average overlap degree of each third-level region.

[0124] If the average value of the coincidence degree is less than or equal to the preset average value of the coincidence degree, then determine the reason why the analysis of the proportion of the number of the secondary regions does not meet the information transmission standard;

[0125] If the average value of the coincidence degree is greater than the preset average value of the coincidence degree, then determine that the reason for not meeting the information transmission standard is the deviation of the feature points, and re-acquire the target image.

[0126] Specifically, in this embodiment, the preset average value of the coincidence degree is selected within the range of [0.62, 0.66].

[0127] Specifically, the reasons why the analysis of the proportion of the number of the secondary regions does not meet the information transmission standard include:

[0128] If the proportion of the number of the secondary regions is less than or equal to the preset proportion of the secondary number, then determine that the reason for not meeting the information transmission standard is the unqualified target matching, and send out a warning signal;

[0129] If the proportion of the number of the secondary regions is greater than the preset proportion of the secondary number, then determine that the reason for not meeting the information transmission standard is the unqualified illumination.

[0130] Specifically, in this embodiment, the preset proportion of the secondary number is selected within the range of [0.3, 0.35].

[0131] Specifically, under the condition of determining the unqualified illumination, adjust the number of the feature points based on the proportion of the number of the secondary regions, wherein the increase amount of the number of the feature points is positively correlated with the proportion of the number of the secondary regions.

[0132] In this embodiment, optionally,

[0133] Compare the proportion of the number of the secondary regions with the first preset proportion of the number and the second preset proportion of the number,

[0134] If the proportion of the number of the secondary regions is less than or equal to the first preset proportion of the number, then increase the number of the first feature points, and the number of the first feature points is 0.2 times of the initial number of the feature points;

[0135] If the proportion of the number of the secondary regions is greater than the first preset proportion of the number and less than or equal to the second preset proportion of the number, then increase the number of the second feature points, and the number of the second feature points is 0.3 times of the initial number of the feature points;

[0136] If the proportion of the number of the secondary regions is greater than the second preset proportion of the number, then increase the number of the third feature points, and the number of the third feature points is 0.4 times of the initial number of the feature points;

[0137] Among them, the first preset quantity ratio is selected within the range of [0.37, 0.4], and the second preset quantity ratio is selected within the range of [0.42, 0.45].

[0138] Specifically, when the number of feature points is adjusted and completed, the new circular regions of the target image are re-determined, step S3 is repeated, the number of various circular regions marked is counted, and whether it meets the information transmission standard is re-analyzed according to the ratio of the number of the re-counted primary regions, including:

[0139] If the ratio of the number of the re-counted primary regions is greater than or equal to the first preset ratio of the number of primary regions, it is determined that the information transmission standard is met, and an identification pass signal is sent out;

[0140] If the ratio of the number of the re-counted primary regions is less than the first preset ratio of the number of primary regions, it is determined that the reason for not meeting the information transmission standard is that the target matching is unqualified, and a warning signal is sent out.

[0141] The construction safety information transmission system based on the intelligent safety helmet provided in this embodiment includes:

[0142] An image pre-storage module, which is used to store a number of pre-stored target images and the data information of each pre-stored target image;

[0143] A signal receiving module, which is used to receive the scanning qualified signal sent by the signal sending end and send out an image acquisition signal;

[0144] An image acquisition module, which is connected to the signal receiving module, is used to receive the image acquisition signal sent by the signal receiving module, acquire the target image, and send out an image analysis instruction;

[0145] An image processing module, which is connected to the image acquisition module, is used to receive the image analysis instruction sent by the image acquisition module, determine a number of feature points of the target image, and draw circular regions with a preset length as the radius centered on each feature point;

[0146] A data analysis module, which is respectively connected to the image pre-storage module, the signal receiving module, the image acquisition module, and the image processing module, is used to obtain the shadow contour lines in each circular region of the target image, determine the matching pre-stored target image corresponding to the target image based on the shadow contour lines, calculate the coincidence degree of the shadow contour lines of each circular region of the target image and the matching pre-stored target image to mark each circular region, count the number of various circular regions marked, and analyze whether it meets the information transmission standard.

[0147] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0148] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A construction safety information transmission method based on a smart safety helmet, characterized in that, Including: Step S1: Irradiate the target with light sources at several different positions to collect several pre-stored target images of a single target and input the pre-stored target images. Step S2: The user scans the identification code of the safety helmet with a mobile terminal. When the signal receiving module finishes scanning, it sends an image acquisition signal to the image acquisition module. When the image acquisition module receives the image acquisition signal, it acquires a target image and issues an image analysis instruction, determines the characteristic points of the target image, and draws circular regions with a preset length as the radius centered on each characteristic point. Step S3: Obtain the shadow contour lines of each of the circular regions, determine the matching pre-stored target image corresponding to the target image based on the shadow contour lines, calculate the coincidence degree between the shadow contour lines of each circular region of the target image and the matching pre-stored target image, and mark each circular region according to this coincidence degree. Step S4: Count the number of various types of circular regions marked, analyze whether it meets the information transmission standard according to the proportion of the number of first-level regions. When it is determined that the information transmission standard is met, send an identification pass signal. When initially determined not to meet the information transmission standard, Based on the distribution of the third-level regions, make a secondary determination. When it is determined that there is an occlusion on the face, re-acquire the target image, and re-analyze whether it meets the information transmission standard based on the re-acquired target image. Or, analyze the reason for not meeting the information transmission standard based on the coincidence degree of each third-level region.

2. The construction safety information transmission method based on an intelligent safety helmet according to claim 1, wherein In step S3, marking each circular region according to the coincidence degree includes: Determine the shadow contour lines of each circular region of the target image to obtain the target shadow contour line. Determine the characteristic points corresponding to the pre-stored target image and the target image, and the shadow contour lines within each circular region to obtain the comparison shadow contour line. Compare the target shadow contour line with the comparison shadow contour line. Determine the contour line length of the overlapping part between the target shadow contour line and the comparison shadow contour line. Calculate the ratio of the contour line length of the overlapping part to the total length of the comparison shadow contour line to obtain the matching degree. Record the pre-stored target image with the highest matching degree as the matching pre-stored target image. Determine the shadow contour line of a single circular region of the target image to obtain the first feature. Determine the shadow contour line of the circular region in the matching pre-stored target image corresponding to this circular region to obtain the second feature. Compare the first feature with the second feature. Determine the contour line length of the overlapping part between the first feature and the second feature. Calculate the ratio of the contour line length of the overlapping part to the total length of the first feature to obtain the coincidence degree. If the coincidence degree is greater than or equal to the first preset coincidence degree, then determine to mark the circular region as a first-level region. If the coincidence degree is less than the first preset coincidence degree and greater than or equal to the second preset coincidence degree, then determine to make a secondary determination of the category of the circular region based on the contour line of the non-overlapping part between the first feature and the second feature. If the coincidence degree is less than the second preset coincidence degree, then determine to mark the circular region as a third-level region.

3. The construction safety information transmission method based on the intelligent safety helmet according to claim 2, characterized in that, Making a secondary determination of the category of the circular region based on the contour line of the non-overlapping part between the first feature and the second feature includes: Determine the contour line of the non-overlapping part between the first feature and the second feature. Determine the minimum distance between the contour line of the non - overlapping part and the center point of the circular area. If the minimum distance is less than or equal to the preset minimum distance, it is determined that the circular area is marked as a third - level area. If the minimum distance is greater than the preset minimum distance, it is determined that the circular area is marked as a second - level area.

4. The construction safety information transmission method based on a smart safety helmet according to claim 1, wherein, In step S4, analyzing whether it meets the information transmission standard according to the proportion of the number of first - level areas includes: Calculate the ratio of the number of first - level areas to the total number of each circular area to obtain the proportion of the number of first - level areas. If the proportion of the number of first - level areas is greater than or equal to the first preset proportion of the number of first - level areas, it is determined that it meets the information transmission standard, and an identification - passed signal is sent. If the proportion of the number of first - level areas is less than the first preset proportion of the number of first - level areas and greater than or equal to the second preset proportion of the number of first - level areas, it is preliminarily determined that it does not meet the information transmission standard, and it is re - determined whether it meets the information transmission standard based on the distribution of the third - level areas. If the proportion of the number of first - level areas is less than the second preset proportion of the number of first - level areas, it is determined that it does not meet the information transmission standard, and the reason for not meeting the information transmission standard is analyzed based on the overlap degree of each third - level area.

5. The construction safety information transmission method based on the intelligent safety helmet according to claim 4, characterized in that, The re - determination of whether it meets the information transmission standard based on the distribution of the third - level areas includes: Determine the positions of the marked third - level areas. If the third - level areas are concentratedly distributed, it is determined that there is occlusion on the face, and an occlusion - elimination signal is sent. If the third - level areas are dispersedly distributed, it is determined that it does not meet the information transmission standard, and the reason for not meeting the information transmission standard is analyzed based on the overlap degree of each third - level area.

6. The construction safety information transmission method based on the intelligent safety helmet according to claim 1, characterized in that In step S4, analyzing the reason for not meeting the information transmission standard based on the overlap degree of each third - level area includes: Calculate the average value of the overlap degrees of each third - level area. If the average value of the overlap degrees is less than or equal to the preset average value of the overlap degrees, it is determined that the reason for not meeting the information transmission standard is analyzed based on the proportion of the number of second - level areas. If the average value of the overlap degrees is greater than the preset average value of the overlap degrees, it is determined that the reason for not meeting the information transmission standard is the offset of feature points, and the target image is re - obtained.

7. The construction safety information transmission method based on the intelligent safety helmet according to claim 6, wherein Analyzing the reason for not meeting the information transmission standard based on the proportion of the number of second - level areas includes: If the proportion of the number of second - level areas is less than or equal to the preset proportion of the number of second - level areas, it is determined that the reason for not meeting the information transmission standard is unqualified target matching, and a warning signal is sent. If the proportion of the number of second - level areas is greater than the preset proportion of the number of second - level areas, it is determined that the reason for not meeting the information transmission standard is unqualified lighting.

8. The construction safety information transmission method based on an intelligent safety helmet according to claim 7, wherein Under the condition of determining unqualified lighting, adjust the number of feature points based on the proportion of the number of second - level areas, where the increase in the number of feature points is positively correlated with the proportion of the number of second - level areas.

9. The construction safety information transmission method based on the intelligent safety helmet according to claim 8, characterized in that, When the adjustment of the number of feature points is completed, re - determine the new circular areas of the target image, repeat step S3, count the number of various circular areas marked, and re - analyze whether it meets the information transmission standard according to the proportion of the number of first - level areas re - counted, including: If the proportion of the number of first - level areas re - counted is greater than or equal to the first preset proportion of the number of first - level areas, it is determined that it meets the information transmission standard, and an identification - passed signal is sent. If the proportion of the quantity of the re - counted primary regions is less than the first preset proportion of the quantity of primary regions, it is determined that the reason for not meeting the information transmission standard is unqualified target matching, and a warning signal is sent.

10. A construction safety information transmission system based on a smart safety helmet for implementing the method according to any one of claims 1-9, characterized in that, Including: An image pre - storage module, which is used to store a number of pre - stored target images and the data information of each pre - stored target image; A signal receiving module, which is used to receive the scanning qualified signal sent by the signal sending end and send an image acquisition signal; An image acquisition module, which is connected to the signal receiving module, used to receive the image acquisition signal sent by the signal receiving module, acquire a target image, and send an image analysis instruction; An image processing module, which is connected to the image acquisition module, used to receive the image analysis instruction sent by the image acquisition module, determine a number of feature points of the target image, and draw circular regions with a preset length as the radius centered on each feature point; A data analysis module, which is respectively connected to the image pre - storage module, the signal receiving module, the image acquisition module and the image processing module, used to obtain the shadow contour lines in each circular region of the target image, determine the matching pre - stored target image corresponding to the target image based on the shadow contour lines, calculate the coincidence degree between the shadow contour lines of each circular region of the target image and the matching pre - stored target image to mark each circular region, count the quantity of various marked circular regions, and analyze whether it meets the information transmission standard.

Images