Pedestrian protection head shape point database modeling method and device for deep learning
By importing head-type point coordinate files, multi-view screenshots and classifications, the problem of lack of pedestrian protection head-type point database modeling in the existing technology is solved, and high-precision head-type HIC intelligent prediction and database establishment are achieved.
Patent Information
- Application Number
- CN202211301514.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-10-24
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2042-10-24
AI Technical Summary
The existing technology lacks a pedestrian protection head-type point database modeling method, making it difficult to achieve high-precision head-type HIC intelligent prediction.
By importing the head-shaped point coordinate file into the pedestrian protection simulation model, traversing all head-shaped points, taking multi-view screenshots, and classifying the screenshots according to the head-shaped point head injury standards to establish a database.
Automatic screenshots of all points are realized in multi-view angles to ensure that the screenshot size and proportion are consistent, and the screenshots are classified according to the head type HIC, thus establishing an efficient head type point database.
Smart Images

Figure CN115658939B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of modeling, and in particular to a method and device for modeling a pedestrian protection head shape point database for deep learning. Background Art
[0002] Deep learning is widely used in the field of image recognition. It discovers the distributed feature representation of data by learning the intrinsic rules and representation levels of sample data. In the development of pedestrian protection head shape performance, a head shape point database can be built, and deep learning can be used to perform second-level, high-precision intelligent prediction of head shape HIC; however, no modeling method for pedestrian protection head shape point database has been found in the currently available literature. Summary of the invention
[0003] The present invention provides a method and device for modeling a pedestrian protection head shape point database for deep learning, which can realize multi-perspective screenshots of all points, and the screenshot size and scale of all points are consistent. The screenshots can be classified according to the head injury standards of the head shape points, so as to establish a database, filling the gap of the pedestrian protection head shape point database modeling method.
[0004] The technical solution of the present invention is described as follows in conjunction with the accompanying drawings:
[0005] In a first aspect, an embodiment of the present invention provides a method for modeling a pedestrian protection head type point database for deep learning, comprising:
[0006] Step 1: Import the head shape point coordinate file into the pedestrian protection simulation model;
[0007] Step 2: Traverse all head shape points. If not finished, go to step 3; if finished, go to step 4;
[0008] Step 3: Take screenshots of multiple points from multiple perspectives;
[0009] Step 4: Classify the screenshots and finally obtain the head shape point database.
[0010] Furthermore, the taking multi-perspective screenshots of multiple points includes taking multi-perspective screenshots of multiple single points.
[0011] Furthermore, the specific method of taking multi-view screenshots of a single point is as follows:
[0012] 31) Mark the points, point names, and point coordinates of the current head shape;
[0013] 32) Establish the current head shape point auxiliary frame;
[0014] 33) Take a screenshot of the top view of the current point and save it in a folder;
[0015] 34) Take a screenshot of the front view of the current point and save it in a folder;
[0016] 35) Take a screenshot of the left view of the current point and save it in a folder;
[0017] 36) Delete the head shape point auxiliary frame.
[0018] Furthermore, the specific method of taking a multi-view screenshot of a single point in step 33) is as follows:
[0019] 331) Only display the current head shape point auxiliary frame;
[0020] 332) Set the top viewing angle;
[0021] 333) Adapt the size of the view;
[0022] 334) only displays the simulation model;
[0023] 335) Cut the model, take screenshots and save them in a folder.
[0024] Furthermore, the specific method of step 34) is as follows:
[0025] 341) Only display the current head shape point auxiliary frame;
[0026] 342) Set the front view angle;
[0027] 343) Adapt the size of the view;
[0028] 344) only displays the simulation model;
[0029] 345) Cut the model, take screenshots and save them in a folder.
[0030] Furthermore, the specific method of step 35) is as follows:
[0031] 351) Only display the current head shape point auxiliary frame;
[0032] 352) Set the left viewing angle;
[0033] 353) Adapt the size of the view;
[0034] 354) only displays the simulation model;
[0035] 355) Cut the model, take screenshots and save them in a folder.
[0036] Furthermore, the specific method of step 4 is as follows:
[0037] 41) Read the head shape point head injury standard score Excel;
[0038] 42) Obtain the correspondence between the point name and the standard score of head injury;
[0039] 43) Create a new folder, and create a folder with the same name as the head injury standard score under the new folder;
[0040] 44) Read the folder where the multi-angle screenshots are stored;
[0041] 45) Obtain the corresponding relationship between the screenshot name and the screenshot path;
[0042] 46) Move the folder where the multi-angle screenshots are saved to the newly created folder under All Screenshots to complete the classification of the screenshots.
[0043] In a second aspect, an embodiment of the present invention further provides a pedestrian protection head type point database modeling device for deep learning, comprising:
[0044] Import module, used to import the head shape point coordinate file into the pedestrian protection simulation model;
[0045] The traversal module is used to traverse all head shape points;
[0046] Screenshot module, used to take screenshots of multiple points and angles;
[0047] The classification module is used to classify the screenshots and finally obtain the head shape point database.
[0048] In a third aspect, an embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for modeling a pedestrian protection head type point database for deep learning as described in any one of the embodiments of the present invention is implemented.
[0049] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a pedestrian protection head type point database modeling method for deep learning as described in any one of the embodiments of the present invention.
[0050] The beneficial effects of the present invention are:
[0051] 1) The present invention can realize multi-view automatic screenshot of a single point top view, front view, and left view;
[0052] 2) The present invention can realize multi-view automatic screenshots of all points;
[0053] 3) The present invention can achieve consistent screenshot sizes and scales at all viewing angles and points;
[0054] 3) The present invention can classify the screenshots according to the head type HIC, thereby establishing a database. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0056] Figure 1 A flowchart of a method for modeling a pedestrian protection head shape point database for deep learning according to the present invention;
[0057] Figure 2 This is a schematic diagram of the head shape point coordinate file format;
[0058] Figure 3 Schematic diagram of HIC score in Excel format;
[0059] Figure 4 It is a structural schematic diagram of a pedestrian protection head shape point database modeling device for deep learning according to the present invention;
[0060] Figure 5 The figure is a schematic diagram of the structure of an electronic device in the present invention. DETAILED DESCRIPTION
[0061] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0062] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0063] Embodiment 1
[0064] Figure 1 The flowchart of a method for modeling a pedestrian protection head shape point database for deep learning provided in the first embodiment of the present invention is applicable to the case of modeling a pedestrian protection head shape point database for deep learning. The method can be executed by the device for modeling a pedestrian protection head shape point database for deep learning in the embodiment of the present invention. The method specifically includes the following steps:
[0065] See also Figure 1 , a pedestrian protection head type point database modeling method for deep learning, comprising the following steps:
[0066] Step 1: Import the head shape point coordinate file into the pedestrian protection simulation model; the details are as follows:
[0067] 11) Open the pedestrian protection simulation model as follows:
[0068] 111) Open PRIMER software;
[0069] 112) In PRIMER software, select and open the pedestrian protection simulation model through "Model|Read";
[0070] 12) Import the head shape point coordinate file as follows:
[0071] 121) In PRIMER software, select and open the automation script through "Tools|Script";
[0072] 122) Click the "select" button after the automation script "1.points file", select and import the head shape point coordinate file (assigned to the variable file_point_list), the file format is as follows Figure 2 shown.
[0073] Step 2: Traverse all head shape points. If not finished, go to step 3; if finished, go to step 4.
[0074] Step 3: Take screenshots of multiple points from multiple perspectives;
[0075] The taking multi-view screenshots of multiple points includes taking multi-view screenshots of multiple single points.
[0076] The specific method of taking multi-view screenshots of a single point is as follows:
[0077] 31) Mark the points, point names, and point coordinates of the current head shape; the method is as follows:
[0078] The current head shape point is recorded as cur_point, the point name is recorded as cur_point_name, and the point x, y, and z coordinates are recorded as cur_point_x, cur_point_y, and cur_point_z respectively;
[0079] 32) Establish the current head shape point auxiliary frame, recorded as cur_point_frame; the method is as follows:
[0080] Use "var part_cur_point_frame=new Part(m_p,Part.NextFreeLabel(m_p),999,999,"auto_frame")" to create the part where the auxiliary frame cur_point_frame is located, recorded as part_cur_point_frame, where m_p is the current pedestrian protection simulation model, the first 999 is the attribute number of the part (null value), the second 999 is the material number of the part (null value), and "auto_frame" is the name of the current part;
[0081] part_cur_point_frame contains only one solid type unit, which is denoted as s and is created using “var s=new Solid(m_p,Solid.NextFreeLabel(m_p),p.pid,n2.nid,n1.nid,n4.nid,n3.nid,n6.nid,n5.nid,n8.nid,n7.nid)”. This unit is a cube with 8 nodes, namely n1-n8. n1 is created using “var n1=new Node(m_p,Node.NextFreeLabel(m_p),cur_point_x-size / 2,cur_point_y+size / 2,cur_point_z+size / 2)”, n2 is created using “var n2=new Node(m_p,Node.NextFreeLabel(m_p),cur_point_x+size / 2,cur_point_y+size / 2,cur_point_z+size / 2)”, and n3 is created using “var n3=new Node(m_p,Node.NextFreeLabel(m_p),cur_point_x+size / 2,cur_point_y+size / 2,cur_point_z-size / 2)" is created, n4 is created using "var n4=new Node(m_p,Node.NextFreeLabel(m_p),cur_point_x-size / 2,cur_point_y+size / 2,cur_point_z-size / 2)" is created, n5 uses "var n5=new Node(m_p,Node.NextFreeLabel(m_p),cur_point_x-size / 2,cur_point_y-size / 2,cur_point_z+size / 2)" is created, n6 uses "var n6=new Node(m_p,Node.NextFreeLabel(m_p),cur_point_x+size / 2,cur_point_y-size / 2,cur_point_z+size / 2)" is created, n7 uses "var n7=new Node(m_p,Node.NextFreeLabel(m_p),cur_point_x+size / 2,cur_point_y-size / 2,cur_point_z-size / 2)" is created, n8 is created using "var n8=new Node(m_p,Node.NextFreeLabel(m_p),cur_point_x-size / 2,cur_point_y-size / 2,cur_point_z-size / 2)” is established, where size is the side length of the cube s.
[0082] 33) Take a screenshot of the top view of the current point and save it in a folder; the details are as follows:
[0083] 331) Only display the current head shape point auxiliary frame, the method is: use "Part.BlankAll(m_p)" to hide all parts, and use "Part.GetFromID(m_p,cur_point_frame.pid).Unblank()" to display the current head shape point auxiliary frame, that is, cur_point_frame;
[0084] 332) Set the top viewing angle: Use "View.Show (+View.XY)" to set the PRIMER software workspace to the top viewing angle;
[0085] 333) Adapt the view size by using “View.Ac()” to adapt the view size of the PRIMER software workspace;
[0086] 334) Only display the simulation model, the method is: use "Part.UnblankAll(m_p)" to display all parts, use "Part.GetFromID(m_p,cur_point_frame.pid).Blank()" to hide the current head shape point auxiliary frame, that is, cur_point_frame;
[0087] 335) Cut the model, take a screenshot and save it into a folder. The method is as follows: in PRIMER software, open the PRIMER software macro recording function through "Tools|Macro|Record", then create an x-section at the x-coordinate of the head shape point through "Tools|Cut sect", and take a screenshot of the workspace through "Images|Image file" and save it to the folder result_path to obtain a screenshot of the top perspective of the simulation model, and the screenshot name is "point name_top"; embed the generated macro file into the automation script to realize screenshot automation.
[0088] 34) Take a screenshot of the front view of the current point and save it in a folder; the details are as follows:
[0089] 341) Only display the current head shape point auxiliary frame, the method is: use "Part.BlankAll(m_p)" to hide all parts, and use "Part.GetFromID(m_p,cur_point_frame.pid).Unblank()" to display the current head shape point auxiliary frame, that is, cur_point_frame;
[0090] 342) Set the front view by:
[0091] Use "View.Show (-View.YZ)" to set the PRIMER software workspace to the front perspective;
[0092] 343) Adapt the view size by using “View.Ac()” to adapt the view size of the PRIMER software workspace;
[0093] 344) Only display the simulation model, the method is: use "Part.UnblankAll(m_p)" to display all parts, use "Part.GetFromID(m_p,cur_point_frame.pid).Blank()" to hide the current head shape point auxiliary frame, that is, cur_point_frame;
[0094] 345) Cut the model, take a screenshot and save it into a folder. The method is as follows: in PRIMER software, open the PRIMER software macro recording function through "Tools|Macro|Record", then create an x-section at the x-coordinate of the head shape point through "Tools|Cut sect", and take a screenshot of the workspace through "Images|Image file" and save it to the folder result_path to obtain a screenshot of the simulation model from the front perspective, with the screenshot name "point name_front"; embed the generated macro file into the automation script to realize screenshot automation.
[0095] 35) Take a screenshot of the left view of the current point and save it in a folder; the specific method is as follows:
[0096] 351) Only display the current head shape point auxiliary frame, the method is: use "Part.BlankAll(m_p)" to hide all parts, and use "Part.GetFromID(m_p,cur_point_frame.pid).Unblank()" to display the current head shape point auxiliary frame, that is, cur_point_frame;
[0097] 352) Set the left viewing angle: Use "View.Show (+View.XZ)" to set the PRIMER software workspace to the left viewing angle;
[0098] 353) Adapt the view size by using “View.Ac()” to adapt the view size of the PRIMER software workspace;
[0099] 354) Only display the simulation model, the method is: use "Part.UnblankAll(m_p)" to display all parts, use "Part.GetFromID(m_p,cur_point_frame.pid).Blank()" to hide the current head shape point auxiliary frame, that is, cur_point_frame;
[0100] 355) Cut the model, take a screenshot and save it into a folder. The method is as follows: in PRIMER software, open the PRIMER software macro recording function through "Tools|Macro|Record", then create an x-section at the x-coordinate of the head shape point through "Tools|Cut sect", and take a screenshot of the workspace through "Images|Image file" and save it to the folder result_path to obtain a screenshot of the left perspective of the simulation model, and the screenshot name is "point name_left"; embed the generated macro file into the automation script to realize screenshot automation.
[0101] 36) Delete the head shape point auxiliary frame, as follows:
[0102] Use "var ps = Part.GetAll(m_p)" to get the array ps composed of all parts; use "var flag_del = AllocateFlag()" to define the label flag_del; use a for loop to iterate over all parts in ps. If the title of a part (assuming it is ps[i]) is "auto_frame", use "ps[i].SetFlag(flag_del)" to set the label "flag_del" for the part; use "m_p.DeleteFlagged(flag_del)" to delete all parts with the label "flag_del".
[0103] Step 4: Classify the screenshots and finally obtain the head shape point database. This step is implemented through Python programming, as follows:
[0104] 41) Read the Excel file of head injury standard score of head shape points, the method is: import the pandas library, use "df = pd.read_excel("D: / head shape HIC0 score.xlsx", header = None)" to read the Excel file of head shape HIC score, that is, "D: / head shape HIC0 score.xlsx";
[0105] 42) Obtain the correspondence between the point name and the head injury standard score. The method is as follows: use "point_hic = []" to create an empty list to store the correspondence between the point name and the HIC score; use "for i in range(df.shape[0]-1)" to traverse each row of the Excel file of the head shape point HIC score; use "for j in range(1,df.shape[1])” to traverse each column of the Excel of the head shape point HIC score; use “point=str(int(df.iat[i,0]))+'_'+str(int(df.iat[df.shape[0]-1,j]))” to get the current point name; use “hic=str(df.iat[i,j])” to get the current point HIC score; use “point_hic.append(point+'_'+hic)” to put the current point name and the current point HIC score into point_hic to get the corresponding relationship between the point name and the HIC score. The Excel format of the HIC score is as follows: Figure 3 As shown;
[0106] 43) Create an img_path folder, and create a folder with the same name as the head injury standard score under img_path;
[0107] 44) Read all the screenshots in the result_path folder, the method is: import the os library, use "img_path = 'D: / pic-label / '" to define the variable img_path, that is, the head shape point database folder; use "imgs = []" to create an empty list for storing the screenshot file path; use "for root, dirs, files in os.walk(result_path)" to traverse all the contents in the screenshot folder; use "for file in files:" to traverse all the screenshots in the screenshot folder; use "imgs.append(os.path.join(root,file))" to put the current screenshot file path into imgs;
[0108] 45) Get the correspondence between the screenshot name and the screenshot path by: using "for point in point_hic" to traverse the correspondence between all point names and HIC scores; using "for img in imgs" to traverse all screenshot file paths;
[0109] 46) Move all screenshots under result_path to the corresponding folder under img_path by using “ifpoint.split('_')[0]==img.split('_')[1]and point.split('_')[1]==img.split('_')[2]:” to determine whether the point name of the current screenshot file is the same as the point name of the current screenshot file path. If they are the same, use “mkdir(img_path+point.split('_')[2])” to create a folder with the same name as the HIC score under img_path, and use “shutil.copy(img,dstpath+img_path+point.split('_')[2]+' / '+im.split('_')[-1])” to copy the current screenshot file to the folder with the same name as the HIC score to complete the screenshot classification;
[0110] 47) Finally, the head shape point database is obtained, that is, the "D: / pic-label / " folder.
[0111] Embodiment 2
[0112] Figure 4 This is a schematic diagram of a device for deep learning of a pedestrian protection head shape point database modeling provided in the second embodiment of the present invention. This embodiment is applicable to the case of deep learning of pedestrian protection head shape point database modeling. The device can be implemented in software and / or hardware. The device can be integrated in any device that provides the function of pedestrian protection head shape point database modeling, such as Figure 4 As shown, the device comprises:
[0113] Import module, used to import the head shape point coordinate file into the pedestrian protection simulation model;
[0114] The traversal module is used to traverse all head shape points;
[0115] Screenshot module, used to take screenshots of multiple points and angles;
[0116] The classification module is used to classify the screenshots and finally obtain the head shape point database.
[0117] The above-mentioned product can execute the method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0118] Embodiment 3
[0119] Figure 5 This is a schematic diagram of the structure of a computer device in Embodiment 3 of the present invention. Figure 5 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 5 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0120] like Figure 5 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).
[0121] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.
[0122] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.
[0123] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.
[0124] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.
[0125] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), may also communicate with one or more devices that enable a user to interact with the computer device 12, and / or communicate with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through an input / output (I / O) interface 22. In addition, the computer device 12 in this embodiment, the display 24 does not exist as an independent individual, but is embedded in the mirror surface, and when the display surface of the display 24 is not displayed, the display surface of the display 24 and the mirror surface are visually integrated. In addition, the computer device 12 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) through a network adapter 20. As shown in the figure, the network adapter 20 communicates with other modules of the computer device 12 through a bus 18. It should be understood that although not shown in the figures, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0126] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, for example, implementing a pedestrian protection head type point database modeling method for deep learning provided by an embodiment of the present invention.
[0127] Embodiment 4
[0128] Embodiment 4 of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, a method for modeling a pedestrian protection head type point database for deep learning is implemented as provided in all the embodiments of the invention of this application.
[0129] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.
[0130] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0131] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0132] Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0133] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A pedestrian protection head type point database modeling method for deep learning, characterized in that: The following steps are involved: Step 1: Import the head shape point coordinate file into the pedestrian protection simulation model; Step 2: Traverse all head shape points. If not finished, go to step 3; if finished, go to step 4; Step 3: Take screenshots of multiple points from multiple perspectives; Step 4: Classify the screenshots and finally obtain the head shape point database; The taking multi-view screenshots of multiple points includes taking multi-view screenshots of multiple single points; The specific method of taking multi-view screenshots of a single point is as follows: 31) Mark the points, point names, and point coordinates of the current head shape; 32) Establish the current head shape point auxiliary frame; 33) Take a screenshot of the top view of the current point and save it in a folder; 34) Take a screenshot of the front view of the current point and save it in a folder; 35) Take a screenshot of the left view of the current point and save it in a folder; 36) Delete the head shape point auxiliary frame; The specific method of taking a multi-view screenshot of a single point in step 33) is as follows: 331) Only display the current head shape point auxiliary frame; 332) Set the top viewing angle; 333) Adapt the size of the view; 334) only displays the simulation model; 335) Cut the model, take screenshots and save them in a folder; The specific method of step 34) is as follows: 341) Only display the current head shape point auxiliary frame; 342) Set the front view angle; 343) Adapt the size of the view; 344) only displays the simulation model; 345) Cut and screenshot the model and save it in a folder; The specific method of step 35) is as follows: 351) Only display the current head shape point auxiliary frame; 352) Set the left viewing angle; 353) Adapt the size of the view; 354) only displays the simulation model; 355) Cut the model, take screenshots and save them in a folder; The specific method of step 4 is as follows: 41) Read the head shape point head injury standard score Excel; 42) Obtain the correspondence between the point name and the standard score of head injury; 43) Create a new folder, and create a folder with the same name as the head injury standard score under the new folder; 44) Read the folder where the multi-angle screenshots are stored; 45) Obtain the corresponding relationship between the screenshot name and the screenshot path; 46) Move the folder where the multi-angle screenshots are saved to the newly created folder under All Screenshots to complete the classification of the screenshots.
2. A pedestrian protection head shape point database modeling device for deep learning, used to execute the pedestrian protection head shape point database modeling method for deep learning according to claim 1, characterized in that: include: Import module, used to import the head shape point coordinate file into the pedestrian protection simulation model; The traversal module is used to traverse all head shape points; Screenshot module, used to take screenshots of multiple points and angles; The classification module is used to classify the screenshots and finally obtain the head shape point database.
3. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, a pedestrian protection head type point database modeling method for deep learning as described in claim 1 is implemented.
4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a pedestrian protection head type point database modeling method for deep learning as described in claim 1 is implemented.
