CN111695423A - Crime scene map generation method, system and storage medium based on three-dimensional reconstruction - Google Patents
Crime scene map generation method, system and storage medium based on three-dimensional reconstruction Download PDFInfo
- Publication number
- CN111695423A CN111695423A CN202010376135.3A CN202010376135A CN111695423A CN 111695423 A CN111695423 A CN 111695423A CN 202010376135 A CN202010376135 A CN 202010376135A CN 111695423 A CN111695423 A CN 111695423A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- crime scene
- model
- scene
- graph
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Abstract
The invention discloses a crime scene graph generation method, a system and a storage medium based on three-dimensional reconstruction, wherein the method comprises the following steps: three-dimensional scanning is carried out on a crime scene to obtain three-dimensional data, and a three-dimensional real scene model of the crime scene is established by combining the three-dimensional data and a preset artificial intelligence algorithm; and acquiring a crime scene graph according to the three-dimensional real scene model, wherein the crime scene graph comprises a plane scale graph and/or a solid scale graph. According to the invention, the crime scene is scanned, and after the three-dimensional real scene model is established, the plane scale map and the three-dimensional scale map of the crime scene are directly obtained according to the three-dimensional real scene model, so that manual drawing is not needed, the drawing cost is greatly reduced, meanwhile, the occurrence of manual drawing errors is avoided, and the drawing quality is improved. In addition, the proportion graph obtained through the three-dimensional real-scene model can record details of a crime scene in detail, improves the scientificity of drawing, and can be widely applied to the technical field of data processing.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a crime scene map generation method and system based on three-dimensional reconstruction and a storage medium.
Background
Crime scene investigation is the starting point for case detection. The fixation, restoration and reconstruction of the crime scene must comprehensively and objectively reflect the real situation of the scene. For a long time, on-site surveyors are influenced by hardware equipment, technical conditions and professional levels, and at present, cases are still analyzed and researched by using the forms of manual drawing, on-site photos, PPT and the like.
At present, when drawing is carried out on a crime scene, a manual drawing mode is mainly adopted, the current dimension is surveyed firstly, and a scene structure diagram is drawn after scaling so as to display the structure layout in the scene, therefore, a professional drawing worker needs to spend much time on drawing; if the data measured manually has errors, errors of the structure chart can also be caused. In addition, such a drawing is generally a black and white line drawing, and simply outlines the structure of the appearance field, and omits a detailed screen in the building, which is not favorable for objectively reflecting the situation of the field.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a crime scene map generating method, system and storage medium based on three-dimensional reconstruction, which can automatically generate a crime scene structure map without drawing by a professional.
The technical scheme adopted by the invention is as follows:
a crime scene graph generation method based on three-dimensional reconstruction comprises the following steps:
three-dimensional scanning is carried out on a crime scene to obtain three-dimensional data, and a three-dimensional real scene model of the crime scene is established by combining the three-dimensional data and a preset artificial intelligence algorithm;
and acquiring a crime scene graph according to the three-dimensional real scene model, wherein the crime scene graph comprises a plane scale graph and/or a solid scale graph.
Further, the three-dimensional live-action model is a three-dimensional live-action model in a building room, and the method further comprises the step of generating a two-dimensional house type map, and specifically comprises the following steps:
and acquiring point cloud data of the three-dimensional live-action model, and acquiring an indoor two-dimensional indoor type map according to the point cloud data.
Further, the step of obtaining an indoor two-dimensional indoor layout according to the point cloud data includes:
slicing the three-dimensional model according to the point cloud data of the three-dimensional model to obtain point cloud data of a model section;
and connecting the point cloud data of the model section by adopting a preset deep learning algorithm to generate an indoor two-dimensional house pattern.
Further, the step of obtaining the plane scale map of the crime scene according to the three-dimensional real-scene model specifically comprises:
and acquiring a display picture of the three-dimensional real scene model under the overlooking angle, and generating a plane scale map by combining the display picture and a preset mark.
Further, the step of obtaining the three-dimensional scale map of the crime scene according to the three-dimensional live-action model specifically comprises:
and after deleting the three-dimensional live-action model according to a preset mode, acquiring a display picture of the three-dimensional live-action model at a preset angle, and generating a stereoscopic scale map by combining the display picture and a preset mark.
Further, the method also comprises the following steps:
after the input instruction information is acquired, the stereo scale chart is displayed in a partition mode so as to display the local structure of the crime scene.
Further, the method also comprises a step of constructing the virtual object, which specifically comprises the following steps:
in the three-dimensional live-action model, acquiring size information and grain characteristics of evidence traces;
and constructing an object three-dimensional model corresponding to the evidence trace by combining the size information, the texture characteristics and a preset algorithm.
The other technical scheme adopted by the invention is as follows:
a crime scene map generation system based on three-dimensional reconstruction, comprising:
the modeling module is used for carrying out three-dimensional scanning on the crime scene to obtain three-dimensional data and establishing a three-dimensional real scene model of the crime scene by combining the three-dimensional data and a preset artificial intelligence algorithm;
and the drawing module is used for acquiring a crime scene graph according to the three-dimensional real scene model, and the crime scene graph comprises a plane scale graph and/or a solid scale graph.
The other technical scheme adopted by the invention is as follows:
a crime scene map generation system based on three-dimensional reconstruction, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method described above.
The other technical scheme adopted by the invention is as follows:
a storage medium having stored therein processor-executable instructions for performing the method as described above when executed by a processor.
The invention has the beneficial effects that: according to the invention, the crime scene is scanned, and after the three-dimensional real scene model is established, the plane scale map and the three-dimensional scale map of the crime scene are directly obtained according to the three-dimensional real scene model, so that manual drawing is not needed, the drawing cost is greatly reduced, meanwhile, the occurrence of manual drawing errors is avoided, and the drawing quality is improved. In addition, the proportion graph obtained through the three-dimensional real-scene model can record details of a crime scene in detail, and the drawing accuracy is improved.
Drawings
Fig. 1 is a flowchart illustrating steps of a crime scene map generation method based on three-dimensional reconstruction according to an embodiment;
FIG. 2 is a schematic illustration of a perspective view of an on-site survey in an embodiment;
FIG. 3 is a schematic diagram of a three-dimensional real-world model for field survey in an embodiment;
FIG. 4 is a first schematic view of a plan scale view of the embodiment;
FIG. 5 is a second schematic view of a plan view of the embodiment;
FIG. 6 is a schematic view of an example of a perspective view;
FIG. 7 is a schematic illustration of the partitioned display of FIG. 6;
FIG. 8 is a schematic diagram of a kitchen mark in a three-dimensional real-world model of a crime scene in an embodiment;
FIG. 9 is a schematic diagram of a bedroom mark in a three-dimensional real-world model of a crime scene in an embodiment;
FIG. 10 is a schematic diagram of point cloud data of a section in a three-dimensional real-scene model in an embodiment;
FIG. 11 is a schematic diagram of a two-dimensional house type graph obtained after processing point cloud data in the embodiment;
FIG. 12 is a schematic plan view of evidence traces in an example;
FIG. 13 is a schematic diagram of an embodiment of building a virtual object based on evidence traces;
FIG. 14 is a schematic illustration of a three-dimensional model of a tool according to an embodiment;
fig. 15 is a block diagram of a crime scene map generation system based on three-dimensional reconstruction in the embodiment.
Detailed Description
The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention.
It should be noted that, unless otherwise specified, when a feature is referred to as being "fixed" or "connected" to another feature, it may be directly fixed or connected to the other feature or indirectly fixed or connected to the other feature. Furthermore, the descriptions of upper, lower, left, right, etc. used in the present disclosure are only relative to the mutual positional relationship of the constituent parts of the present disclosure in the drawings. As used in this disclosure, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any combination of one or more of the associated listed items.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element of the same type from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present disclosure. The use of any and all examples, or exemplary language ("e.g.," such as "or the like") provided herein, is intended merely to better illuminate embodiments of the invention and does not pose a limitation on the scope of the invention unless otherwise claimed.
In the conventional technology, a professional person must draw a crime scene, if the crime scene is complicated or has a large area, a worker needs to perform on-site investigation and finish drawing for several days, so that a large amount of manpower is consumed, and the efficiency is low. Human errors may also occur with manual drawing, such as errors in sizing, or errors in drawing labels, etc. In addition, in the manual drawing, only a simple line drawing can be drawn, details in the drawing are omitted, and the scene cannot be scientifically and objectively reflected.
Based on the above problem, as shown in fig. 1, the present embodiment provides a crime scene map generating method based on three-dimensional reconstruction, including the following steps:
s1, carrying out three-dimensional scanning on the crime scene to obtain three-dimensional data, and establishing a three-dimensional real scene model of the crime scene by combining the three-dimensional data and a preset artificial intelligence algorithm;
s2, obtaining a crime scene graph according to the three-dimensional real scene model, wherein the crime scene graph comprises a plane scale graph and/or a solid scale graph.
In this embodiment, the crime scene including indoor or outdoor robbery, theft, or injury is scanned in all directions. The field can be scanned by using an existing scanning device, and specifically, the scanning device can be an aerial photography scanning device, an indoor scanning device, an outdoor scanning device or a tool scanning device. The aerial photography scanning device can be aerial photography equipment such as an aerial photography airplane and the like and is used for scanning three-dimensional data of an area range (such as a whole house) in a scene. An indoor scanning device for scanning three-dimensional data of an indoor environment (e.g., a room in a house). The indoor scanning device can be a handheld scanning device (such as a camera with a support frame) or other automatic scanning device (such as an automatic scanning robot). The outdoor scanning device is used for scanning three-dimensional data of an outdoor environment (such as a road beside a certain house) and can be a handheld scanning device (such as a camera with a support frame) or other automatic scanning devices (such as an automatic scanning robot). The tool scanning device is used for carrying out all-dimensional scanning on the criminal tool, and can adopt the existing object scanning device. Wherein the three-dimensional data comprises a two-dimensional picture and depth information.
The scanning equipment sends the image data scanned on site to a modeling cloud platform, and in the modeling cloud platform, a preset artificial intelligence algorithm is adopted to carry out three-dimensional reconstruction on the image data, so that a three-dimensional model on site is generated, and point cloud data of the three-dimensional model are obtained. The three-dimensional reconstruction content comprises model repairing, clipping, face reducing, model reducing, compression, material processing, map processing and lamplight processing, and can be realized by adopting the conventional artificial intelligence algorithm. The three-dimensional model comprises a stereogram and a three-dimensional real scene model, and is a stereogram as shown in FIG. 2; as shown in fig. 3, a three-dimensional real scene model. The structure of the whole indoor layout can be visually seen clearly in the stereogram, in the three-dimensional live-action model, a user can check the field situation at a first visual angle, and can roam in the field live-action by inputting a switching instruction to watch the pictures at all angles.
The method comprises the following steps of obtaining a plane scale map of a crime scene according to a three-dimensional real-scene model, and specifically comprises the following steps:
and acquiring a display picture of the three-dimensional real scene model under the overlooking angle, and generating a plane scale map by combining the display picture and a preset mark.
The plan scale map is a structural plan map based on a reduced preset scale, the traditional structural map is mainly a top-view structural map, and the whole indoor or outdoor structural layout condition can be seen clearly through the top view. Referring to fig. 4, in this embodiment, a top view picture of the three-dimensional real scene model is directly obtained, the layout structure of the whole room can be clearly seen through the top view picture, and a proportional parameter is added, where the proportional parameter is a proportional relation between the size on the plan view and the real size. The scale parameters can be labeled in two ways, the first way is: referring to fig. 5, scale parameters are added directly outside the graph; the second way is: while the scale parameter was added outside the figure, the length lines are also indicated inside the figure.
The method comprises the following steps of obtaining a three-dimensional scale map of a crime scene according to a three-dimensional live-action model, wherein the steps specifically comprise:
and after deleting the three-dimensional live-action model according to a preset mode, acquiring a display picture of the three-dimensional live-action model at a preset angle, and generating a stereoscopic scale map by combining the display picture and a preset mark.
The stereoscopic proportion map is a stereoscopic map which is displayed in a reduced manner based on the actual size, and the three-dimensional live-action model is deleted in two manners, wherein the first manner is as follows: referring to fig. 2, model data of a ceiling in a room is deleted, a display screen is displayed at an angle from top to bottom, and a stereoscopic proportion map is obtained after the display screen is labeled. The second way is: referring to fig. 6, model data of a ceiling and walls of a building are deleted, a display screen is displayed at an angle from top to bottom, and a stereoscopic proportion map is obtained after the display screen is labeled. The method for obtaining the stereo scale map in the second mode further comprises the following steps:
after the input instruction information is acquired, the stereo scale chart is displayed in a partition mode so as to display the local structure of the crime scene.
This is because, when a crime scene is a multistory building, a factory building having a large area, or a construction site, and a three-dimensional real view model is displayed, it is difficult for a worker to clearly understand a local situation because the three-dimensional situation is too complicated. For example, in a multiple apartment house at a crime scene, referring to fig. 6, the perspective view includes layers, and the side of detection can be clearly seen when viewed from the side of the perspective view, and when the layout of the structures of the layers needs to be overlooked, it is difficult to clearly see due to the overlapping of the two layers of screens. Therefore, in this embodiment, the staff may switch the display condition of the perspective view by inputting an instruction, for example, only displaying the perspective view of the lower-level building, as shown in fig. 7, so that the influence of the perspective view of the upper-level building can be avoided, and the layout condition of each floor can be viewed more clearly and intuitively. Optionally, when the current great factory building of area of crime, then can carry out the subregion on the plane, so, the staff can look over first district earlier, looks over areas such as second district again, and the scene of crime situation is known to the staff of greatly making things convenient for.
Further as an optional implementation manner, the method further includes a step of generating a two-dimensional floor plan, specifically as steps a1 to A3:
and A1, acquiring point cloud data of the three-dimensional real scene model.
A2, slicing the three-dimensional model according to the point cloud data of the three-dimensional model to obtain point cloud data of a model section;
and A3, connecting the point cloud data of the model section by adopting a preset deep learning algorithm to generate an indoor two-dimensional house model graph.
As shown in the upper right corner of fig. 8, a two-dimensional house type diagram of the indoor building is displayed in the three-dimensional real-scene model, so that when a picture in the three-dimensional real-scene model is played, a worker can know the position of the picture in the room, and the worker can know the case more conveniently. For example, the position of fig. 8 is a kitchen, in the middle of a house; whereas in fig. 9 the position of the master bedroom is shown, wherein in fig. 8 and 9 also detailed traces within the scene are marked, such as hair and fruit knives etc. Specifically, as shown in fig. 10, in order to obtain a schematic diagram of point data obtained by slicing point cloud data, since the point cloud data are generated in a later stage, points on the point cloud data are discrete and not a complete solid line, and therefore, a later-stage connection process is required, and finally, an indoor two-dimensional house type diagram is generated, as shown in fig. 11. Therefore, the two-dimensional household map can be automatically generated based on the point cloud data, manual investigation and manual drawing of workers on site are not needed, the investigation efficiency is greatly improved, errors in the manual investigation process can be greatly avoided, and the quality of site investigation is improved. The point cloud data comprises point cloud data of objects (such as objects), and the point cloud of each object can be obtained by segmenting and identifying the point cloud data by adopting a preset AI algorithm. The mode is obtained by slicing the whole three-dimensional model, and besides the mode, the two-dimensional user-type diagram can also be generated by acquiring the two-dimensional point cloud data of each part of the three-dimensional model and combining the two-dimensional point cloud data of each part.
Further as an optional implementation manner, the method further includes a step of constructing the virtual object, specifically:
in the three-dimensional live-action model, acquiring size information and grain characteristics of evidence traces;
and constructing an object three-dimensional model corresponding to the evidence trace by combining the size information, the texture characteristics and a preset algorithm.
Referring to fig. 12, in this embodiment, a shoe mark is used for illustration, and according to the size of the shoe mark and the pattern of the sole, a preset deep learning algorithm is combined to make up the appearance of the shoe, and finally the made up shoe is shown in fig. 13. Aiming at shoe printing, general workers hardly think the appearance of shoes unless criminal policemen with related experience can imagine the types (sports shoes or sneakers) and the structures (outlines, shapes and the like) of the shoes, and the workers can know the case more conveniently by fictitious shapes of the shoes. The picture of the virtual shoe is not directly displayed in the three-dimensional live-action model, the three-dimensional live-action model only displays the shoe print, when a worker needs to check, the worker can specifically set a trigger key (such as beside the shoe print) on the three-dimensional live-action model by triggering and calling related data, and after the worker clicks the trigger key, the three-dimensional model of the virtual shoe is automatically played. The playing mode may be a bullet frame mode, and the virtual module may be directly displayed on the three-dimensional real-scene model, for example, a virtual shoe is displayed on the shoe print, as shown in fig. 13.
Further as an optional implementation, the method further includes a tool scanning step, specifically:
the method comprises the steps of scanning a tool to be scanned in an all-around manner to generate a three-dimensional model of the tool;
and acquiring the size information of the tool according to the three-dimensional model of the tool, and marking the size information on the three-dimensional model of the tool.
Referring to fig. 14, for some key tools, such as a crime tool, an auxiliary tool or a tool left by a criminal, the tool can be scanned in all directions at the first time of field investigation, and a three-dimensional model of the tool is established, when a later worker needs to check the tool, the worker does not need to search related photos or physical objects, and only needs to call corresponding data to check the data, and the worker can check the tool by 360 degrees by inputting switching information. When the tool three-dimensional model is stored on the cloud platform, workers in different places can log in the cloud platform to check, and more convenience is brought to multiple collaborative case handling. Furthermore, a trigger button is arranged in the three-dimensional real-scene model, for example, the tool is a planning tool, the trigger button is arranged at a position beside the tool in the three-dimensional real-scene model, when a worker needs to check the three-dimensional model of the tool, the worker directly clicks the trigger button to automatically call data, and the three-dimensional model of the tool is displayed.
In summary, compared with the prior art, the present embodiment has at least the following beneficial effects:
(1) and timely: the crime scene is quickly copied by utilizing three-dimensional scanning (object, space and aerial photography) equipment and an automatic modeling technology of artificial intelligence, and the efficiency of scene investigation is greatly improved.
(2) And objectively: the randomness is rejected, each object and the state thereof on the spot are objectively recorded, and real and reliable space scene data and material evidence position relation are provided. And display the evidence trace or the size of the tool in an intuitive manner.
(3) And science: big data is stored and displayed and is returned to the site at any time for analysis, case data is never damaged or lost, online collaborative case handling is supported, and the effect of meeting the necessity of minutes and seconds is achieved.
As shown in fig. 15, this embodiment further provides a crime scene map generating system based on three-dimensional reconstruction, including:
the modeling module is used for carrying out three-dimensional scanning on the crime scene to obtain three-dimensional data and establishing a three-dimensional real scene model of the crime scene by combining the three-dimensional data and a preset artificial intelligence algorithm;
and the drawing module is used for acquiring a crime scene graph according to the three-dimensional real scene model, and the crime scene graph comprises a plane scale graph and/or a solid scale graph.
The crime scene graph generation system based on three-dimensional reconstruction according to the embodiment of the invention can execute the crime scene graph generation method based on three-dimensional reconstruction provided by the embodiment of the invention, can execute any combination implementation steps of the embodiment of the method, and has corresponding functions and beneficial effects of the method.
The embodiment further provides a crime scene map generation system based on three-dimensional reconstruction, which includes:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method described above.
The crime scene graph generation system based on three-dimensional reconstruction according to the embodiment of the invention can execute the crime scene graph generation method based on three-dimensional reconstruction provided by the embodiment of the invention, can execute any combination implementation steps of the embodiment of the method, and has corresponding functions and beneficial effects of the method.
The present embodiments also provide a storage medium having stored therein processor-executable instructions, which when executed by a processor, are configured to perform the method as described above.
The storage medium of this embodiment may execute the crime scene map generation method based on three-dimensional reconstruction provided by the method embodiment of the present invention, may execute any combination of the implementation steps of the method embodiment, and has corresponding functions and beneficial effects of the method.
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein.
A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means. The invention is capable of other modifications and variations in its technical solution and/or its implementation, within the scope of protection of the invention.
Claims (10)
1. A crime scene graph generation method based on three-dimensional reconstruction is characterized by comprising the following steps:
three-dimensional scanning is carried out on a crime scene to obtain three-dimensional data, and a three-dimensional real scene model of the crime scene is established by combining the three-dimensional data and a preset artificial intelligence algorithm;
and acquiring a crime scene graph according to the three-dimensional real scene model, wherein the crime scene graph comprises a plane scale graph and/or a solid scale graph.
2. The crime scene graph generation method based on three-dimensional reconstruction as claimed in claim 1, wherein the three-dimensional real scene model is a three-dimensional real scene model in a building room, further comprising a step of generating a two-dimensional house type graph, specifically:
and acquiring point cloud data of the three-dimensional live-action model, and acquiring an indoor two-dimensional indoor type map according to the point cloud data.
3. The method for generating a crime scene map based on three-dimensional reconstruction as claimed in claim 2, wherein the step of obtaining an indoor two-dimensional house type map from point cloud data comprises:
slicing the three-dimensional model according to the point cloud data of the three-dimensional model to obtain point cloud data of a model section;
and connecting the point cloud data of the model section by adopting a preset deep learning algorithm to generate an indoor two-dimensional house pattern.
4. The method for generating a crime scene map based on three-dimensional reconstruction according to claim 1, wherein the step of obtaining a plane scale map of the crime scene according to the three-dimensional real-scene model specifically comprises:
and acquiring a display picture of the three-dimensional real scene model under the overlooking angle, and generating a plane scale map by combining the display picture and a preset mark.
5. The method for generating a crime scene map based on three-dimensional reconstruction according to claim 1, wherein the step of obtaining the stereoscopic proportion map of the crime scene according to the three-dimensional real-scene model specifically comprises:
and after deleting the three-dimensional live-action model according to a preset mode, acquiring a display picture of the three-dimensional live-action model at a preset angle, and generating a stereoscopic scale map by combining the display picture and a preset mark.
6. The crime scene graph generation method based on three-dimensional reconstruction as recited in claim 5, further comprising the steps of:
after the input instruction information is acquired, the stereo scale chart is displayed in a partition mode so as to display the local structure of the crime scene.
7. The crime scene graph generation method based on three-dimensional reconstruction according to claim 1, characterized by further comprising a step of virtual object construction, specifically:
in the three-dimensional live-action model, acquiring size information and grain characteristics of evidence traces;
and constructing an object three-dimensional model corresponding to the evidence trace by combining the size information, the texture characteristics and a preset algorithm.
8. A crime scene map generation system based on three-dimensional reconstruction, comprising:
the modeling module is used for carrying out three-dimensional scanning on the crime scene to obtain three-dimensional data and establishing a three-dimensional real scene model of the crime scene by combining the three-dimensional data and a preset artificial intelligence algorithm;
and the drawing module is used for acquiring a crime scene graph according to the three-dimensional real scene model, and the crime scene graph comprises a plane scale graph and/or a solid scale graph.
9. A crime scene map generation system based on three-dimensional reconstruction, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement a crime scene map generation method based on three-dimensional reconstruction as recited in any one of claims 1 to 7.
10. A storage medium having stored therein processor-executable instructions, which when executed by a processor, are configured to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010376135.3A CN111695423A (en) | 2020-05-07 | 2020-05-07 | Crime scene map generation method, system and storage medium based on three-dimensional reconstruction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010376135.3A CN111695423A (en) | 2020-05-07 | 2020-05-07 | Crime scene map generation method, system and storage medium based on three-dimensional reconstruction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111695423A true CN111695423A (en) | 2020-09-22 |
Family
ID=72476533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010376135.3A Pending CN111695423A (en) | 2020-05-07 | 2020-05-07 | Crime scene map generation method, system and storage medium based on three-dimensional reconstruction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695423A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206400641U (en) * | 2017-01-13 | 2017-08-11 | 中国人民公安大学 | Portable scene of a crime rebuilds scanner and scene of a crime three-dimensional reconstruction system |
| CN107131827A (en) * | 2017-04-28 | 2017-09-05 | 上海双微导航技术有限公司 | A kind of method of three-dimensional on-site data gathering |
| CN110738895A (en) * | 2019-09-16 | 2020-01-31 | 潘涛 | Criminal scene investigation real-scene VR comprehensive training system |
-
2020
- 2020-05-07 CN CN202010376135.3A patent/CN111695423A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206400641U (en) * | 2017-01-13 | 2017-08-11 | 中国人民公安大学 | Portable scene of a crime rebuilds scanner and scene of a crime three-dimensional reconstruction system |
| CN107131827A (en) * | 2017-04-28 | 2017-09-05 | 上海双微导航技术有限公司 | A kind of method of three-dimensional on-site data gathering |
| CN110738895A (en) * | 2019-09-16 | 2020-01-31 | 潘涛 | Criminal scene investigation real-scene VR comprehensive training system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11734468B2 (en) | System and method for generating computerized models of structures using geometry extraction and reconstruction techniques | |
| Rebolj et al. | Point cloud quality requirements for Scan-vs-BIM based automated construction progress monitoring | |
| RU2524836C2 (en) | Information processor, processing method and programme | |
| US10607163B2 (en) | LOD work package | |
| ES2780174T3 (en) | A procedure for automatic material classification and texture simulation for 3D models | |
| JP6094648B2 (en) | Information processing system, information processing apparatus, control method thereof, and program | |
| KR101181967B1 (en) | 3D street view system using identification information. | |
| KR102010030B1 (en) | Method and system for providing mixed reality service | |
| JP7391317B2 (en) | Information management device, information management system, information management method, and information management program | |
| JP6310149B2 (en) | Image generation apparatus, image generation system, and image generation method | |
| Barrile et al. | Geomatics and augmented reality experiments for the cultural heritage | |
| KR20210086837A (en) | Interior simulation method using augmented reality(AR) | |
| CN111695424A (en) | Crime scene restoration method, crime scene restoration system and storage medium based on three-dimensional real scene | |
| Inkpen et al. | Assessing stone degradation using an integrated database and geographical information system (GIS) | |
| CN111695423A (en) | Crime scene map generation method, system and storage medium based on three-dimensional reconstruction | |
| US20160349409A1 (en) | Photovoltaic shade impact prediction | |
| CN116406461B (en) | Generating measurements of physical structure and environment by automatic analysis of sensor data | |
| KR101036107B1 (en) | Emergency notification system using rfid | |
| KR102500488B1 (en) | Method for measuring Real length in 3D tour and 3D tour system therefor | |
| EP2993613A1 (en) | A capture system arranged to create a 3d model from a scanned scene, a method and a graphical user interface | |
| CN111695425A (en) | Crime scene marking method, system and storage medium based on three-dimensional real scene | |
| CN111696194A (en) | Three-dimensional visualization implementation method and system based on field investigation and storage medium | |
| WO2023047763A1 (en) | Survey assistance device, survey assistance method, program, survey assistance system, and database creation method | |
| Son | Research about semi-automation solutions that generate the BIM model from point cloud data | |
| KR20090123442A (en) | Method and apparatus for generating map data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |