Physical evidence investigation method, device and equipment and storage medium
Through the image acquisition and moving components of the automated inspection equipment, combined with the adapted light source and color filter, the automatic inspection and feature recognition of physical evidence surveys are achieved, and the missed inspection and missed inspection problems caused by traditional equipment relying on manual operations is solved, and the problem of missed inspection and missed inspection caused by traditional equipment is improved. The accuracy and efficiency of physical evidence inspection.
Patent Information
- Application Number
- CN202411130490.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-11-08
AI Technical Summary
Traditional physical evidence survey equipment relies on manual operation, resulting in missed inspection, wrong inspection, and misoperation, low efficiency, low accuracy, and lack of automation convenience.
Automatic inspection equipment, including image acquisition components and mobile components, reduces manual intervention through automatic inspection and feature recognition, and uses adaptive light sources and color filters for automated surveying.
It improves the accuracy and efficiency of physical evidence survey, reduces artificial errors, and improves the reliability and accuracy of physical evidence survey results.
Smart Images

Figure CN118914187A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of physical evidence investigation, and in particular to a physical evidence investigation method, device, equipment and storage medium. Background Art
[0002] As we all know, when conducting physical evidence investigation in the laboratory, supporting equipment such as light sources, cameras and microscopes are often used to collect physical evidence. The selection and application of light sources are crucial. Different types and characteristics of physical evidence require different spectral characteristics and color filters for illumination to highlight key information. Finally, cameras and microscopes are used to capture subtle features on the surface of the evidence.
[0003] However, during operation, traditional evidence investigation equipment often relies on manual movement of the lens or evidence samples for detailed observation and analysis, and the focus function of the equipment is mostly limited to manual adjustment, or automatic focus at close range, and fails to fully realize intelligent automatic zoom. In addition, the switching of light sources and the selection of color filters, that is, replacing the corresponding filters according to specific light source requirements, this process is still done manually. In the case of identification and discrimination work, it also mainly relies on manual judgment, lacking the convenience and limitations of automation. Summary of the invention
[0004] The embodiments of the present disclosure at least provide a method, device, equipment and storage medium for physical evidence inspection to solve the existing phenomenon of manual operation and identification of physical evidence, which may cause missed detection, wrong detection, misoperation, poor inspection efficiency and low inspection accuracy due to human factors.
[0005] The embodiment of the present disclosure provides a physical evidence investigation method, which is applied to an automated investigation device, wherein the automated investigation device includes an image acquisition component, a moving component for moving the image acquisition component, and at least one light source and at least one color filter adapted to the image acquisition component. The method includes:
[0006] In response to an inspection instruction for the object to be inspected, determining at least one inspection range point for automatically inspecting the object to be inspected;
[0007] By controlling the movement of the mobile component, an image of the object collected by the image acquisition component at each inspection range point is obtained;
[0008] Perform physical evidence feature recognition processing on each of the object images to obtain a target image containing the physical evidence features.
[0009] Through the physical evidence inspection method provided by the present application, the automated inspection equipment is provided with an image acquisition component and a moving component for moving the image acquisition component. When inspecting physical evidence, the physical evidence can be automatically inspected and feature extracted in real time, thereby making the feature extraction of the physical evidence more accurate, reducing manual operation time and the probability of human inspection errors, greatly preserving the integrity of the physical evidence, and effectively improving the inspection efficiency of the physical evidence, thereby enhancing the reliability and accuracy of the physical evidence inspection results.
[0010] In an optional implementation manner, the determining of at least one inspection range point for automatically inspecting the object to be inspected includes:
[0011] Acquire the at least one inspection range point set in advance by the user through a point setting operation; or
[0012] Identifying the at least one inspection range point for the object to be inspected according to the shape of the object to be inspected acquired by the image acquisition component; or
[0013] A target point set selected by a user from a plurality of preset inspection point sets is obtained, wherein each of the inspection point sets includes at least one inspection range point, and different inspection point sets include different numbers of inspection range points.
[0014] In an optional implementation manner, the at least one inspection range point set by the user in advance through a point setting operation is obtained through the following steps:
[0015] In response to a movement operation of a user, controlling the movement of the moving component;
[0016] In response to a user's fixed-point operation, determining a current position where the mobile component is located;
[0017] According to the current position, determine a positioning point on the object carrier corresponding to the current position;
[0018] The positioning point is determined as the inspection range point.
[0019] In an optional implementation, the step of obtaining the shape of the object to be inspected by the image acquisition component and identifying the at least one inspection range point for the object to be inspected includes:
[0020] Acquire a first preview image of the object to be inspected by the image acquisition component;
[0021] The shape of the object to be inspected is recognized according to the preview image to obtain at least one inspection range point for automatic inspection of the object to be inspected.
[0022] Here, image recognition technology is used to quickly locate key inspection points and accurately analyze the shape of objects, reducing manual intervention and judgment time, thereby improving overall inspection efficiency and the reliability and flexibility of inspection results, and ensuring the accuracy of inspection range points.
[0023] In an optional implementation, before obtaining the object image captured by the image acquisition component for each inspection range point by controlling the movement of the mobile component, the method includes:
[0024] Acquire a second preview image of the object to be inspected by the image acquisition component;
[0025] Based on the second preview image, identifying the target features of the object to be inspected, wherein the target features include the object features of the object to be inspected and / or the image features of the second preview image;
[0026] Determining a first target light source from the at least one light source and a first target color filter from the at least one color filter according to the target feature;
[0027] Switch the first target light source and the first target color filter to the image acquisition component.
[0028] In an optional implementation, before obtaining the object image captured by the image acquisition component for each inspection range point by controlling the movement of the mobile component, the method further includes:
[0029] In response to a switching operation of a user, determining a second target light source from the at least one light source, and determining a second target color filter from the at least one color filter;
[0030] Switch the second target light source and the second target color filter to the image acquisition component.
[0031] In an optional implementation, the object image collected by the image acquisition component for each inspection range point is obtained by controlling the movement of the mobile component, including:
[0032] Based on the at least one range point, controlling the moving component to move to a collection position corresponding to each inspection range point respectively;
[0033] The image acquisition component is controlled to acquire the image of the object to be inspected at the acquisition position.
[0034] In an optional implementation, after obtaining the object image captured by the image acquisition component for each inspection range point by controlling the movement of the mobile component, the method includes:
[0035] The object image is stored in a first storage location, and a picture number corresponding to the object image is generated based on the object image.
[0036] In an optional implementation, performing physical evidence feature recognition processing on each of the object images to obtain a target image containing physical evidence features includes:
[0037] Inputting each of the object images into a pre-trained physical evidence recognition model to obtain a recognition result of each of the object images output by the physical evidence recognition model, wherein the recognition result indicates that the object image contains an object feature corresponding to a physical evidence type, or that the object image does not contain an object feature corresponding to a physical evidence type;
[0038] The object image containing the object features is determined as a target image.
[0039] Here, a pre-trained physical evidence recognition model is used for training and recognition, which can accurately identify the specific physical evidence type and its corresponding object features in the object image, and give the recognition result in a short time. This greatly shortens the time required for traditional manual recognition, reduces the possibility of human misjudgment, improves work efficiency, and is more objective and accurate than manual recognition.
[0040] In an optional implementation, after performing physical evidence feature recognition processing on each of the object images to obtain a target image containing physical evidence features, the method includes:
[0041] The target image is image-encoded, and the target image is stored in a target storage location corresponding to the physical evidence feature contained in the target image.
[0042] In an optional implementation manner, the method further includes:
[0043] In response to a first viewing operation of the target image by the user, extracting the target image from a target storage location according to an image code of the target image, wherein the target image is stored in a target storage location corresponding to a physical evidence feature contained in the target image;
[0044] The target image is displayed.
[0045] In an optional implementation manner, the method further includes:
[0046] In response to a second viewing operation of the user on the target image, determining an inspection range point when acquiring the target image;
[0047] Controlling the moving component to move to a collection position corresponding to an inspection range point when collecting the target image;
[0048] A comparison image acquired at the corresponding acquisition position is displayed, wherein the comparison image is an acquisition image or a preview image acquired at the corresponding acquisition position by the image acquisition component.
[0049] Here, by returning to the inspection range point and acquisition position when the target image was acquired, the user can more intuitively understand the specific circumstances and conditions of image acquisition, and display the comparison image at the same acquisition position, which reduces the time for the user to manually search and compare images, helps to identify changes and anomalies in the image, and further promotes the in-depth progress of case detection or security inspections, thereby improving work efficiency.
[0050] The embodiment of the present disclosure also provides a physical evidence inspection device, which is applied to an automated inspection device. The automated inspection device includes an image acquisition component, a moving component for moving the image acquisition component, and at least one light source and at least one color filter adapted to the image acquisition component. The device includes:
[0051] A determination module, configured to determine at least one inspection range point for automatically inspecting the object to be inspected in response to an inspection instruction for the object to be inspected;
[0052] An acquisition module, configured to obtain the object image acquired by the image acquisition component at each inspection range point by controlling the movement of the mobile component;
[0053] The recognition module is used to perform physical evidence feature recognition processing on each of the object images to obtain a target image containing the physical evidence features.
[0054] In an optional implementation manner, the determination module is specifically used to:
[0055] Acquire the at least one inspection range point set in advance by the user through a point setting operation; or
[0056] Identify the at least one inspection range point for the object to be inspected according to the shape of the object to be inspected obtained by the image acquisition component; or
[0057] A target point set selected by a user from a plurality of preset inspection point sets is obtained, wherein each of the inspection point sets includes at least one inspection range point, and different inspection point sets include different numbers of inspection range points.
[0058] In an optional implementation manner, the determination module is used to obtain the at least one inspection range point set in advance by the user through a point setting operation through the following steps:
[0059] In response to a movement operation of a user, controlling the movement of the moving component;
[0060] In response to a user's fixed-point operation, determining a current position where the mobile component is located;
[0061] According to the current position, determine a positioning point on the object carrier corresponding to the current position;
[0062] The positioning point is determined as the inspection range point.
[0063] In an optional implementation manner, when the determination module is used to identify the at least one inspection range point for the object to be inspected according to the shape of the object to be inspected acquired by the image acquisition component, it is specifically used to:
[0064] Acquire a first preview image of the object to be inspected by the image acquisition component;
[0065] The shape of the object to be inspected is recognized according to the preview image to obtain at least one inspection range point for automatic inspection of the object to be inspected.
[0066] In an optional implementation, the device further includes a switching module, and the switching module is used to:
[0067] Acquire a second preview image of the object to be inspected by the image acquisition component;
[0068] Based on the second preview image, identifying the target features of the object to be inspected, wherein the target features include the object features of the object to be inspected and / or the image features of the second preview image;
[0069] Determining a first target light source from the at least one light source and a first target color filter from the at least one color filter according to the target feature;
[0070] Switch the first target light source and the first target color filter to the image acquisition component.
[0071] In an optional implementation manner, the switching module is further used to:
[0072] In response to a switching operation of a user, determining a second target light source from the at least one light source, and determining a second target color filter from the at least one color filter;
[0073] Switch the second target light source and the second target color filter to the image acquisition component.
[0074] In an optional implementation manner, the acquisition module is specifically used for:
[0075] Based on the at least one range point, controlling the moving component to move to a collection position corresponding to each inspection range point respectively;
[0076] The image acquisition component is controlled to acquire the image of the object to be inspected at the acquisition position.
[0077] In an optional implementation manner, the acquisition module is further used to:
[0078] The object image is stored in a first storage location, and a picture number corresponding to the object image is generated based on the object image.
[0079] In an optional implementation manner, the identification module is specifically used for:
[0080] Inputting each of the object images into a pre-trained physical evidence recognition model to obtain a recognition result of each of the object images output by the physical evidence recognition model, wherein the recognition result indicates that the object image contains an object feature corresponding to a physical evidence type, or that the object image does not contain an object feature corresponding to a physical evidence type;
[0081] The object image containing the object features is determined as a target image.
[0082] In an optional implementation, the device further includes a storage module, and the storage module is used to:
[0083] The target image is image-encoded, and the target image is stored in a target storage location corresponding to the physical evidence feature contained in the target image.
[0084] In an optional implementation, the device further includes a display module, and the display module is used to:
[0085] In response to a first viewing operation of the target image by the user, extracting the target image from a target storage location according to an image code of the target image, wherein the target image is stored in a target storage location corresponding to a physical evidence feature contained in the target image;
[0086] The target image is displayed.
[0087] In an optional manner, the device further includes a re-inspection module, and the re-inspection module is used to:
[0088] In response to a second viewing operation of the user on the target image, determining an inspection range point when acquiring the target image;
[0089] Controlling the moving component to move to a collection position corresponding to an inspection range point when collecting the target image;
[0090] A comparison image acquired at the corresponding acquisition position is displayed, wherein the comparison image is an acquisition image or a preview image acquired at the corresponding acquisition position by the image acquisition component.
[0091] The embodiment of the present disclosure also provides a computer device, including: a processor, a memory and a bus, the memory stores machine-readable instructions executable by the processor, when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps in any optional implementation of the above-mentioned physical evidence inspection method are performed.
[0092] The embodiment of the present disclosure also provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, it enables the computer to execute the steps in any optional implementation of the above-mentioned physical evidence inspection method.
[0093] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present disclosure.
[0094] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0095] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0096] Figure 1 A structural block diagram of an automated inspection device provided in an embodiment of the present disclosure;
[0097] Figure 2 A flowchart of a physical evidence inspection method provided for a disclosed embodiment;
[0098] Figure 3 A flowchart of another physical evidence inspection method provided for the disclosed embodiment;
[0099] Figure 4 This is an example diagram of a physical evidence investigation process;
[0100] Figure 5 A schematic diagram of a physical evidence inspection device provided by an embodiment of the present disclosure;
[0101] Figure 6 A second schematic diagram of a physical evidence inspection device provided in an embodiment of the present disclosure;
[0102] Figure 7A schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0103] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0104] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0105] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.
[0106] Research has found that physical evidence investigation is a crucial part of criminal investigation. It involves a detailed and systematic investigation of the crime scene to collect, extract and analyze physical evidence related to the case. In some physical evidence, some specific light sources are needed to show the characteristics of the physical evidence, such as multi-band light sources, which are suitable for the inspection of a variety of physical evidence and can stimulate the fluorescence produced by different substances. In addition, there are ultraviolet light sources, infrared light sources, laser light sources, natural light, and LED light sources. The appearance of physical evidence characteristics is also inseparable from the selection of color filters, which are also called filters. For color filters, for example, they can be classified by color, such as red, green, blue, yellow, purple, etc. Each color filter can enhance the chromaticity of its complementary color and weaken the chromaticity of the same color, thereby enhancing the contrast and visibility of objects in physical evidence photography and investigation. For physical evidence that is difficult for investigators to identify clearly with the naked eye, such as sweat marks, saliva marks, semen stains, fingerprints, exfoliated cells, fibers, etc., it is necessary to select the appropriate light source and the corresponding color filter as mentioned above to stimulate the fluorescence and reflection characteristics of the physical evidence, so as to make it appear.
[0107] During the observation process, the operator needs to rotate the objective lens converter or replace the objective lens of different magnifications to adjust the magnification and observation range according to factors such as the morphology of the evidence. In addition, it is necessary to optimize the imaging quality by fine-tuning the lens position. For large or irregular evidence, it may be necessary to change the position of the evidence under the microscope by moving the stage or adjusting the sample clamping device in order to fully observe different areas of the evidence. This not only wastes extra time, but also significantly reduces work efficiency, especially when frequent changes are required to obtain the best observation effect. This method is particularly inconvenient for scenes where a large amount of evidence needs to be processed quickly or time is tight, and the observation conditions will change significantly each time the light source or filter is switched, which may make it difficult for investigators to accurately compare the observation results under different settings, affecting the accurate judgment of the evidence.
[0108] Based on the above research, the present disclosure provides a method for investigating physical evidence. By having an image acquisition component, a moving component for moving the image acquisition component, and at least one light source and at least one color filter adapted to the image acquisition component on an automated investigation device, the physical evidence can be automatically inspected, image processed, identified, judged, and numbered and stored in real time when investigating the physical evidence, thereby reducing the problems of missed detection, wrong detection, and misoperation caused by human factors, preserving the integrity of the physical evidence, and making the feature extraction of the physical evidence more accurate. When there is a misjudgment or missed detection in the first inspection, the correctness of the initial analysis result can be verified through re-inspection, and the efficiency of investigating the physical evidence is effectively improved, and the reliability and accuracy of the physical evidence results are improved.
[0109] First, the present disclosure provides an automatic evidence inspection device, such as Figure 1 As shown, Figure 1 This is a structural block diagram of an automatic inspection device provided by an embodiment of the present disclosure. Figure 1 As shown, the automatic evidence inspection device 100 provided by the embodiment of the present disclosure includes an image acquisition component 110, a moving component 120 for moving the image acquisition component 110, and a distance measuring component 130 for measuring a distance position provided on the moving component.
[0110] Preferably, in the implementation of the present disclosure, the image acquisition component 110 mainly includes a camera, and key components such as at least one light source and at least one color filter adapted to the image acquisition component, for capturing and transmitting high-quality target image data, wherein the camera can be a full-spectrum camera, an ordinary visible light camera, an area array camera, a line array camera, an analog camera, a digital camera, or a color separation camera, etc. The light source can include a natural light source, an incandescent lamp, a fluorescent lamp, an LED lamp, a laser light source (a trace light source or a full-spectrum light source), an infrared ultraviolet light source, etc. The color filter is divided into a long-wave pass, a short-wave pass, and a narrow-band color filter, and each light source corresponds to a different color filter.
[0111] Correspondingly, the image acquisition component 110 is installed at the movable end of the mobile component 120. The mobile component 120 can use a mobile telescopic arm or a mobile mechanical arm, etc., and can move in any direction in three-dimensional space, so as to collect physical evidence in difficult-to-reach locations. In other embodiments, a drone-mounted module can also be used, which is suitable for aerial evidence collection of a large range of physical evidence and provides images from a global perspective.
[0112] The distance measuring component 130 is fixed on the mobile component 120. The distance measuring component 130 can be a laser distance measuring device, an ultrasonic distance measuring sensor, an infrared distance measuring device, a radar distance measuring sensor, or a time-of-flight sensor. Since the physical evidence is uneven, the distance measuring component 130 can be used to enable the image acquisition component 110 in the mobile component 120 to obtain a higher-definition image.
[0113] In addition, the automatic inspection equipment 100 also includes components included in general automatic inspection equipment, such as a host computer, a remote sensor and a foot pedal for controlling the moving component, a tablet computer for controlling the light source and color filter adapted for the image acquisition component, a stage, a radiator, and related components for the disinfection function, etc., which will not be described one by one here.
[0114] The automatic inspection device 100 can automatically inspect physical evidence. For example, taking a book as an example, it is necessary to identify whether the item to be inspected has various biological stains, fingerprints or shed skin (shedding cells) on a suitable light source and filter. Before that, the user needs to place the item to be inspected on the stage of the automatic inspection device 100. During the inspection process, the user selects the appropriate range point, light source and filter for the item to be inspected. The operation can be done manually or automatically. The image acquisition component 110 can conduct a comprehensive inspection and take photos of the item to be inspected by moving the mobile component 120, and perform feature recognition on the image after the photo is taken, so that the images that meet various biological stains, fingerprints or shed skin (shedding cells) are stored separately in the folder corresponding to the type of physical evidence. During the entire automatic inspection process, the physical evidence can be accurately identified and analyzed through automated inspection, which makes the inspection of physical evidence simple and convenient and improves the accuracy of evidence analysis.
[0115] The embodiment of the present disclosure also provides a method for examining physical evidence. In combination with the above-mentioned automated examination equipment, the method for examining physical evidence provided by the embodiment of the present disclosure is described below.
[0116] See also Figure 2 , Figure 2 A flowchart of a physical evidence inspection method provided by the embodiment of the present disclosure. Figure 2 As shown in the figure, the physical evidence inspection method provided by the embodiment of the present disclosure includes the following steps:
[0117] S201: In response to an inspection instruction for the object to be inspected, determine at least one inspection range point for automatically inspecting the object to be inspected.
[0118] It is understandable that when the user needs to conduct an automated inspection of the items to be inspected, the user can place the items to be inspected on the above-mentioned automatic inspection equipment 100, for example, on the loading table of the automatic inspection equipment 100. Correspondingly, in this step, the automatic inspection equipment can perform real-time detection on whether to start the inspection to detect whether an inspection instruction has been received. If the instruction is detected, then in response to the instruction, at least one inspection range point required for automatic inspection can be obtained.
[0119] Among them, the real-time detection performed by the automatic inspection equipment can be real-time monitoring after it is turned on, or it can be turned on after detecting that an object is placed on the loading platform.
[0120] It can be understood that the inspection instruction can be a received instruction for starting an inspection, which can be an instruction sent by a user to the automatic inspection device, such as an instruction sent by a user to the automatic inspection device through a terminal or an instruction generated by a user through an operation on the automatic inspection device, or an instruction generated by the automatic inspection device after autonomous detection.
[0121] Among them, the user generates instructions by operating on the automatic inspection device, which may be a mechanical component for starting the patrol inspection on the automatic inspection device, such as a button, or a virtual control for starting the patrol inspection, such as a start button displayed on a related display screen. When the user needs to use it, he can click or press the above-mentioned mechanical component or virtual control. Accordingly, when the automatic inspection device detects that the above-mentioned mechanical component or virtual control is triggered, it can be considered that the inspection instruction sent by the user is received, and the patrol inspection process can be started.
[0122] Among them, the instructions generated by the automatic inspection equipment after autonomous detection can be used by the automatic inspection equipment to inspect the loading platform. If it is detected that there are objects placed on the loading platform, it can be considered that the inspection instruction has been received.
[0123] For the inspection range points, it is necessary to understand in detail the structural layout, specific type and attributes of the items to be inspected. Based on the characteristics of the items, identify areas that may hide important clues or require special attention. You can choose interference-free and easily identifiable points to facilitate the initialization positioning of automatic inspection equipment and path planning. For example, for a significant mark or edge of the item to be inspected, and determine at least one fixed point for automatic inspection, you can choose automatic operation or manual operation.
[0124] In a possible implementation, step S201 includes:
[0125] Acquire the at least one inspection range point set in advance by the user through a point setting operation; or
[0126] Identifying the at least one inspection range point for the object to be inspected according to the shape of the object to be inspected acquired by the image acquisition component; or
[0127] A target point set selected by a user from a plurality of preset inspection point sets is obtained, wherein each of the inspection point sets includes at least one inspection range point, and different inspection point sets include different numbers of inspection range points.
[0128] Here, the selection of inspection range points can be at least one inspection range point manually set by the user through the corresponding components on the automated inspection equipment, or it can be automatically set by the automated inspection equipment through recognition of the collected preview image, or it can be a target point set including inspection range points selected by the user from the option point set preset in the automated inspection equipment.
[0129] Among them, for the preset multiple inspection point sets, each inspection point set may include at least one inspection range point, and the number of inspection range points included in different inspection point sets is different.
[0130] Furthermore, in a possible implementation, the automated inspection equipment automatically determines the inspection range points through the object to be inspected, that is, identifies the at least one inspection range point for the object to be inspected based on the shape of the object to be inspected acquired by the image acquisition component. It can be that a first preview image of the object to be inspected is first acquired by the image acquisition component, and then the shape of the object to be inspected is identified based on the preview image to obtain at least one inspection range point for automatic inspection of the object to be inspected.
[0131] It is understandable that the automated inspection equipment can utilize the first preview image of the object to be inspected captured by the image acquisition component, and can analyze its features through a built-in image processing algorithm, or output the features of the object to be inspected through a pre-trained recognition model, wherein the recognition model includes training data learned based on machine learning, and the training data includes the unique shape, size, type attributes or surface features of the object to be inspected, etc. Based on a preset target point set and the results of the recognition analysis, at least one inspection range point is automatically generated.
[0132] Accordingly, in another possible implementation, for manually determining the inspection range points, that is, the at least one inspection range point set in advance by the user through a point setting operation, the automated inspection equipment may be provided with corresponding operating components, such as mechanical remote sensing, a touch control panel, a mouse, etc. The user may control the movement of the mobile component through the above-mentioned operating components. Accordingly, during the operation of the user, for the automated inspection equipment, the movement of the mobile component may be controlled in response to the user's movement operation, and the current position of the mobile component may be determined in response to the user's fixed-point operation, and then the positioning point on the article carrier corresponding to the current position may be determined based on the current position, and the positioning point may be determined as the inspection range point.
[0133] It is understandable that, since different objects to be inspected have different shapes, sizes, and the positions of the main physical evidence points on the objects to be inspected are different, the user can make specific layouts and point selections in advance according to the shape, size, and actual needs of the objects to be inspected, which can effectively improve the accuracy of physical evidence acquisition. Therefore, the user can control the movement of the mobile component according to the needs, and apply the corresponding fixed-point operation when it moves to the position where the inspection range point needs to be set. The automated inspection equipment can perform different controls such as the movement and fixed-point of the mobile component by detecting different operations, so as to determine the inspection range point by detecting the corresponding positioning points. For example, a book has four corners, and the user can select the edge position points of the four corners or select several center position points to determine the inspection range point. The user receives the fixed-point operation response of the object to be inspected by the remote sensor or the foot pedal, and the automated inspection equipment controls the movement of the mobile component and determines the current position. According to the current position, the fixed point corresponding to the current position on the stage is determined, and the fixed point is determined as the automatic inspection range point.
[0134] In addition, whether the automated inspection equipment autonomously sets the inspection range points or the user manually selects the inspection range points, it can be within the number of optional range points specified by the automated inspection equipment, that is, the number of multiple range points that can be displayed by the terminal device in the automated inspection equipment, that is, the number of inspection range points that can be set. The user can first select the number of inspection range points according to needs, and then when the automated inspection equipment autonomously sets the inspection range points or the user manually selects the inspection range points, it needs to be consistent with this number.
[0135] S202: obtaining the object image captured by the image acquisition component at each inspection range point by controlling the movement of the mobile component.
[0136] After determining the range points of automatic inspection, the automated inspection equipment can pre-plan or calculate in real time an inspection path based on at least one determined inspection range point, and then control the mobile component to move along an inspection path by sending motion instructions to the mobile component, and control the image acquisition component to collect object images at the position corresponding to the corresponding inspection range point by sending corresponding acquisition instructions to the image acquisition component.
[0137] In a specific embodiment, for collecting object images, the mobile component can be controlled to move to the collection position corresponding to each inspection range point based on the at least one range point, and the image collection component can be controlled to collect the object image of the object to be inspected at the collection position.
[0138] It is understandable that the motion instructions include but are not limited to movement speed, direction, acceleration and necessary stop point instructions to ensure that the moving component can smoothly and accurately reach each preset inspection range point.
[0139] Among them, the mobile component can achieve precise position control through the distance measuring component. As the mobile component moves, the image acquisition component also adjusts its position and angle accordingly, controlling the image acquisition component to collect images of objects at each inspection range point at the collection position.
[0140] Furthermore, before obtaining the image of the object collected by the image acquisition component for each inspection range point, the automated inspection equipment can also switch appropriate light sources and color filters to adapt to the object to be inspected to enhance the image of the object and facilitate subsequent identification of specific features on the object image.
[0141] In a specific implementation, by switching a suitable light source and a color filter, the second preview image of the object to be inspected can be acquired through the image acquisition component.
[0142] Based on the second preview image, target features of the object to be inspected are identified, wherein the target features include object features of the object to be inspected and / or image features of the second preview image.
[0143] According to the target feature, a first target light source is determined from the at least one light source, and a first target color filter is determined from the at least one color filter.
[0144] Switch the first target light source and the first target color filter to the image acquisition component.
[0145] It is understandable that before obtaining the object image collected by the image acquisition component for each inspection range point, the image acquisition component captures a second preview image of the object to be inspected. For the second preview image, the automated inspection equipment will perform in-depth analysis on the second preview image to identify the target features and / or image features of the object to be inspected. These target features are not limited to the specific shape, color, texture, type, attribute and other object features of the object itself, as well as the image features such as brightness, contrast, color distribution in the image, such as blood stains, fingerprints, and detached cells on the object. For different types of physical evidence on the object to be inspected, the object features and / or image features will also show different target features.
[0146] Furthermore, for the identified target features, the lighting conditions and color filter conditions suitable for the current detection will be further analyzed and determined, and the first target light source will be determined from at least one light source and the first target color filter will be determined from at least one color filter, wherein the first target light source may depend on the absorption and reflection characteristics of the light source of the object to be inspected, as well as the specific level of detail to be detected. The selection of the first target color filter may be to enhance or suppress light of a specific wavelength in the image, highlight or eliminate certain unnecessary interference factors. Finally, the automated inspection equipment quickly switches the first target light source and the first target color filter to the image acquisition component.
[0147] Accordingly, in a possible implementation, for switching the light source and the color filter, a second target light source may be determined from the at least one light source, and a second target color filter may be determined from the at least one color filter in response to a switching operation of the user.
[0148] Switch the second target light source and the second target color filter to the image acquisition component.
[0149] It can be understood that when the user manually switches the operation, the automated survey equipment receives the user's operation response, selects the second target light source and the second target color filter that best suit the current user needs from the available light source set, and finally, the automated survey equipment quickly switches the second target light source and the second target color filter to the image acquisition component.
[0150] In addition, whether it is manual operation or automatic operation, it is necessary to switch the appropriate light source and color filter. Once the automatic inspection equipment starts, the image acquisition component will be instructed to capture the image of the object one by one at the preset inspection range point, and the collected object image will immediately enter the subsequent processing flow.
[0151] In a specific embodiment, after the object image is collected, the object image may be stored in a first storage location, and a picture number corresponding to the object image may be generated based on the object image.
[0152] It is understandable that after completing the object image acquisition at each inspection range point, the acquired object image data is saved to a designated first storage location, wherein the storage location here can be a hard disk drive, a solid state drive, or a storage server connected via a network.
[0153] Furthermore, based on the object image, a unique picture number will be generated for each image while storing the object image, wherein the number can be based on a timestamp, a serial number, an identifier, etc.
[0154] S203: Perform physical evidence feature recognition processing on each of the object images to obtain a target image containing physical evidence features.
[0155] In this step, each object image to be processed can be preprocessed first, and the preprocessing here can be image size adjustment, image denoising, contrast enhancement, brightness adjustment, color correction, etc., to eliminate interference factors introduced during the image acquisition process. Then, the preprocessed image can be comprehensively extracted using physical evidence feature recognition technology and other methods to obtain a target image containing physical evidence features.
[0156] In a specific embodiment, feature recognition is performed on each object image to obtain a target image containing the physical evidence feature. Each of the object images can be input into a pre-trained physical evidence recognition model to obtain a recognition result of each of the object images output by the physical evidence recognition model, and then the object image containing the object feature is determined as the target image.
[0157] The recognition result indicates that the object image contains object features corresponding to the physical evidence type, or that the object image does not contain object features corresponding to the physical evidence type.
[0158] It is understandable that the pre-processed object image is input into the physical evidence recognition model that has been pre-trained with a large number of samples. The physical evidence recognition model here can be a convolutional neural network, a recurrent neural network or other deep learning architecture, and the image is analyzed by multi-level and multi-dimensional feature extraction. During the training process, the physical evidence recognition model learns a large number of physical evidence images, so that it can accurately identify the features corresponding to the type of physical evidence in the new image.
[0159] In the feature extraction stage, the physical evidence recognition model will capture the shape, texture, color, structure and other features in the object image. These features are then fed into the classifier or regressor to be compared and matched with the physical evidence type features of the pre-trained physical evidence recognition model.
[0160] Furthermore, after feature extraction and comparison, the recognition result of each object image is output, clearly indicating whether the image contains a specific type of physical evidence and its corresponding object features. Furthermore, those images that are confirmed by the physical evidence recognition model to contain physical evidence features are marked as target images.
[0161] In this way, by having an image acquisition component, a moving component for moving the image acquisition component, and at least one light source and at least one color filter adapted to the image acquisition component on the automated inspection equipment, the physical evidence can be automatically inspected, image processed, identified, judged, and numbered and stored in real time when the physical evidence is inspected, thereby reducing the problems of missed detection, wrong detection, and misoperation caused by human factors, preserving the integrity of the physical evidence, and making the feature extraction of the physical evidence more accurate. When there is a misjudgment or missed detection in the first inspection, the correctness of the initial analysis results can be verified through re-inspection, and the inspection efficiency of the physical evidence is effectively improved, and the reliability and accuracy of the physical evidence results are improved.
[0162] See also Figure 3 , Figure 3 A flowchart of another physical evidence inspection method provided by the embodiment of the present disclosure. Figure 2 The physical evidence inspection method disclosed in the embodiment of the present disclosure is the same as that shown in the figure. The physical evidence inspection method disclosed in the embodiment of the present disclosure can also be applied to Figure 1 The automated inspection equipment shown, such as Figure 3 As shown in the figure, the physical evidence inspection method provided by the embodiment of the present disclosure includes the following steps:
[0163] S301: In response to an inspection instruction for the object to be inspected, determine at least one inspection range point for automatically inspecting the object to be inspected.
[0164] S302: obtaining the object image captured by the image acquisition component at each inspection range point by controlling the movement of the mobile component.
[0165] S303: Perform physical evidence feature recognition processing on each of the object images to obtain a target image containing physical evidence features.
[0166] Among them, the description of step S301 to step S303 can refer to the description of step S201 to step S203, and can solve the same technical problems and achieve the same technical effects, which will not be repeated here.
[0167] S304: Perform image encoding on the target image, and store the target image in a target storage location corresponding to the physical evidence feature contained in the target image.
[0168] In this step, the target image is firstly subjected to efficient image encoding processing. The encoding here can be numbering the image or converting the target image into a digital format. The encoding methods include JPEG, PNG, etc.
[0169] The encoding parameters are automatically adjusted according to the image content to achieve the best balance between visual fidelity and file size. In order to ensure the orderly storage and efficient retrieval of target images, they are classified and stored according to the type of physical evidence features contained in the target images. For example, images containing fingerprint features are stored in the "Fingerprint" folder, images containing bloodstain features are stored in the "Bloodstain" folder, and so on, which can lay the foundation for subsequent re-examination.
[0170] In one possible implementation, the method further includes:
[0171] In response to a first viewing operation of the target image by a user, the target image is extracted from a target storage location according to an image code of the target image, wherein the target image is stored in a target storage location corresponding to a physical evidence feature contained in the target image.
[0172] The target image is displayed.
[0173] It is understandable that when the user's first viewing operation is captured, which can be achieved by clicking a button on the user interface, touching the button, or inputting a keyboard, the automated inspection equipment recognizes this operation and immediately starts the image retrieval and display process. Before extracting the target image, the image code associated with the image needs to be identified based on the image code input by the user. After determining the target image code, since the target image is classified according to the physical evidence features it contains and stored in the corresponding target storage location, the target storage location is quickly located based on the relevant information in the image code (such as folder path, database table name, etc.), and the target image at that location is extracted. If the image data is encrypted, it needs to be decrypted during the extraction process, and finally the extracted target image is presented to the user, who can then perform a review operation on the target image.
[0174] In a possible implementation, the method further includes:
[0175] In response to a second viewing operation of the user on the target image, an inspection range point when acquiring the target image is determined.
[0176] The moving component is controlled to move to a collection position corresponding to a patrol range point when collecting the target image.
[0177] A comparison image acquired at the corresponding acquisition position is displayed, wherein the comparison image is an acquisition image or a preview image acquired at the corresponding acquisition position by the image acquisition component.
[0178] It is understandable that capturing the user's second viewing operation can be triggered by a button click, touch operation, or keyboard input on the user interface. The user inputs the code of the target image to determine the inspection range point of the target image. Next, according to the determined inspection range point, the mobile component is controlled to move to the acquisition position corresponding to the inspection range point. The distance measurement component can be used to achieve precise position control. As the mobile component moves, the image acquisition component also adjusts its position and angle to accurately reach the acquisition position.
[0179] Furthermore, after the mobile component reaches the acquisition position, a comparison image begins to be displayed at that position, wherein the comparison image may be an image actually acquired by the image acquisition component at the acquisition position, and the preview image may be an image acquired in real time at the same position or an image generated by pre-capturing.
[0180] Next, the above-mentioned physical evidence inspection scheme is explained with a specific example. Figure 4 , Figure 4 This is an example diagram of the physical evidence inspection process. Figure 4 As shown, this example takes the fingerprint inspection on the book as an example, and the automated inspection equipment includes a computer host, a mechanical arm for moving the light source system and the spectrum camera, a remote sensor and a foot pedal for controlling the movement of the mechanical arm, and a tablet computer for controlling the switching of the light source and the color filter. Start the host 401, the automated inspection equipment starts working, open the motion software of the mechanical arm and click the inspection mode 402, here select the inspection mode for initial inspection 403, which can be manually selected by the remote sensor and foot pedal for controlling the movement of the machine or automatically selected. The scanning area 414 is established to determine the range point of the automatic inspection, and after determination, the light source is selected 404. According to the size and shape of the book, the trace light source system 405 or the full spectrum source system 406 can be automatically or manually selected, and the required light source and color filter are turned on to present the characteristics of the physical evidence, and the full spectrum camera 407 is used to take pictures.
[0181] When the automatic inspection begins, the full-spectrum camera 407 installed on the robotic arm starts to move. According to the range points determined for the automatic inspection, the full-spectrum camera automatically focuses 408 every time the robotic arm moves a range point unit. After focusing successfully, the robotic arm stops moving and sends a photo command to enable the photo software 411 running on the computer host to take a photo and save it in a folder. The photographed image is identified according to the physical evidence recognition model on the host computer. When the fingerprint feature is identified, the photo 412 containing the fingerprint feature point is classified and stored in the folder corresponding to the fingerprint (and the number and size of the feature can be set). The user opens the picture of the feature point, enters the number of the photo containing the feature point, and conducts a re-inspection 409. The robotic arm moves to the corresponding feature point position 410 and extracts the corresponding physical evidence 413.
[0182] The physical evidence inspection method provided by the embodiment of the present disclosure determines at least one inspection range point for automatically inspecting the object to be inspected in response to the inspection instruction for the object to be inspected; obtains the object image collected by the image acquisition component for each of the inspection range points by controlling the movement of the mobile component; and performs physical evidence feature recognition processing on each of the object images to obtain a target image containing the physical evidence features.
[0183] In this way, by having an image acquisition component, a moving component for moving the image acquisition component, and at least one light source and at least one color filter adapted to the image acquisition component on the automated inspection equipment, the physical evidence can be automatically inspected, image processed, identified, judged, and numbered and stored in real time when the physical evidence is inspected, thereby reducing the problems of missed detection, wrong detection, and misoperation caused by human factors, preserving the integrity of the physical evidence, and making the feature extraction of the physical evidence more accurate. When there is a misjudgment or missed detection in the first inspection, the correctness of the initial analysis results can be verified through re-inspection, and the inspection efficiency of the physical evidence is effectively improved, and the reliability and accuracy of the physical evidence results are improved.
[0184] See also Figure 5 and Figure 6 , Figure 5 This is one of the schematic diagrams of a physical evidence inspection device provided in an embodiment of the present disclosure, Figure 6 The second schematic diagram of a physical evidence inspection device provided in the embodiment of the present disclosure. The physical evidence inspection device 500 disclosed in the embodiment of the present disclosure can also be applied to Figure 1 As shown in the automated inspection equipment, it can be understood that the physical evidence inspection device 500 can be embedded in the automated inspection equipment as a part of the inspection equipment, or it can be a device independent of the inspection equipment, communicating with the inspection equipment to assist the inspection equipment in completing physical evidence inspection. Figure 5 As shown in , the physical evidence inspection device 500 provided by the embodiment of the present disclosure includes:
[0185] A determination module 510 is used to determine at least one inspection range point for automatic inspection of the object to be inspected in response to an inspection instruction for the object to be inspected;
[0186] An acquisition module 520, configured to obtain the object image collected by the image acquisition component at each inspection range point by controlling the movement of the mobile component;
[0187] The recognition module 530 performs physical evidence feature recognition processing on each of the object images to obtain a target image containing the physical evidence features.
[0188] In an optional implementation manner, the determination module 510 is specifically configured to:
[0189] Acquire the at least one inspection range point set in advance by the user through a point setting operation; or
[0190] Identify the at least one inspection range point for the object to be inspected according to the shape of the object to be inspected obtained by the image acquisition component; or
[0191] A target point set selected by a user from a plurality of preset inspection point sets is obtained, wherein each of the inspection point sets includes at least one inspection range point, and different inspection point sets include different numbers of inspection range points.
[0192] In an optional implementation manner, the determination module 510 is used to obtain the at least one inspection range point set in advance by the user through a point setting operation through the following steps:
[0193] In response to a movement operation of a user, controlling the movement of the moving component;
[0194] In response to a user's fixed-point operation, determining a current position where the mobile component is located;
[0195] According to the current position, determine a positioning point on the object carrier corresponding to the current position;
[0196] The positioning point is determined as the inspection range point.
[0197] In an optional implementation, when the determination module 510 is used to identify the at least one inspection range point for the object to be inspected according to the shape of the object to be inspected acquired by the image acquisition component, it is specifically used to:
[0198] Acquire a first preview image of the object to be inspected by the image acquisition component;
[0199] The shape of the object to be inspected is recognized according to the preview image to obtain at least one inspection range point for automatic inspection of the object to be inspected.
[0200] In an optional implementation, the physical evidence investigation device 500 further includes a switching module 540, and the switching module 540 is used to:
[0201] Acquire a second preview image of the object to be inspected by the image acquisition component;
[0202] Based on the second preview image, identifying the target features of the object to be inspected, wherein the target features include the object features of the object to be inspected and / or the image features of the second preview image;
[0203] Determining a first target light source from the at least one light source and a first target color filter from the at least one color filter according to the target feature;
[0204] Switch the first target light source and the first target color filter to the image acquisition component.
[0205] In an optional implementation manner, the switching module 540 is further configured to:
[0206] In response to a switching operation of a user, determining a second target light source from the at least one light source, and determining a second target color filter from the at least one color filter;
[0207] Switch the second target light source and the second target color filter to the image acquisition component.
[0208] In an optional implementation manner, the acquisition module 520 is specifically used to:
[0209] Based on the at least one range point, controlling the moving component to move to a collection position corresponding to each inspection range point respectively;
[0210] The image acquisition component is controlled to acquire the image of the object to be inspected at the acquisition position.
[0211] In an optional implementation manner, the acquisition module 520 is further configured to:
[0212] The object image is stored in a first storage location, and a picture number corresponding to the object image is generated based on the object image.
[0213] In an optional implementation manner, the identification module 530 is specifically configured to:
[0214] Inputting each of the object images into a pre-trained physical evidence recognition model to obtain a recognition result of each of the object images output by the physical evidence recognition model, wherein the recognition result indicates that the object image contains an object feature corresponding to a physical evidence type, or that the object image does not contain an object feature corresponding to a physical evidence type;
[0215] The object image containing the object features is determined as a target image.
[0216] In an optional implementation, the physical evidence investigation device 500 further includes a storage module 550, and the storage module 550 is used to:
[0217] The target image is image-encoded, and the target image is stored in a target storage location corresponding to the physical evidence feature contained in the target image.
[0218] In an optional implementation, the physical evidence investigation device 500 further includes a display module 560, and the display module 560 is used to:
[0219] In response to a first viewing operation of the target image by the user, extracting the target image from a target storage location according to an image code of the target image, wherein the target image is stored in a target storage location corresponding to a physical evidence feature contained in the target image;
[0220] The target image is displayed.
[0221] In an optional manner, the physical evidence investigation device 500 further includes a re-examination module 570, and the re-examination module 570 is used to:
[0222] In response to a second viewing operation of the user on the target image, determining an inspection range point when acquiring the target image;
[0223] Controlling the moving component to move to a collection position corresponding to an inspection range point when collecting the target image;
[0224] A comparison image acquired at the corresponding acquisition position is displayed, wherein the comparison image is an acquisition image or a preview image acquired at the corresponding acquisition position by the image acquisition component.
[0225] The physical evidence inspection device provided by the embodiment of the present disclosure can automatically inspect physical evidence in real time, solve the existing phenomenon of manual operation and identification of physical evidence, and solve the problems of missed detection, wrong detection, and misoperation caused by human factors, effectively improve the inspection efficiency of physical evidence, and enhance the reliability and accuracy of physical evidence inspection results.
[0226] See also Figure 7 , Figure 7A schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure. Figure 2 and Figure 3 The physical evidence inspection method shown in the embodiment of the present disclosure also provides a computer device 700, including: a processor 710, a memory 720 and a bus 730, the memory 720 stores machine-readable instructions executable by the processor 710, when the computer device 700 is running, the processor 710 and the memory 720 communicate through the bus 730, and the machine-readable instructions are executed by the processor 710 as follows Figure 2 and Figure 3 The steps of the physical evidence investigation method shown in .
[0227] Among them, the memory 720 can be, but is not limited to, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
[0228] The processor 710 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0229] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the computer device 700. In other embodiments of the present application, the computer device 700 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.
[0230] The present disclosure also provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor when it is run. Figure 2 and Figure 3 The steps for testing the physical evidence investigation method are shown in .
[0231] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for physical evidence inspection, characterized in that: Applied to an automated inspection device, the automated inspection device comprises an image acquisition component, a moving component for moving the image acquisition component, and at least one light source and at least one color filter adapted to the image acquisition component, the method comprising: In response to an inspection instruction for an object to be inspected, determining at least one inspection range point for automatically inspecting the object to be inspected; By controlling the movement of the mobile component, the image of the object collected by the image acquisition component at each inspection range point is obtained; Perform physical evidence feature recognition processing on each of the object images to obtain a target image containing the physical evidence features.
2. The method according to claim 1, characterized in that The step of determining at least one inspection range point for automatically inspecting the object to be inspected includes: Acquire the at least one inspection range point set in advance by the user through a point setting operation; or Identifying the at least one inspection range point for the object to be inspected according to the shape of the object to be inspected acquired by the image acquisition component; or A target point set selected by a user from a plurality of preset inspection point sets is obtained, wherein each of the inspection point sets includes at least one inspection range point, and different inspection point sets include different numbers of inspection range points.
3. The method according to claim 2, characterized in that The at least one inspection range point set by the user in advance through the point setting operation is obtained by the following steps: In response to a movement operation of a user, controlling the movement of the moving component; In response to a user's fixed-point operation, determining a current position where the mobile component is located; According to the current position, determine a positioning point on the object carrier corresponding to the current position; The positioning point is determined as the inspection range point.
4. The method according to claim 2, characterized in that: The step of identifying at least one inspection range point for the object to be inspected according to the shape of the object to be inspected acquired by the image acquisition component comprises: Acquire a first preview image of the object to be inspected by the image acquisition component; The shape of the object to be inspected is recognized according to the preview image to obtain at least one inspection range point for automatic inspection of the object to be inspected.
5. The method according to claim 1, characterized in that Before obtaining the object image collected by the image collection component for each inspection range point by controlling the movement of the mobile component, the method includes: Acquire a second preview image of the object to be inspected by the image acquisition component; Based on the second preview image, identifying the target features of the object to be inspected, wherein the target features include the object features of the object to be inspected and / or the image features of the second preview image; Determining a first target light source from the at least one light source and a first target color filter from the at least one color filter according to the target feature; Switch the first target light source and the first target color filter to the image acquisition component.
6. The method according to claim 1, characterized in that Before obtaining the object image collected by the image collection component for each inspection range point by controlling the movement of the mobile component, the method further includes: In response to a switching operation of a user, determining a second target light source from the at least one light source, and determining a second target color filter from the at least one color filter; Switch the second target light source and the second target color filter to the image acquisition component.
7. The method according to claim 1, characterized in that By controlling the movement of the mobile component, the object image collected by the image acquisition component for each inspection range point is obtained, including: Based on the at least one range point, controlling the moving component to move to a collection position corresponding to each inspection range point respectively; The image acquisition component is controlled to acquire the image of the object to be inspected at the acquisition position.
8. The method according to claim 1, characterized in that After obtaining the object image collected by the image acquisition component for each inspection range point by controlling the movement of the mobile component, the method includes: The object image is stored in a first storage location, and a picture number corresponding to the object image is generated based on the object image.
9. The method according to claim 1, characterized in that: The step of performing physical evidence feature recognition processing on each of the object images to obtain a target image containing physical evidence features includes: Inputting each of the object images into a pre-trained physical evidence recognition model to obtain a recognition result of each of the object images output by the physical evidence recognition model, wherein the recognition result indicates that the object image contains an object feature corresponding to a physical evidence type, or that the object image does not contain an object feature corresponding to a physical evidence type; The object image containing the object features is determined as a target image.
10. The method according to any one of claims 1 to 9, characterized in that: After performing physical evidence feature recognition processing on each of the object images to obtain a target image containing physical evidence features, the method includes: The target image is image-encoded, and the target image is stored in a target storage location corresponding to the physical evidence feature contained in the target image.
11. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: In response to a first viewing operation of the target image by the user, extracting the target image from a target storage location according to an image code of the target image, wherein the target image is stored in a target storage location corresponding to a physical evidence feature contained in the target image; The target image is displayed.
12. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: In response to a second viewing operation of the user on the target image, determining an inspection range point when acquiring the target image; Controlling the moving component to move to a collection position corresponding to an inspection range point when collecting the target image; A comparison image acquired at the corresponding acquisition position is displayed, wherein the comparison image is an acquisition image or a preview image acquired at the corresponding acquisition position by the image acquisition component.
13. A physical evidence inspection device, characterized in that: Applied to an automated inspection device, the automated inspection device comprises an image acquisition component, a moving component for moving the image acquisition component, and at least one light source and at least one color filter adapted to the image acquisition component, the device comprises: A determination module, configured to determine at least one inspection range point for automatically inspecting the object to be inspected in response to an inspection instruction for the object to be inspected; An acquisition module, configured to obtain the object image acquired by the image acquisition component at each inspection range point by controlling the movement of the mobile component; The recognition module is used to perform physical evidence feature recognition processing on each of the object images to obtain a target image containing the physical evidence features.
14. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the physical evidence inspection method as described in any one of claims 1 to 12 are performed.
15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the physical evidence inspection method as described in any one of claims 1 to 12.
Citation Information
Cited By
Multifunctional on-site material evidence investigation and evidence obtaining system based on intelligent robot dog
CN121032991A
A multifunctional on-site evidence investigation and evidence collection system based on an intelligent robot dog
CN121032991B
