A mouse species identification device, method and system

Abstract

The present invention discloses a device, method, and system for identifying mouse species, relating to the field of mouse identification. The device comprises: a housing, a point cloud acquisition unit, a distance measuring unit, and a processing unit; a food placement area is provided at the bottom of the housing; the point cloud acquisition unit is provided at one end of the top of the housing, and the horizontal distance between the point cloud acquisition unit and one end of the food placement area is greater than the length of the mouse to be identified; the point cloud acquisition unit is used to collect epidermal point cloud data of the mouse to be identified; the distance measuring unit is provided at the other end of the food placement area; the distance measuring unit is used to measure the displacement of the mouse to be identified; and the processing unit is used to determine the three-dimensional point cloud outline of the mouse to be identified based on the epidermal point cloud data and displacement, determine the proportions of the head, body, and tail of the mouse to be identified based on the three-dimensional point cloud outline, and determine the species of the mouse to be identified based on the proportions. The present invention improves the accuracy of mouse species identification.

Description

Technical Field

[0001] The present invention relates to the field of rodent identification, and in particular to a device, method and system for identifying rodent species. Background Art

[0002] Currently, the only way to identify the population and species of live wild rodents is through live trapping and measurement studies, or through long-term manual video monitoring and observation of rodent characteristics. However, automated measurement of captured rodents using intelligent visual methods is unreliable and inaccurate, making scientific identification of rodent species impossible. Summary of the Invention

[0003] The purpose of the present invention is to provide a device, method and system for identifying rat species, so as to improve the accuracy of rat species identification.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] A mouse species identification device includes: a box, a point cloud acquisition unit, a distance measurement unit, and a processing unit;

[0006] The bottom of the box is provided with a food placement area;

[0007] The point cloud acquisition unit is disposed at one end of the top of the box, and the horizontal distance between the point cloud acquisition unit and one end of the food placement area is greater than the length of the mouse to be identified; the point cloud acquisition unit is used to collect the epidermal point cloud data of the mouse to be identified;

[0008] The distance measuring unit is arranged at the other end of the food placement area; the distance measuring unit is used to measure the displacement of the mouse to be identified;

[0009] The processing unit is connected to the point cloud acquisition unit and the ranging unit respectively; the processing unit is used to determine the three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement, determine the proportions of the head, body and tail of the mouse to be identified based on the three-dimensional point cloud contour, and determine the type of the mouse to be identified based on the proportions.

[0010] Optionally, a door is provided on one side of the box where the distance measuring unit is placed; and the door is movably connected to the top of the box.

[0011] Optionally, an opening is provided on one side of the box where the point cloud acquisition unit is placed; the mouse to be identified enters the box through the opening.

[0012] Optionally, a battery is further included; the battery is connected to the point cloud acquisition unit, the distance measuring unit and the processing unit respectively.

[0013] Optionally, the point cloud acquisition unit is a solid-state laser radar.

[0014] Optionally, the distance measuring unit is a laser rangefinder.

[0015] Optionally, the point cloud acquisition unit and the ranging unit both emit invisible lasers.

[0016] A method for identifying rat species, which is applied to the above-mentioned rat species identification device, and includes:

[0017] Acquire laser coordinate data of the mouse to be identified; the laser coordinate data includes epidermal point cloud data and displacement;

[0018] determining a three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement;

[0019] determining the proportions of the head, body, and tail of the mouse to be identified based on the three-dimensional point cloud outline;

[0020] The type of the mouse to be identified is determined according to the ratio.

[0021] Optionally, determining the three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement specifically includes:

[0022] Deleting abnormal data from the epidermal point cloud data to obtain normal epidermal point cloud data; the abnormal data includes epidermal point cloud data of the mouse to be identified turning around in the channel of the mouse type identification device;

[0023] Configuring corresponding time for the epidermal point cloud data and the displacement to obtain normal epidermal point cloud data with time information and displacement with time information;

[0024] Filtering out the normal epidermal point cloud data with time information and the data with time information whose time interval is greater than a preset interval, to obtain filtered epidermal point cloud data and filtered displacements;

[0025] According to the selected epidermal point cloud data and the filtered displacement, a three-dimensional point cloud outline of the mouse to be identified is generated using three-dimensional point cloud synthesis algorithm software.

[0026] A mouse species identification system, comprising:

[0027] A data acquisition module, used to acquire laser coordinate data of the mouse to be identified; the laser coordinate data includes epidermal point cloud data and displacement;

[0028] a three-dimensional contour determination module, configured to determine a three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement;

[0029] a proportion calculation module, for determining the proportions of the head, body and tail of the mouse to be identified based on the three-dimensional point cloud contour;

[0030] The identification module is used to determine the type of the mouse to be identified according to the ratio.

[0031] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0032] The present invention uses a point cloud acquisition unit and a distance measurement unit in the rat species identification device to collect laser coordinate data of the rat to be identified. A processing unit processes this laser coordinate data to determine the proportions of the rat's head, body, and tail, and thus the rat's species, thereby improving the accuracy of rat identification. Furthermore, the rat species identification device automatically monitors rats, eliminating the need for rat capture and reducing the workload of personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 A cross-sectional view of the mouse species identification device provided by the present invention;

[0035] Figure 2 This is an overall schematic diagram of the mouse species identification device provided by the present invention;

[0036] Figure 3 A top view of the mouse species identification device provided by the present invention;

[0037] Figure 4 A left side view of the mouse species identification device provided by the present invention;

[0038] Figure 5 A front view of the mouse species identification device provided by the present invention;

[0039] Figure 6 A right side view of the mouse species identification device provided by the present invention;

[0040] Figure 7 A bottom view of the mouse species identification device provided by the present invention;

[0041] Figure 8A flow chart of the mouse species identification method provided by the present invention;

[0042] Figure 9 This is a schematic diagram of the three-dimensional point cloud outline of the mouse to be identified provided by the present invention.

[0043] Explanation of symbols:

[0044] 1. Point cloud acquisition unit; 2. Distance measurement unit; 3. Food placement area; 4. Mice to be identified; 5. Door; 6. Box; 7. One-way narrow passage; 8. Battery placement area. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] The purpose of the present invention is to provide a device, method and system for identifying rat species, so as to improve the accuracy of rat species identification.

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] Example 1

[0049] like Figure 1-Figure 7 As shown, the mouse species identification device provided by the present invention includes: a box 6, a point cloud acquisition unit 1, a distance measurement unit 2 and a processing unit (not shown in FIG. Figure 1 shown in ).

[0050] A food placement area 3 is provided at the bottom of the box body 6 .

[0051] The point cloud acquisition unit 1 is disposed at one end of the top of the housing 6, and the horizontal distance between the point cloud acquisition unit 1 and one end of the food placement area 3 is greater than the length of the mouse 4 to be identified. The point cloud acquisition unit 1 is used to collect skin point cloud data of the mouse 4 to be identified. The point cloud acquisition unit 1 is a solid-state laser radar.

[0052] The distance measuring unit 2 is disposed at the other end of the food placement area 3 and is used to measure the displacement of the mouse to be identified 4. The distance measuring unit 2 is a laser rangefinder.

[0053] The processing unit is connected to the point cloud acquisition unit 1 and the ranging unit 2 respectively; the processing unit is used to determine the three-dimensional point cloud contour of the mouse 4 to be identified based on the epidermal point cloud data and the displacement, determine the proportions of the head, body and tail of the mouse 4 to be identified based on the three-dimensional point cloud contour, and determine the type of the mouse 4 to be identified based on the proportions.

[0054] In actual application, a one-way narrow passage 7 is provided in the box 6, and the box 6 is set to a semi-enclosed one-way structure, which can be a cube; the length of the box 6 is to ensure that the mouse can enter at least one body length plus the size of accommodating a laser rangefinder and a bait trap (food placement area 3), the height is not less than 10CM, and the width is only wide enough for one mouse to pass through. Generally, the mouse cannot turn around after entering the passage and finally exits from the side door. When the mouse moves forward quickly, it can ensure that the head, body, tail and whiskers maintain an axis of movement perpendicular to each other.

[0055] A bait trap is set in the one-way narrow channel 7. The size of the trap is not limited. Generally, the trap can be placed by putting bait to attract mice to quickly pass through the one-way narrow channel 7.

[0056] The solid-state laser radar is located above the box 6 and is used to collect cross-sectional data of the mouse body (skin point cloud data). It emits invisible laser light. The solid-state laser radar should be installed at a distance greater than one mouse body length from the bait trap.

[0057] The laser rangefinder is located in the narrow one-way passage 7, directly in front of the opening of the box 6, at least 25 cm from the opening, and directly behind the bait trap. This ensures that after the mouse consumes the bait, its entire body passes through the solid-state laser radar's scanning area. The laser rangefinder, which emits invisible laser light, collects the mouse's movement distance data (displacement).

[0058] A door 5 is provided on the side of the box where the distance measuring unit is placed. This door 5 is movably connected to the top of the box 6 to prevent mice from entering from this end, ensuring that mice can only pass through the one-way narrow passage 7. An opening is provided on the side of the box 6 where the point cloud acquisition unit 1 is placed. The mouse 4 to be identified enters the box 6 through this opening.

[0059] In actual application, the mouse species identification device also includes a battery, which is placed in the battery placement area 8; the battery is respectively connected to the point cloud acquisition unit 1, the ranging unit 2 and the processing unit, and the battery is used to provide power for the solid-state laser radar, laser rangefinder and processing unit.

[0060] Example 2

[0061] The present invention also provides a method for identifying rat species, which is applied to the rat species identification device of embodiment 1. The rat species identification method is as follows: Figure 8 As shown, including:

[0062] Step 201: Obtain laser coordinate data of the mouse to be identified; the laser coordinate data includes skin point cloud data and displacement.

[0063] In practical applications, the solid-state LiDAR acquisition frequency is set to 35Hz. Based on a 5-second radar scan, the point cloud section interval is 0.1cm, or 1mm per section, which meets the required recognition accuracy. Adult mice are generally 20-25cm long. Both the solid-state LiDAR and laser rangefinder use invisible lasers, which will not alert mice.

[0064] Next, laser coordinate data is acquired. The mouse's own movement is used to obtain the cross-sectional and longitudinal point cloud coordinates of the orthographic 3D point cloud. The solid-state laser radar measures the mouse's epidermal cross-sectional point cloud data (X, Y), while the longitudinal laser rangefinder measures the mouse's positional data (i.e., displacement Z).

[0065] Differentiating individual mice: This involves distinguishing when the measurement of a mouse has been completed. Based on the mouse's physical characteristics, after entering the channel, the mouse will first reach the minimum distance position of the solid-state laser radar. At this point, the mouse species identification device begins recording. After the mouse's tail completely leaves the solid-state laser radar scanning area, and the X and Y values ​​of the solid-state laser radar measurement data are all the channel ground values ​​(the default is 0, 0), the system (mouse species identification device) defaults to the completion of the measurement of the mouse.

[0066] Step 202: Determine the three-dimensional point cloud contour of the mouse to be identified based on the skin point cloud data and the displacement.

[0067] As an optional implementation, step 302 specifically includes:

[0068] Abnormal data in the epidermal point cloud data is deleted to obtain normal epidermal point cloud data; the abnormal data includes epidermal point cloud data of the mouse to be identified turning around within the channel of the mouse species identification device. In practical applications, chaotic data is first filtered: abnormal mouse movements or individual mouse abnormalities should be filtered in the current measurement data. For example, if a mouse reverses and squeezes out of the channel midway, it will affect the system's identification judgment. If such data does not conform to the normal measurement value pattern (solid-state laser radar values ​​should follow the normal pattern of small-medium-large-fine), such data sets are directly deleted and not used.

[0069] The epidermal point cloud data and displacement are assigned corresponding times to obtain normal epidermal point cloud data with time information and displacement with time information. In practical applications, the data monitored over a period of time is assigned times. The two-dimensional point cloud data obtained by the solid-state lidar (normal epidermal point cloud data with time information) is TIME, X, Y, and the data obtained by the laser rangefinder (displacement with time information) is (TIME, Z). The measured Z value here represents the distance the mouse has moved. It can also be assumed that the mouse is stationary, indicating that the solid-state lidar has moved the same distance to scan each point on the mouse. In this way, three-dimensional spatial data of all points on the mouse's body, excluding the bottom surface of the abdomen, can be obtained.

[0070] The normal epidermal point cloud data with time information and the displacement data with time information with time information whose time interval is greater than a preset interval are filtered out to obtain the filtered epidermal point cloud data and the filtered displacement data. In actual applications, the X, Y and Z data of the solid-state lidar and the laser rangefinder are matched using the unified clock of TIME. The data with larger time intervals are filtered out, and only the data with the closest time intervals are matched as a group to obtain the accurate spatial three-dimensional data of the point position. The batch processing of data collation is completed to generate a matched spatial three-dimensional data point set (the filtered epidermal point cloud data and the filtered displacement data).

[0071] According to the selected epidermal point cloud data and the filtered displacement, a three-dimensional point cloud outline of the mouse to be identified is generated using three-dimensional point cloud synthesis algorithm software.

[0072] In practical applications, the mouse's 3D point cloud outline is generated based on the matched spatial 3D data point set. Specifically, the matched spatial 3D data point set is input into a 3D point cloud synthesis algorithm software, such as CloudCompare, 3DReshaper, etc., to generate the mouse's 3D point cloud outline. Figure 9 shown.

[0073] Step 203: Determine the proportions of the head, body, and tail of the mouse to be identified based on the three-dimensional point cloud contour.

[0074] In practice, the proportions of various parts of the mouse body are calculated based on the mouse's 3D point cloud outline. Specifically, the mouse's head, body, and tail have distinct boundaries. Although physiological movements, such as head shaking, can create some confusion in the point cloud, this does not affect the measurement of the head, body, and tail dimensions and the calculation of their proportions.

[0075] Calculation method: Each point cloud data packet can be composed of two data structures: horizontal planar surface and vertical longitudinal section. The mouse's head (the data part at the front of the Z axis to the part where the data diameter begins to decrease), body (the data set part with the largest diameter), and tail (the data set part with a diameter not exceeding 1CM) can be identified through regularity.

[0076] Then only calculate the data ratio of each part of the Z axis.

[0077] Step 204: Determine the type of the mouse to be identified according to the ratio.

[0078] According to the data ratio of each part of the Z axis, the mouse species is confirmed according to the preset threshold.

[0079] In actual applications, mouse species include house mice, house mice, prairie voles, yellow-breasted rats, brown rats, shrews, squirrels, chipmunks, etc. The head-to-body-tail proportions of different mouse species are different, and the approximate type of mouse can be calculated through automatic calculation and comparison.

[0080] Once the rat population reaches the population assessment threshold, a direct comparison assessment is conducted. In areas where the same species of rat is prevalent, the body size data of the monitored rats can provide a rough estimate of the age composition of the rat population.

[0081] Example 3

[0082] In order to execute the method corresponding to the above-mentioned embodiment 2 and achieve the corresponding functions and technical effects, a mouse species identification system is provided below, including:

[0083] The data acquisition module is used to acquire the laser coordinate data of the mouse to be identified; the laser coordinate data includes epidermal point cloud data and displacement.

[0084] The three-dimensional contour determination module is used to determine the three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement.

[0085] A proportion calculation module is used to determine the proportions of the head, body and tail of the mouse to be identified based on the three-dimensional point cloud contour.

[0086] The identification module is used to determine the type of the mouse to be identified according to the ratio.

[0087] The mouse species identification device, method, and system of the present invention have the following advantages:

[0088] The present invention utilizes the movement of mice to obtain the cross-sectional point cloud coordinates and longitudinal point cloud coordinates of the orthographic three-dimensional point cloud of the body, and automatically monitors without manually capturing live mice. The three-dimensional data collected is relatively accurate. The proportions of various parts of the mouse's body can be automatically calculated based on the three-dimensional point cloud data, and the type or age of the mouse can be compared and identified. In addition, the monitoring can be repeated for a long time without capturing or killing the target mouse, which will not cause pollution.

[0089] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0090] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A device for identifying mouse species, characterized in that: include: Box, point cloud acquisition unit, ranging unit and processing unit; The bottom of the box is provided with a food placement area; The point cloud acquisition unit is disposed at one end of the top of the box, and the horizontal distance between the point cloud acquisition unit and one end of the food placement area is greater than the length of the mouse to be identified; the point cloud acquisition unit is used to collect the epidermal point cloud data of the mouse to be identified; The distance measuring unit is arranged at the other end of the food placement area; the distance measuring unit is used to measure the displacement of the mouse to be identified; The processing unit is connected to the point cloud acquisition unit and the distance measurement unit respectively; the processing unit is used to determine the three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement, determine the proportions of the head, body and tail of the mouse to be identified based on the three-dimensional point cloud contour, and determine the type of the mouse to be identified based on the proportions; Determining the three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement, specifically comprising: Deleting abnormal data from the epidermal point cloud data to obtain normal epidermal point cloud data; the abnormal data includes epidermal point cloud data of the mouse to be identified turning around in the channel of the mouse type identification device; Configuring corresponding time for the epidermal point cloud data and the displacement to obtain normal epidermal point cloud data with time information and displacement with time information; Filtering out the normal epidermal point cloud data with time information and the data with time information whose time interval is greater than a preset interval, to obtain filtered epidermal point cloud data and filtered displacements; Generating a three-dimensional point cloud outline of the mouse to be identified using three-dimensional point cloud synthesis algorithm software based on the selected epidermal point cloud data and the filtered displacement; Determining the proportions of the head, body, and tail of the mouse to be identified based on the three-dimensional point cloud contour specifically includes: Each point cloud data packet uses two data structures, horizontal profile and vertical profile, to identify the mouse's head, body, and tail through regularity; the head is the data part from the front row of the Z axis to the part where the data diameter begins to decrease; the body is the data set part with the largest diameter; the tail is the data set part with a diameter no greater than 1CM; Then calculate the data ratio of each part of the Z axis.

2. The mouse species identification device according to claim 1, characterized in that: A door is provided on one side of the box where the distance measuring unit is placed; the door is movably connected to the top of the box.

3. The mouse species identification device according to claim 1, characterized in that: An opening is provided on one side of the box where the point cloud acquisition unit is placed; the mouse to be identified enters the box through the opening.

4. The mouse species identification device according to claim 1, characterized in that: It also includes a battery; the battery is connected to the point cloud acquisition unit, the distance measuring unit and the processing unit respectively.

5. The mouse species identification device according to claim 1, characterized in that: The point cloud acquisition unit is a solid-state laser radar.

6. The mouse species identification device according to claim 1, characterized in that: The distance measuring unit is a laser rangefinder.

7. The mouse species identification device according to claim 1, characterized in that: The point cloud acquisition unit and the distance measuring unit both emit invisible lasers.

8. A method for identifying mouse species, characterized in that: The rat species identification method is applied to the rat species identification device according to any one of claims 1 to 7, and the rat species identification method includes: Acquire laser coordinate data of the mouse to be identified; the laser coordinate data includes epidermal point cloud data and displacement; determining a three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement; Determining the three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement, specifically comprising: Deleting abnormal data from the epidermal point cloud data to obtain normal epidermal point cloud data; the abnormal data includes epidermal point cloud data of the mouse to be identified turning around in the channel of the mouse type identification device; Configuring corresponding time for the epidermal point cloud data and the displacement to obtain normal epidermal point cloud data with time information and displacement with time information; Filtering out the normal epidermal point cloud data with time information and the data with time information whose time interval is greater than a preset interval, to obtain filtered epidermal point cloud data and filtered displacements; Generating a three-dimensional point cloud outline of the mouse to be identified using three-dimensional point cloud synthesis algorithm software based on the selected epidermal point cloud data and the filtered displacement; determining the proportions of the head, body, and tail of the mouse to be identified based on the three-dimensional point cloud outline; Determining the proportions of the head, body, and tail of the mouse to be identified based on the three-dimensional point cloud contour specifically includes: Each point cloud data packet uses two data structures, horizontal profile and vertical profile, to identify the mouse's head, body, and tail through regularity; the head is the data part from the front row of the Z axis to the part where the data diameter begins to decrease; the body is the data set part with the largest diameter; the tail is the data set part with a diameter no greater than 1CM; Then calculate the data ratio of each part of the Z axis; The type of the mouse to be identified is determined according to the ratio.

9. A mouse species identification system, characterized in that: include: A data acquisition module, used to obtain laser coordinate data of the mouse to be identified; The laser coordinate data includes epidermal point cloud data and displacement; a three-dimensional contour determination module, configured to determine a three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement; Determining the three-dimensional point cloud contour of the mouse to be identified based on the epidermal point cloud data and the displacement, specifically comprising: Deleting abnormal data from the epidermal point cloud data to obtain normal epidermal point cloud data; the abnormal data includes epidermal point cloud data of the mouse to be identified turning around in the channel of the mouse type identification device; Configuring corresponding time for the epidermal point cloud data and the displacement to obtain normal epidermal point cloud data with time information and displacement with time information; Filtering out the normal epidermal point cloud data with time information and the data with time information whose time interval is greater than a preset interval, to obtain filtered epidermal point cloud data and filtered displacements; Generating a three-dimensional point cloud outline of the mouse to be identified using three-dimensional point cloud synthesis algorithm software based on the selected epidermal point cloud data and the filtered displacement; a proportion calculation module, for determining the proportions of the head, body and tail of the mouse to be identified based on the three-dimensional point cloud contour; Determining the proportions of the head, body, and tail of the mouse to be identified based on the three-dimensional point cloud contour specifically includes: Each point cloud data packet uses two data structures, horizontal profile and vertical profile, to identify the mouse's head, body, and tail through regularity; the head is the data part from the front row of the Z axis to the part where the data diameter begins to decrease; the body is the data set part with the largest diameter; the tail is the data set part with a diameter no greater than 1CM; Then calculate the data ratio of each part of the Z axis; The identification module is used to determine the type of the mouse to be identified according to the ratio.

Images