Plant high-throughput phenotyping platform working condition detection method and device

Abstract

The present invention provides a method and device for detecting the working condition of a plant high-throughput phenotyping platform, the method comprising: obtaining target detection data of the plant high-throughput phenotyping platform; the target detection data comprising image data and point cloud data of the plant to be detected; and determining the motion speed error of the imaging unit of the plant high-throughput phenotyping platform and the height error of the imaging unit based on the target detection data. The method for detecting the working condition of the plant high-throughput phenotyping platform of the present invention can realize the analysis of the motion speed error and height error of the imaging unit of the plant high-throughput phenotyping platform by analyzing the image data and point cloud data collected by the plant high-throughput phenotyping platform, realize monitoring and detection of the working condition of the plant high-throughput phenotyping platform, facilitate timely maintenance, and thus facilitate the plant high-throughput phenotyping platform to stably and efficiently obtain detection data.

Description

Technical Field

[0001] The present invention relates to the technical field of plant phenotyping detection, and in particular to a method and device for detecting working conditions of a plant high-throughput phenotyping platform. Background Art

[0002] Plant phenotype refers to the physical, physiological and biochemical traits that can reflect the structural and functional characteristics of plant cells, tissues, organs, plants and populations. Its essence is the external temporal three-dimensional expression of crop gene maps under the influence of the environment, as well as its regional differentiation characteristics and intergenerational evolution laws. From the perspective of omics, systematic and in-depth exploration of the intrinsic relationship between "gene-phenotype-environment" can reveal the response mechanism of multi-scale structural and functional characteristics of plants to genetic information and environmental changes, which can achieve accurate identification of crop breeding omics and promote a significant improvement in crop breeding efficiency.

[0003] The raw data of high-throughput plant phenotyping is mainly obtained by mounting sensors such as visible light cameras, lidar, multi- / hyperspectral cameras, thermal infrared cameras on various phenotyping platforms, and then using phenotypic analysis methods and software to obtain phenotypic indicators of interest to agronomists. The plant high-throughput phenotyping platform is an important phenotyping infrastructure that can be deployed in the field or greenhouse. It drives the sensor through a transmission device to obtain phenotypic data of crops in the target area. The operating accuracy of the imaging unit of the plant high-throughput phenotyping platform determines the quality of the phenotypic data.

[0004] Due to the complex crop production environment, high temperature, high humidity, heavy rain, strong wind, soft soil and other conditions, the phenotyping platform frequently causes track sinking and rusting during data acquisition, which reduces the transmission accuracy of the imaging unit and leads to errors in the acquired phenotypic data. Plants are constantly growing, and their height changes every day. The height of the imaging unit from the plant is an important parameter for subsequent data processing. In addition, the operating speed of the imaging unit also has a great influence on the three-dimensional point cloud data and image data generated by the speed. Therefore, how to monitor and detect the working conditions of the plant high-throughput phenotyping platform during use to ensure that the platform can stably and efficiently obtain high-quality phenotypic data is an urgent problem to be solved. Summary of the invention

[0005] The present invention provides a method and device for detecting the working condition of a plant high-throughput phenotyping platform, which are used to solve the defect in the prior art that the working condition of the plant high-throughput phenotyping platform cannot be detected during use, and achieves the effect of detecting the working condition of the plant high-throughput phenotyping platform.

[0006] The present invention provides a method for detecting working conditions of a plant high-throughput phenotyping platform, comprising:

[0007] Acquire target detection data of a plant high-throughput phenotyping platform; the target detection data includes image data and point cloud data of the plant to be detected;

[0008] Based on the target detection data, a motion speed error of an imaging unit of the plant high-throughput phenotyping platform and a height error of the imaging unit are determined.

[0009] According to a method for detecting working conditions of a plant high-throughput phenotyping platform provided by the present invention, the image data includes a plurality of target images collected continuously, and the motion speed error of the imaging unit is determined by the following method:

[0010] Determine the target overlap width of two consecutive target images in the moving direction of the imaging unit;

[0011] Determining the motion speed error based on all the target overlap widths and the standard width;

[0012] The standard width is the overlap width of two images continuously acquired when the imaging unit moves at a standard speed in the moving direction of the imaging unit.

[0013] According to a method for detecting working conditions of a plant high-throughput phenotyping platform provided by the present invention, the image data includes a plurality of target images collected continuously, and the height error of the imaging unit is determined by the following method:

[0014] Determine the target overlap size of two consecutive target images in a direction perpendicular to the motion direction of the imaging unit;

[0015] Determining the height error based on all of the target overlap dimensions and the standard dimensions;

[0016] The standard size is the size of the target image in a direction perpendicular to the movement direction of the imaging unit.

[0017] According to a method for detecting working conditions of a plant high-throughput phenotyping platform provided by the present invention, the image data includes a plurality of target images collected continuously, and the motion speed error of the imaging unit is determined by the following method:

[0018] Determining the size of the image data;

[0019] Determining the motion speed error based on the size of the image data;

[0020] or,

[0021] determining the number of the target images;

[0022] Based on the number of the target images, the motion speed error is determined.

[0023] According to a method for detecting working conditions of a plant high-throughput phenotyping platform provided by the present invention, the motion speed error of the imaging unit is determined by the following method:

[0024] Dividing a plurality of first target intervals in a moving direction of the imaging unit;

[0025] Based on all the point cloud data in each of the first target intervals, determining an average distance between points corresponding to two adjacent point cloud data in each of the first target intervals in the motion direction of the imaging unit;

[0026] Based on all of the average spacings, the motion speed error is determined.

[0027] According to a method for detecting working conditions of a plant high-throughput phenotyping platform provided by the present invention, before obtaining target detection data of the plant high-throughput phenotyping platform, the method comprises:

[0028] Dividing a plurality of second target intervals in the moving direction of the imaging unit;

[0029] Controlling the movement of the imaging unit and determining the movement speed of the imaging unit in all the second target intervals;

[0030] Based on all the movement speeds, determining a movement speed error of the imaging unit;

[0031] When the motion speed error is greater than a first threshold, it is determined that the plant high-throughput phenotyping platform needs to be repaired.

[0032] The present invention also provides a plant high-throughput phenotyping platform working condition detection device, comprising:

[0033] An acquisition module, used to acquire target detection data of a plant high-throughput phenotyping platform; the target detection data includes image data and point cloud data of the plant to be detected;

[0034] A processing module is used to determine a motion speed error of an imaging unit of the plant high-throughput phenotyping platform and a height error of the imaging unit based on the target detection data.

[0035] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for detecting the working condition of a high-throughput phenotyping platform for plants as described above is implemented.

[0036] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for detecting the working condition of a plant high-throughput phenotyping platform as described in any one of the above is implemented.

[0037] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned plant high-throughput phenotyping platform working condition detection methods.

[0038] The method and device for detecting the working condition of a plant high-throughput phenotyping platform provided by the present invention can analyze the motion speed error and height error of the imaging unit of the plant high-throughput phenotyping platform by analyzing the image data and point cloud data collected by the plant high-throughput phenotyping platform, thereby monitoring and detecting the working condition of the plant high-throughput phenotyping platform, facilitating timely maintenance, and thus facilitating the plant high-throughput phenotyping platform to obtain detection data stably and efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 It is a schematic diagram of the process of the plant high-throughput phenotyping platform working condition detection method provided by the present invention;

[0041] Figure 2 It is a schematic diagram of the structure of the plant high-throughput phenotyping platform working condition detection device provided by the present invention;

[0042] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0044] Combine the following Figure 1-Figure 3 The present invention describes a method and device for detecting working conditions of a plant high-throughput phenotyping platform.

[0045] Before describing the working condition detection method of the plant high-throughput phenotyping platform according to an embodiment of the present invention, the plant high-throughput phenotyping platform is described first.

[0046] The plant high-throughput phenotyping platform mainly includes an imaging unit and a carrying platform. The imaging unit may include sensors such as a visible light camera, a lidar, a multi- / hyperspectral camera, and a thermal infrared camera. The carrying platform is used to carry the imaging unit, and the imaging unit can move on the carrying platform to obtain phenotypic data of plants at different positions.

[0047] In related technologies, the carrier platform is usually a track platform, and the imaging unit has good height and speed stability when moving on the track, which can ensure that the collected data has high quality and accuracy. In this case, it is necessary to ensure that the height of the imaging unit from the ground and the speed of movement do not change significantly, and that the imaging unit runs at the same speed in each section of the track, so as to ensure the accuracy and quality of the acquisition of phenotypic data such as point cloud data and image data.

[0048] The working condition detection method of the plant high-throughput phenotyping platform of the embodiment of the present invention is described below using the track-type plant high-throughput phenotyping platform.

[0049] The execution subject of the plant high-throughput phenotyping platform working condition detection method of the embodiment of the present invention may be a controller. Of course, in some embodiments, the execution subject may also be a server, and the type of the execution subject is not limited here. The following takes the execution subject as an example to illustrate the plant high-throughput phenotyping platform working condition detection method of the embodiment of the present invention.

[0050] Reference Figure 1 The plant high-throughput phenotyping platform working condition detection method of the embodiment of the present invention mainly includes step 110 and step 120.

[0051] Step 110, obtaining target detection data of the plant high-throughput phenotyping platform.

[0052] It can be understood that the target detection data is data directly obtained through the plant high-throughput phenotyping platform, and the target detection data includes image data and point cloud data of the plant to be detected.

[0053] It is understandable that the image data may be images taken by a visible light camera, a spectral camera or a thermal infrared camera of an imaging unit, etc. The point cloud data may be spatial position coordinate information of various parts of a plant acquired by a laser radar of an imaging unit.

[0054] When the imaging unit moves along the track-type carrying platform, it continuously collects the phenotypic data of the plant, and then continuously obtains the target detection data.

[0055] In this process, the same image sensor on the imaging unit can collect image data at a certain time interval. It is understandable that in order to maximize the coverage of target detection data on plants, two images continuously collected by the same image sensor will have a certain overlap area to achieve full coverage of plant image data.

[0056] For example, visible light images captured by visible light cameras can be used for research in areas such as crop counting, crop ear identification, pest and disease detection, and population three-dimensional modeling.

[0057] Similarly, spectral cameras can be used to collect spectral images, which can then be used for research in plant nutrition, soil fertility, decision-making prescriptions, and crop yield estimation. Thermal infrared cameras can be used to collect thermal infrared images, which can then be used for research in plant canopy evapotranspiration estimation, plant water stress detection, irrigation management, and other areas.

[0058] When using laser radar to collect point cloud data, a point cloud data map of a certain density can be generated according to the movement speed of the imaging unit.

[0059] For example, the acquired point cloud data can be used to conduct research in areas such as precise measurement of plant height and detection of plant canopy structure.

[0060] Step 120, based on the target detection data, determining the motion speed error and the height error of the imaging unit of the plant high-throughput phenotyping platform

[0061] It is understandable that the target detection data includes image data and point cloud data of the plant to be detected. During a normal acquisition process, the imaging unit maintains a certain speed for acquisition in each section of the track, and maintains a set height for acquisition during one acquisition process.

[0062] Since the same image sensor on the imaging unit can collect image data at a certain time interval, two images continuously collected by the same image sensor will have a certain overlap area.

[0063] Therefore, in some embodiments, when the time interval for collecting image data is known, the height error and movement speed error of the sensor on the imaging unit when collecting image data can be determined based on the overlap area and the size of the overlap area.

[0064] In other embodiments, since the same image sensor on the imaging unit can collect image data at certain time intervals and the imaging unit will only collect images when it is moving, when the movement speed of the imaging unit has a large deviation, the size of the collected image data will also have a large deviation, and the movement speed error can be determined thereby.

[0065] In other embodiments, since the point cloud data collected by the laser radar carried by the imaging unit is related to the movement speed of the imaging unit, the movement speed error can be determined based on the spatial distribution of the point cloud data.

[0066] According to the method for detecting the working condition of a high-throughput phenotyping platform for plants provided in an embodiment of the present invention, by analyzing the image data and point cloud data collected by the high-throughput phenotyping platform for plants, it is possible to analyze the motion speed error and height error of the imaging unit of the high-throughput phenotyping platform for plants, thereby monitoring and detecting the working condition of the high-throughput phenotyping platform for plants, facilitating timely maintenance, and thereby facilitating the high-throughput phenotyping platform for plants to obtain detection data stably and efficiently.

[0067] In some embodiments, the image data includes a plurality of target images acquired continuously, and the motion speed error of the imaging unit may be determined in the following manner.

[0068] The target overlap width of two consecutive target images in the moving direction of the imaging unit may be determined first. It is understandable that the moving direction of the imaging unit is along the setting direction of the track.

[0069] If the imaging unit moves along a horizontally arranged track, the target overlap width is the width of the overlap area of ​​the two target images in the horizontal direction.

[0070] In some embodiments, an artificial intelligence neural network model may be used to identify overlapping areas of two consecutive target images, such as an image segmentation recognition model.

[0071] It is understandable that the neural network model can be Faster R-CNN (Fast Region Convolutional Neural Networks) or YOLO (You Only Look Once) algorithm, etc., and there is no restriction on the type of image segmentation and recognition model.

[0072] For different types of images collected by different types of image sensors, samples of different image categories can be used to train the image segmentation and recognition model.

[0073] For example, for visible light images taken by a visible light camera, the model can be trained using visible light image samples. For thermal infrared images taken by a thermal infrared camera, the model can be trained using thermal infrared image samples. The type of training samples for the model can be selected based on actual conditions.

[0074] After the overlapping area of ​​the two target images is identified by the model, the size of the overlapping area can be determined.

[0075] For example, for target images captured along the horizontal direction, the target overlap width of two target images in the horizontal direction may be determined.

[0076] After determining the target overlap width, the error in the overlap width can be determined by comparing it with the standard width. Since the overlap width of two consecutive target images taken by the same image sensor at a set motion speed of the imaging unit is also certain, the actual motion speed of the imaging unit can be determined based on the target overlap width, and then the motion speed error can be determined.

[0077] It should be noted that the standard width is the overlap width of two images continuously captured in the moving direction of the imaging unit when the imaging unit moves at a standard speed. The standard speed of the imaging unit is the moving speed set in the moving direction.

[0078] In this case, the target overlap width at each position in the moving direction of the imaging unit can be determined based on all the acquired target images, and the moving speed error in the moving direction can be determined based on all the target overlap widths and the standard width.

[0079] In this embodiment, by determining the size of the overlapping area of ​​the continuously acquired target images in the direction of motion, the motion speed error of the imaging unit can be accurately obtained, thereby facilitating timely maintenance and improving the accuracy of the data acquired by the plant high-throughput phenotyping platform.

[0080] In some embodiments, the height error of the imaging unit may be determined based on two adjacent acquired target images, and the height error of the imaging unit may be determined in the following manner.

[0081] In this embodiment, the target overlap size of two consecutive target images in a direction perpendicular to the movement direction of the imaging unit is determined.

[0082] For example, for a target image captured along a horizontal direction, the overlap size of the overlapped area of ​​two target images in the vertical direction, ie, the target overlap size, can be determined.

[0083] It should be noted that when the height of the imaging unit is in a stable state, the height of the imaging unit will not change, so the overlapping size of the overlapping area of ​​two consecutive target images in the vertical direction is the size of the target image in the vertical direction.

[0084] In this case, the height error can be determined based on the size relationship between the target overlap size of the overlap area of ​​two consecutive target images in the vertical direction and the standard size. The standard size is the size of the target image in the direction perpendicular to the motion direction of the imaging unit.

[0085] In this embodiment, the difference between the standard size and the target overlap size is the height error. Of course, the height of the imaging unit can be further determined based on the position of the overlap area in the target image, which will not be described in detail here.

[0086] Therefore, based on all target coincidence dimensions and standard dimensions, a height error can be determined when there is a difference between the target coincidence dimension and the standard dimension.

[0087] In this embodiment, by determining the size of the overlapping area of ​​the continuously acquired target images perpendicular to the direction of movement, the height error of the imaging unit can be accurately obtained, thereby facilitating timely maintenance and improving the accuracy of the data obtained by the plant high-throughput phenotyping platform.

[0088] In some embodiments, the image data includes a plurality of target images acquired continuously, and the motion speed error of the imaging unit is further determined in the following manner.

[0089] In this embodiment, the size of the image data may be determined first, and then the motion speed error may be determined based on the size of the image data.

[0090] It is understandable that, when the imaging unit is moving, various image sensors on the imaging unit also start to collect image data. When collecting at a set standard speed, the number of collected target images is certain, so whether there is an error in the movement speed can be determined based on the number of target images.

[0091] In this case, the number of images collected by a sensor when moving at a set standard speed can be determined in advance, and then the number of target images collected by the sensor during the actual measurement process can be determined and compared with the number of images collected by a sensor when moving at the set standard speed.

[0092] If the two numbers are different or the difference is too large, it can be determined that the imaging unit has a motion speed error, and the size of the motion speed error can be inferred based on the difference.

[0093] In other embodiments, since the number of images captured by a sensor when moving at a set standard speed is certain, and the data size of a target image captured by the image sensor is constant within a range, the motion speed error can be determined based on the size of the captured image data.

[0094] In this case, the size of the image data collected by a sensor when moving at a set standard speed can be determined in advance, and then the size of the image data collected by the sensor during the actual measurement process can be determined and compared with the size of the image data collected by a sensor when moving at the set standard speed.

[0095] If the difference between the data sizes of the two is not within a reasonable range, it can be determined that the imaging unit has a motion speed error, and the size of the motion speed error can be inferred based on the size of the difference.

[0096] In this embodiment, by monitoring the number of collected target images or the size of image data, the motion speed error of the imaging unit can be identified, thereby facilitating timely maintenance to improve the accuracy of data acquired by the plant high-throughput phenotyping platform.

[0097] In some embodiments, the motion speed error of the imaging unit may also be determined by point cloud data acquired by a laser radar.

[0098] In this embodiment, a plurality of first target intervals may be divided in the moving direction of the imaging unit.

[0099] For example, if the imaging unit moves in a horizontal direction, a spatial rectangular coordinate system can be established with the horizontal direction as the x-axis and the vertical direction as the z-axis. On the xoz plane, rectangular areas corresponding to multiple first target intervals can be obtained.

[0100] When the imaging unit moves in the horizontal direction, if the movement speed remains unchanged, the scaling ratio between the plant outline formed by the points corresponding to the point cloud data in each first target interval on the xoz plane and the real outline of the measured plant is the same.

[0101] When the movement speeds of different first target intervals are different, the horizontal spacings between the points corresponding to the point cloud data on the xoz plane are also different.

[0102] In this case, the average distance between points corresponding to two adjacent point cloud data in each first target interval in the motion direction of the imaging unit can be determined based on all point cloud data in each first target interval, and the motion speed error can be determined based on all average distances.

[0103] It is understandable that when the actual motion speed of the imaging unit is too fast, the average spacing will be too small; when the actual motion speed of the imaging unit is too slow, the average spacing will be too large. In this case, the motion speed can be determined according to the specific size of the average spacing, and then compared with the standard speed to determine the size of the motion speed error.

[0104] In this embodiment, by analyzing the specific distribution of the point cloud data, the motion speed error can be easily determined, thereby facilitating timely maintenance and improving the accuracy of the data obtained by the plant high-throughput phenotyping platform.

[0105] In some embodiments, before acquiring target detection data of the plant high-throughput phenotyping platform, a troubleshooting test may be performed in advance to determine whether there are motion speed errors and height errors.

[0106] A plurality of second target intervals may be divided in the direction of motion of the imaging unit. In this case, points may be set at key positions of the track-type plant high-throughput phenotyping platform. For example, key positions include the starting position, the column point of the track, the inflection point position, and the end position, and the interval between the two points is used as the second target interval.

[0107] In this case, the movement of the imaging unit is controlled, and the movement speed of the imaging unit in all the second target intervals is determined.

[0108] Specifically, when the imaging unit passes through a set key point, the point time is automatically recorded. According to the distance between adjacent points and the time difference when the imaging unit passes through the corresponding point, the movement speed of the imaging unit in the second target interval corresponding to the distance is calculated, and then the movement speed error of the imaging unit is determined.

[0109] The movement speed measured by the plant high-throughput phenotyping platform before each day's operation must be compared with the standard speed. If the error is higher than the set first threshold, the movement speed of the imaging unit has changed significantly, and the plant high-throughput phenotyping platform needs to be inspected and maintained.

[0110] Specifically, it can be determined that the running speed in a certain second target interval is higher than the first threshold, which indicates that the speed of the imaging unit in the second target interval has changed significantly, and the track of the second target interval needs to be inspected and maintained.

[0111] In this embodiment, by conducting a trial run for inspection before formal data collection, it is possible to eliminate possible faults in the plant high-throughput phenotyping platform before formal measurement, thereby improving the accuracy of each data collection and the overall collection efficiency.

[0112] In some embodiments, the height error can also be checked and calibrated before formal measurement. For example, a zero position is set on the track-type plant high-throughput phenotyping platform, that is, the static position of the imaging unit when the platform is not started.

[0113] A reference plane is set at the zero position, and the height of the plane is fixed throughout the crop growth period as a reference height. The standard distance from the bottom of the imaging unit to the zero position reference plane can be measured and recorded with a laser rangefinder. Before starting the platform for data acquisition each time and after the imaging unit returns to the reference position after data acquisition, a laser rangefinder is used to measure the distance from the imaging unit to the zero position reference plane, and compared with the standard to obtain the height error. When the height error is higher than the set threshold, it is considered that the height of the imaging unit has changed significantly, and the platform needs to be inspected and maintained.

[0114] In other embodiments, in order to improve the accuracy of the acquired image data, a temperature sensor may be provided in the imaging unit. If the temperature in the imaging unit is higher than a preset threshold, an alarm may be sounded, thereby facilitating the timely stop of acquisition and avoiding data acquisition errors caused by the image sensor due to excessive temperature.

[0115] The plant high-throughput phenotyping platform working condition detection device provided by the present invention is described below. The plant high-throughput phenotyping platform working condition detection device described below and the plant high-throughput phenotyping platform working condition detection method described above can be referenced to each other.

[0116] Reference Figure 2 The plant high-throughput phenotyping platform working condition detection device of the embodiment of the present invention includes an acquisition module 210 and a processing module 220.

[0117] The acquisition module 210 is used to acquire target detection data of the plant high-throughput phenotyping platform; the target detection data includes image data and point cloud data of the plant to be detected;

[0118] The processing module 220 is used to determine the motion speed error and the height error of the imaging unit of the plant high-throughput phenotyping platform based on the target detection data.

[0119] According to the plant high-throughput phenotyping platform working condition detection device provided by the embodiment of the present invention, by analyzing the image data and point cloud data collected by the plant high-throughput phenotyping platform, it is possible to analyze the motion speed error and height error of the imaging unit of the plant high-throughput phenotyping platform, thereby realizing monitoring and detection of the working condition of the plant high-throughput phenotyping platform, facilitating timely maintenance, and thereby facilitating the plant high-throughput phenotyping platform to obtain detection data stably and efficiently.

[0120] In some embodiments, the image data includes multiple target images captured continuously, and the processing module 220 is also used to determine the target overlap width of two consecutive target images in the movement direction of the imaging unit; based on all target overlap widths and the standard width, determine the movement speed error; the standard width is the overlap width of two continuously captured images in the movement direction of the imaging unit when the imaging unit moves at a standard speed.

[0121] In some embodiments, the image data includes multiple target images captured continuously, and the processing module 220 is also used to determine the target overlap size of two consecutive target images in the direction of movement perpendicular to the imaging unit; determine the height error based on all target overlap sizes and standard sizes; the standard size is the size of the target image in the direction of movement perpendicular to the imaging unit.

[0122] In some embodiments, the image data includes multiple target images collected continuously, and the processing module 220 is also used to determine the size of the image data; based on the size of the image data, determine the motion speed error; or, the processing module 220 is also used to determine the number of target images; based on the number of target images, determine the motion speed error.

[0123] In some embodiments, the processing module 220 is also used to divide the imaging unit into multiple first target intervals in the direction of movement of the imaging unit; based on all point cloud data in each first target interval, determine the average spacing between points corresponding to two adjacent point cloud data in each first target interval in the direction of movement of the imaging unit; based on all average spacings, determine the motion speed error.

[0124] In some embodiments, the plant high-throughput phenotyping platform working condition detection device of the embodiment of the present invention also includes a control module, which is used to divide the movement direction of the imaging unit into multiple second target intervals; control the movement of the imaging unit, and determine the movement speed of the imaging unit in all second target intervals; based on all movement speeds, determine the movement speed error of the imaging unit; when the movement speed error is greater than a first threshold, determine that the plant high-throughput phenotyping platform needs to be repaired.

[0125] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the working condition detection method of the plant high-throughput phenotyping platform, the method comprising: obtaining target detection data of the plant high-throughput phenotyping platform; the target detection data includes image data and point cloud data of the plant to be detected; based on the target detection data, determining the motion speed error of the imaging unit of the plant high-throughput phenotyping platform and the height error of the imaging unit.

[0126] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0127] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the plant high-throughput phenotyping platform working condition detection method provided by the above-mentioned methods, and the method includes: obtaining target detection data of the plant high-throughput phenotyping platform; the target detection data includes image data and point cloud data of the plant to be detected; based on the target detection data, determining the motion speed error of the imaging unit and the height error of the imaging unit of the plant high-throughput phenotyping platform.

[0128] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the plant high-throughput phenotyping platform working condition detection method provided by the above-mentioned methods, the method comprising: obtaining target detection data of the plant high-throughput phenotyping platform; the target detection data comprising image data and point cloud data of the plant to be detected; based on the target detection data, determining the motion speed error of the imaging unit and the height error of the imaging unit of the plant high-throughput phenotyping platform.

[0129] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0130] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0131] 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 make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting working conditions of a plant high-throughput phenotyping platform, characterized in that: include: Acquire target detection data of a plant high-throughput phenotyping platform; the target detection data includes image data and point cloud data of the plant to be detected; Determining a motion speed error of an imaging unit of the plant high-throughput phenotyping platform and a height error of the imaging unit based on the target detection data; The image data includes a plurality of target images collected continuously, and the height error of the imaging unit is determined by: Determine the target overlap size of two consecutive target images in a direction perpendicular to the motion direction of the imaging unit; Determining the height error based on all of the target overlap dimensions and the standard dimensions; The standard size is the size of the target image in a direction perpendicular to the movement direction of the imaging unit.

2. The plant high-throughput phenotyping platform working condition detection method according to claim 1, characterized in that: The image data includes a plurality of target images collected continuously, and the motion speed error of the imaging unit is determined by: Determine the target overlap width of two consecutive target images in the moving direction of the imaging unit; Determining the motion speed error based on all the target overlap widths and the standard width; The standard width is the overlap width of two images continuously acquired when the imaging unit moves at a standard speed in the moving direction of the imaging unit.

3. The plant high-throughput phenotyping platform working condition detection method according to claim 1, characterized in that: The image data includes a plurality of target images collected continuously, and the motion speed error of the imaging unit is determined by: Determining the size of the image data; Determining the motion speed error based on the size of the image data; or, determining the number of the target images; Based on the number of the target images, the motion speed error is determined.

4. The plant high-throughput phenotyping platform working condition detection method according to claim 1, characterized in that: The motion speed error of the imaging unit is determined by: Dividing a plurality of first target intervals in a moving direction of the imaging unit; Based on all the point cloud data in each of the first target intervals, determining an average distance between points corresponding to two adjacent point cloud data in each of the first target intervals in the motion direction of the imaging unit; Based on all of the average spacings, the motion speed error is determined.

5. The plant high-throughput phenotyping platform working condition detection method according to claim 1, characterized in that: Before obtaining the target detection data of the plant high-throughput phenotyping platform, the method includes: Dividing a plurality of second target intervals in the moving direction of the imaging unit; Controlling the movement of the imaging unit and determining the movement speed of the imaging unit in all the second target intervals; Based on all the movement speeds, determining a movement speed error of the imaging unit; When the motion speed error is greater than a first threshold, it is determined that the plant high-throughput phenotyping platform needs to be repaired.

6. A plant high-throughput phenotyping platform working condition detection device, characterized in that: include: An acquisition module, used to acquire target detection data of a plant high-throughput phenotyping platform; the target detection data includes image data and point cloud data of the plant to be detected; A processing module, configured to determine a motion speed error of an imaging unit of the plant high-throughput phenotyping platform and a height error of the imaging unit based on the target detection data; The image data includes a plurality of target images collected continuously, and the height error of the imaging unit is determined by: Determine the target overlap size of two consecutive target images in a direction perpendicular to the motion direction of the imaging unit; Determining the height error based on all of the target overlap dimensions and the standard dimensions; The standard size is the size of the target image in a direction perpendicular to the movement direction of the imaging unit.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the plant high-throughput phenotyping platform working condition detection method as described in any one of claims 1 to 5 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the plant high-throughput phenotyping platform working condition detection method as described in any one of claims 1 to 5 is implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the plant high-throughput phenotyping platform working condition detection method as described in any one of claims 1 to 5 is implemented.

Images