CN-116973386-B - Method, device and system for quickly detecting eggs in grains by fusing insect eggs and insect hole structural characteristics and computer readable medium

CN116973386BCN 116973386 BCN116973386 BCN 116973386BCN-116973386-B

Abstract

The invention relates to the technical field of grain quality safety detection, and discloses a method, a device, a system and a computer readable medium for quickly detecting eggs in grains, wherein the method comprises the steps of acquiring grain pile gray digital images, performing three-dimensional reconstruction to obtain multi-grain pile stereoscopic images, dividing the multi-grain pile stereoscopic images to obtain single grain or multiple grain unit images, identifying insect hole areas in the single grain or multiple grain unit images based on insect biological characteristics, identifying whether the insect hole areas are insect egg areas based on insect hole structural characteristics, and identifying whether the insect egg areas are survival insect eggs based on insect egg geometric characteristics and physical characteristics. The CT tomography technology is applied to the detection of insect eggs of pests in grains, and the structural characteristics and biological characteristics of the insect eggs and insect holes are combined to directly detect pests in the egg period in the grains, so that less time consumption and high detection accuracy can be realized.

Inventors

SHAO XIAOLONG
YANG XIAOJING

Assignees

南京财经大学

Dates

Publication Date: 20260512
Application Date: 20220703

Claims (8)

1. The rapid detection method for the eggs in the grain grains by fusing the structural characteristics of the eggs and the worm holes is characterized by comprising the following steps of: Step1, acquiring a grain pile scanning image, wherein the grain pile scanning image comprises a plurality of gray scale digital images; step 2, carrying out three-dimensional reconstruction on the grain pile scanning image to obtain a multi-grain pile stereoscopic image; step 3, dividing the multi-grain pile stereoscopic image to obtain single grain or multi-grain unit images; Step 4, identifying insect hole areas in single grain or grain unit images based on insect biological characteristics; Step 5, identifying whether the worm hole area is an worm egg area based on the worm hole structural characteristics, and Step 6, identifying whether the insect eggs are alive or not in the insect egg area based on geometric characteristics and physical characteristics of the insect eggs; wherein, based on the geometric and physical characteristics of the eggs, identifying whether the eggs are viable eggs in the egg area comprises: Judging whether the insect eggs and the survival states of the insect eggs are contained in the insect egg area or not based on the geometric characteristics and the physical characteristics of the insect eggs; The geometric characteristics of the worm eggs comprise length, width, height, specific surface area, volume and sphericity characteristics of the worm eggs; The physical features include worm egg density features configured to be estimated based on a linear relationship of gray values of the gray image to density, wherein: the linear relationship is expressed as: ; wherein ρ 1 、ρ 2 、ρ 3 represents the density of air, grain particles and ovum respectively, and G 1 、G 2 、G 3 represents the gray value of air, grain particles and ovum respectively; The density rho 2 of the grain particles is calculated based on M/V, M represents the mass of the grain particles, and V represents the volume of the grain particles; the air density rho 1 is determined based on the altitude and the temperature of the test area; The grey values G 1 、G 2 、G 3 of the air, grain particles and ova are as follows: The gray values of the gray images are read, gray values of a plurality of points in an image area between the insect eggs and grain grains in the insect egg area are randomly taken and averaged to be used as air gray values G 1 , gray values of a plurality of points in a part of the image area corresponding to the non-insect hole area of the grain grains are randomly taken and averaged to be used as grain gray values G 2 , and gray values of a plurality of points in the image area inside the insect eggs in the insect egg area are randomly taken and averaged to be used as insect egg gray values G 3 .
2. The method for rapid detection of eggs in grains by fusing worm eggs with worm hole structural features according to claim 1, wherein the identification of worm hole areas in single grain or several grain unit images based on pest biological features comprises the following steps: judging whether the spherical or spheroidic cavity space is positioned at a shallow surface layer position below the surface of the single grain according to the spherical or spheroidic cavity space in the gray level image and is in a closed state, if so, judging the insect hole area, and if not, judging the insect hole area.
3. The method for rapid detection of eggs in grain, which fuses eggs with worm hole structural features according to claim 1, wherein the identifying whether the worm hole area is an egg area based on worm hole structural features comprises: judging whether the insect hole area is an insect egg area or not according to the step change of the gray level in the insect hole area.
4. The method for rapidly detecting eggs in grains by fusing eggs and worm holes according to claim 3, wherein the step change of gray level in the worm hole area is used for judging whether the eggs are egg areas or not, comprising the following steps: if the gray level in the worm hole area is in a high-low-high step change trend or a low-high-low step change trend, the worm hole area is judged, and if the gray level in the worm hole area is single, the worm hole area is judged to be a cavitation hole.
5. The method for quickly detecting eggs in grains by fusing eggs with the structural features of worm holes according to claim 1, wherein the step of judging whether eggs and the survival state of eggs are contained in the egg area based on the geometric features and the physical features of the eggs comprises the steps of: and judging whether the insect egg area contains the survival insect eggs or not based on the length, width, height, volume, specific surface area, sphericity and physical characteristics of the insect eggs within the range of a preset insect egg model, and otherwise judging that the insect eggs are inactivated or chips fill the cavities.
6. Quick detection device of grain interior worm ovum of fusion worm ovum and worm hole structural feature, its characterized in that includes: the image acquisition module is used for acquiring a grain pile scanning image, and the grain pile scanning image is a gray digital image; the three-dimensional reconstruction module is used for carrying out three-dimensional reconstruction on the grain pile scanning image to obtain a multi-grain pile stereoscopic image; the image segmentation module is used for carrying out segmentation processing on the multi-grain pile three-dimensional image to obtain single grain or multi-grain unit images; A pest hole area identification module for identifying pest hole areas in single grain or multiple grain unit images based on pest biological characteristics; An insect egg area identification module for identifying whether the insect hole area is an insect egg area based on the insect hole structural characteristics, and An egg identification module for identifying whether a viable egg is within the egg area based on the geometric and physical characteristics of the egg; wherein the geometric characteristics of the worm eggs comprise length, width, height, specific surface area, volume and sphericity characteristics of the worm eggs; The physical features include worm egg density features configured to be estimated based on a linear relationship of gray values of the gray image to density, wherein: the linear relationship is expressed as: ; wherein ρ 1 、ρ 2 、ρ 3 represents the density of air, grain particles and ovum respectively, and G 1 、G 2 、G 3 represents the gray value of air, grain particles and ovum respectively; The density rho 2 of the grain particles is calculated based on M/V, M represents the mass of the grain particles, and V represents the volume of the grain particles; the air density rho 1 is determined based on the altitude and the temperature of the test area; The grey values G 1 、G 2 、G 3 of the air, grain particles and ova are as follows: The gray values of the gray images are read, gray values of a plurality of points in an image area between the insect eggs and grain grains in the insect egg area are randomly taken and averaged to be used as air gray values G 1 , gray values of a plurality of points in a part of the image area corresponding to the non-insect hole area of the grain grains are randomly taken and averaged to be used as grain gray values G 2 , and gray values of a plurality of points in the image area inside the insect eggs in the insect egg area are randomly taken and averaged to be used as insect egg gray values G 3 .
7. A grain interior insect egg rapid detection system integrating insect egg and insect hole structural characteristics is characterized by comprising: one or more processors; A memory storing instructions operable, when executed by the one or more processors, to cause the one or more processors to perform operations comprising performing the process of any of the methods of claims 1-5.
8. A computer readable medium storing software, the software comprising instructions executable by one or more computers which when executed by the one or more computers implement the process of the method of any one of claims 1-5.

Description

Method, device and system for quickly detecting eggs in grains by fusing insect eggs and insect hole structural characteristics and computer readable medium Technical Field The invention relates to the technical field of grain quality safety detection, in particular to a method, a device, a system and a computer readable medium for quickly detecting eggs in grains by fusing insect eggs and insect hole structural characteristics. Background According to investigation statistics, the comprehensive loss of the grains in the world can reach 8% -10% each year due to insect attack, and huge economic loss is caused. The pests such as corn and rice damage the stored grain crops and lay eggs in the grains, such as wheat, rice, sorghum, corn, peanut, soybean, broad bean and the like, and the whole growth process is completed in the grains. The grain particles cannot be monitored by naked eyes and can be continuously eroded in the growth and development process, so that the grain storage safety is extremely threatened. At present, by means of a high-definition X-ray two-dimensional imaging and image processing technology, identification of pest larvae, pupae stages and adult stages in grain can be achieved, but early detection of pests still depends on artificial experience, so that detection efficiency and detection accuracy are low. More importantly, the eggs of the pests are difficult to detect. The pest eggs have concealment and stronger vitality, and are potential hazards for long time. Quick detection of eggs becomes a technical problem to be solved in the current industry. Disclosure of Invention According to a first aspect of the invention, there is provided a method for rapid detection of eggs in grains, which fuses the structural characteristics of eggs and worm holes, comprising the steps of: step 1, acquiring a grain pile scanning image, wherein the grain pile scanning image is a gray digital image; Step2, carrying out three-dimensional reconstruction on the grain pile scanning image to obtain a multi-grain pile stereoscopic image; step 3, dividing the multi-grain pile stereoscopic image to obtain single grain or multi-grain unit images; Step 4, identifying insect hole areas in single grain or grain unit images based on insect biological characteristics; step 5, identifying whether the worm hole area is an worm egg area based on the worm hole structural characteristics, and And step 6, identifying whether the insect eggs are alive or not in the insect egg area based on the geometric characteristics and the physical characteristics of the insect eggs. According to a second aspect of the present invention, there is also provided a rapid detection device for eggs in grains, which fuses structural features of eggs and worm holes, comprising: the image acquisition module is used for acquiring a grain pile scanning image; the three-dimensional reconstruction module is used for carrying out three-dimensional reconstruction on the grain pile scanning image to obtain a multi-grain pile stereoscopic image; the image segmentation module is used for carrying out segmentation processing on the multi-grain pile three-dimensional image to obtain single grain or multi-grain unit images; A pest hole area identification module for identifying pest hole areas in single grain or multiple grain unit images based on pest biological characteristics; an insect egg area identification module for identifying whether the insect hole area is an insect egg area based on the insect hole structural characteristics, and And the insect egg identification module is used for identifying whether the insect eggs are viable or not in the insect egg area based on the insect egg geometric characteristics and the physical characteristics. According to a third aspect of the present invention, there is also provided a rapid detection system for eggs in grains, which fuses structural features of eggs and worm holes, comprising: one or more processors; A memory storing instructions operable, when executed by the one or more processors, to cause the one or more processors to perform operations comprising performing the processes of the aforementioned methods. According to a fourth aspect of the object of the invention, there is also proposed a computer readable medium storing software comprising instructions executable by one or more computers, the operations comprising performing the process of the aforementioned method. Drawings The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component that is illustrated in various figures may be represented by a like numeral. For purposes of clarity, not every component may be labeled in every drawing. Embodiments of various aspects of the invention will now be described, by way of example, with reference to the accompanying drawings, in which: FIG. 1 is a schematic diagram of a rapid scanning detection system for eggs within grains according to an embodiment