A method and device for detecting and counting grain grains based on deep learning
A technology of deep learning and counting methods, which is applied to the counting of items shipped through the conveying device, counting objects, counting mechanisms/items, etc., can solve the problems that cannot meet the detection and counting of different grain grains, and achieve convenient operation and smooth calculation process. Simplicity, high recall and accuracy
Active Publication Date: 2021-07-02
ANHUI GAOZHE INFORMATION TECH CO LTD
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the present invention is to provide a method and device for detecting and counting grain grains based on deep learning, so as to solve the problem that the prior art proposed in the above-mentioned background technology cannot satisfy the detection and counting of different grain grains
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0024] see Figure 1-6 , the present invention provides a technical solution: a method for detecting and counting grain grains based on deep learning, comprising the following steps:
[0025] S1. Design of deep convolutional learning network model;
[0026] S2. Solve the parameters of the deep convolutional learning network model.
[0027] The construction of the deep convolutional learning network model in step S1 needs to solve the detection of dense small targ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method and device for detecting and counting grain grains based on deep learning in the technical field of grain grain counting, including a box body, a high-definition camera, a bright field lighting lamp, a grain grain loading plate, a transmission mechanism, and dark field lighting Lamp, grain grain feeding port, man-machine interactive touch screen and electromechanical control device, the grain grain feeding port is located above the box body, the surface of the conveying mechanism is fixed with a grain grain loading plate, and the electromechanical control device is electrically connected with the conveying mechanism, The transmission mechanism is fixed between the front and back of the inner wall of the box, and the high-definition camera is located on the top of the inner cavity of the box. The high-definition camera is connected to the human-computer interaction touch screen signal. Through deep convolution learning network model design and parameter solution, it can detect dense and The sticky grain grain target has been tested, and the recall rate and correct rate of grain grain detection are very high, the calculation process is simple, and the operation is convenient.
Description
technical field [0001] The invention relates to the technical field of counting grain grains, in particular to a method and device for detecting and counting grain grains based on deep learning. Background technique [0002] The most widely used method for grain grain detection and counting is the image processing technology based on machine vision. The most commonly used technology in machine vision is image segmentation, and image segmentation methods include Otsu threshold method, edge method, watershed method and distance transformation method. These methods will have some defects or problems, they are insurmountable, grain grain object detection is not like other object detection, they have some unique attributes and states, for example, the grain size is small, the number of grains in a picture is large and It is relatively dense, and there will be multiple adhesions and other states. [0003] At present, there are also some studies that mention the use of some speci...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01N21/85G06M7/00
CPCG01N21/85G06M7/00
Inventor 武勇朱逞春周金旺
Owner ANHUI GAOZHE INFORMATION TECH CO LTD