Object intrusion detection method and device based on grid division and neural network
A neural network and grid division technology, applied in the field of image recognition, can solve the problem of inaccurate detection, and achieve the effect of great application value and high accuracy.
Active Publication Date: 2019-12-31
XIAMEN MEIYA PICO INFORMATION
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The present invention aims to provide a target object intrusion detection method based on grid division and neural network to solve the problem that current algorithms cannot accurately detect objects such as cranes in various environments
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
[0025] To further illustrate the various embodiments, the present invention is provided with accompanying drawings. These drawings are a part of the disclosure of the present invention, which are mainly used to illustrate the embodiments, and can be combined with related descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, those skilled in the art should understand other possible implementations and advantages of the present invention.
[0026] The present invention will be further described in conjunction with the accompanying drawings and specific embodiments.
[0027] figure 1 A flowchart of an embodiment of the invention is shown. Taking a crane as an example, the object intrusion detection method based on grid division and neural network of the present invention will be described below. However, it should be understood that the present invention is not limited thereto.
[0028] S1. Image sample col...
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 present invention relates to a target object intrusion detection method and device based on grid division and neural network. The method may include the following steps: S1. Collect a target object picture sample and preprocess it, and record the circumscribed rectangle of the target object in the picture sample Frame coordinates; S2, divide the image sample into W*H grids, and then classify them into positive sample grids, partial sample grids, and negative sample grids; S3, extract feature heat maps from the grids and Predict the coordinates of the circumscribed rectangular frame; S4, select the optimal grid ratio as the sample training model and use it as the final application model; S5, merge the grids to obtain the position of the target object. The invention can effectively detect the position of the crane, frame the coordinate points in the picture, and has high accuracy. Therefore, it has great application value in monitoring dangerous vehicles such as cranes.
Description
technical field [0001] The invention relates to the field of image recognition, in particular to a method and device for object intrusion detection based on grid division and neural network. Background technique [0002] In a narrow sense, target detection algorithms are collectively referred to as target positioning algorithms, but target detection algorithms can simultaneously locate the positions of different objects. Crane detection is a kind of target detection. It is not difficult for humans to see and distinguish the difference from other objects. It is easy to locate and classify the target objects through the distribution of different color modules and contrast in the picture. For computers, researchers have also studied a large number of target detection algorithms. When the picture quality is clear enough and the target is large enough, these detection algorithms are barely satisfactory. Traditional target detection generally uses the framework of sliding windows...
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): G06T7/00G06T7/70G06K9/62
CPCG06T7/0002G06T7/70G06T2207/20076G06T2207/20081G06T2207/20084G06T2207/20021G06F18/214G06F18/2414
Inventor 黄仁裕高志鹏张光斌姚灿荣尤俊生庄进发
Owner XIAMEN MEIYA PICO INFORMATION