Recognition method of excavator working state based on hybrid lbf shape regression model

A technology of working state and regression model, applied in character and pattern recognition, computer components, instruments, etc., can solve the problem of less research on LBF shape regression model detection

Active Publication Date: 2019-06-25
SOUTH CHINA AGRI UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are very few studies on the detection of feature points of other target objects using the LBF shape regression model.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Recognition method of excavator working state based on hybrid lbf shape regression model
  • Recognition method of excavator working state based on hybrid lbf shape regression model
  • Recognition method of excavator working state based on hybrid lbf shape regression model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further described below in conjunction with the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0023] Such as figure 1 , the present invention is divided into off-line learning stage and on-line recognition working stage:

[0024] S1, during the learning phase, prepare for excavator training, train the hybrid LBF shape regression model of the excavator, use the shape feature to calculate the change angle, construct the feature descriptor MMF (Machine Motion Feature) of the working state of the excavator, and train the MMF as input SVM classifier for excavator working state recognition.

[0025] S11: Excavator dataset preparation.

[0026] In the experiment, the DPM (deformable part model) detection model is used to detect the excavator in the video sequence, and the detected 3000 excavator image sequences are saved as the material of this experiment. For each excavator image, manually mark ...

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

No PUM Login to View More

Abstract

The invention discloses a method for identifying the working state of an excavator based on a hybrid LBF shape regression model, which includes the following steps: 1) training the hybrid LBF shape regression model of the excavator, and using this model to predict the shape of the excavator in the input video frame (that is, the set of relative coordinates of the feature points); 2) According to the coordinates of these feature points and the detected aspect ratio of the excavator, calculate the feature descriptor of the working state of the excavator; 3) Use the SVM classifier to judge the current excavator Working state - working state or non-working state. The method for identifying the working state of the excavator based on the mixed LBF shape regression model proposed by the invention can accurately and automatically identify the working state of the excavator in the land, and provides an intelligent means for monitoring the construction site.

Description

technical field [0001] The present invention relates to the technical field of intelligent video analysis, and more specifically, relates to an excavator working state recognition method based on a hybrid LBF (Local Binary Features, local binary features) shape regression model. Background technique [0002] my country's land resources are becoming more and more serious, and various illegal land use cases are also frequently occurring. The Ministry of Land and Resources attaches great importance to land law enforcement and supervision. In 2011, the Ministry of Land and Resources carried out land video surveillance pilots in 15 prefecture-level cities and counties (cities, districts), and carried out video surveillance on key areas prone to illegal land use. Excavators are one of the most important construction machinery in engineering construction. Accurate and automatic identification of the working status of excavators between land is an important means to timely discover ...

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
no application Login to View More
Patent Type & AuthorityPatents(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V20/42G06V10/467G06V10/44G06F18/2411
Inventor薛月菊毛亮林焕凯
OwnerSOUTH CHINA AGRI UNIV