Unlock instant, AI-driven research and patent intelligence for your innovation.

Driving attitude recognition method based on fusion features of local deformable parts model

A fusion technology of deformed parts and models, applied in the field of intelligent transportation, can solve the problems of recognition speed defects, poor recognition robustness, inapplicable high-efficiency feedback and early warning, etc., to achieve improved recognition speed and accuracy, good feedback fastness, Strong time-sensitive effect

Active Publication Date: 2020-04-14
SOUTHEAST UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the global-based DPM driving posture recognition method contains a lot of redundant information when processing the driving posture image, the recognition of key body parts is not robust, and has obvious defects in recognition speed, which is not suitable for efficient driving under high-speed driving conditions. Feedback and warning

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
  • Driving attitude recognition method based on fusion features of local deformable parts model
  • Driving attitude recognition method based on fusion features of local deformable parts model
  • Driving attitude recognition method based on fusion features of local deformable parts model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Below in conjunction with accompanying drawing and specific embodiment, further illustrate the present invention, should be understood that these embodiments are only for illustrating the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various aspects of the present invention Modifications in equivalent forms all fall within the scope defined by the appended claims of this application.

[0029] A driving posture recognition method based on fusion features of local deformable part models, comprising the following steps:

[0030] The first step: use the video sensor to obtain the image of the driver's posture, and define the driving posture core area (Driving Posture Core Area, DPCA), which are the driver's head area, torso area and hand area: as figure 1 Shown is a schematic diagram of the division of the local core area of ​​the driving posture, and the ...

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 driving posture recognition method based on fusion features of local deformable part models. The method of the present invention comprises the following steps: (1) adopting the video sensor to obtain the image of the driver's posture, and defining the local core area of ​​the driving posture; (2) adopting linear discriminant analysis to respectively determine the number of components in each local core region of the driving posture, and construct The local deformable part model of driving posture local core region detection; (3) construct the score model of the local deformable part model of driving posture local core region respectively, the calculation result of this model is used as the local feature vector of driving posture local core region; ( 4) Using serial fusion rules to construct local deformable part model fusion feature vectors of driver's attitude; (5) Using support vector machine based on RBF kernel to recognize driver's attitude. The invention can effectively detect and recognize the driving posture of the driver.

Description

Technical field: [0001] The invention relates to a driving posture recognition method based on fusion features of local deformable part models, belonging to the technical field of intelligent transportation. Background technique: [0002] In the field of intelligent traffic monitoring, effective real-time monitoring of drivers' driving behavior is an important measure to avoid traffic risks. Various studies have shown that driver error is the core factor of traffic accidents. Therefore, it is particularly important to detect and identify abnormal driving behaviors and attitudes at high speed and with high robustness. kind of challenge. [0003] Deformable Part Model (DPM) is a target detection model proposed by Felzenszwalb et al. The detection process is based on the window scanning method, and achieves scale invariance by constructing image pyramids. However, the global-based DPM driving posture recognition method contains a lot of redundant information when processing t...

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 & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/597G06F18/2411
Inventor 赵池航钱子晨赵敏慧何杰林盛梅
Owner SOUTHEAST UNIV