A Multi-Gaussian Model-Based Moped Detection Method
A multi-Gaussian model, Gaussian model technology, applied in the field of intelligent transportation, can solve problems such as unreasonable, ununiversal, camera orientation and far and near effects
Active Publication Date: 2016-03-09
UNIV OF SCI & TECH OF CHINA
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Documents [9][10] propose to extract simple features such as the shape and speed of moving objects, and use thresholding methods to identify mopeds, but these features are also affected by the orientation and distance of the camera.
Therefore, this type of method is not universal, and different thresholds must be artificially selected for different videos; even for the same video, it is unreasonable to use the same thresholding method to identify mopeds in various places
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
[0056] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
[0057] 1. Learning the scene model
[0058] The invention realizes the recognition of the moped by extracting the appearance feature and the motion feature of the moving object. The size and speed of the moving object are two very important features, but they vary with the camera angle and distance from the camera. Therefore, at different pixel points, this method establishes two sets of Gaussian models to reflect the size and velocity distribution of different types of moving objects.
[0059] The first set of Gaussian models consists of three Gaussian models describing the size distributions of cars, mopeds, and pedestrians, respectively. According to the size of the moving object, it is easy to distinguish the cars. So the second set of Gaussian models consists of two Gaussian models representing the velocity distributions of mopeds and p...
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 provides a moped detection method based on multiple Gaussian models. According to the method, mopeds are recognized by extracting external characteristics and motion characteristics of moving objects. The size and the speed of the moving objects are two important characteristics, but the size and the speed vary along with changes of the angle and the distance of cameras. Therefore, two groups of Gaussian models are established at different pixels to reflect size and speed distribution of different kinds of motion objects. According to the method, recognition of the mopeds can still be performed when the video quality is not high and the motion objects are not large enough. The method is high in universality due to classification threshold self-adaption and low in false detection rate due to the fact that the uniform classification threshold is not adopted. A majority principle is used twice, so that interference of errors and random factors to model establishment can be suppressed.
Description
technical field [0001] The invention belongs to the fields of intelligent transportation and pattern recognition, in particular to a detection method for a moped based on a multi-Gaussian model. Background technique [0002] There are many players in the transportation system, including pedestrians, cars and mopeds (bicycles and electric vehicles). Among them, the moped has become the most common means of travel, all over the streets and alleys of China. Unfortunately, mopeds have become one of the main causes of traffic accidents. According to statistics, a total of 1,840,998 traffic accidents related to mopeds occurred in 2011, causing a total loss of up to 440 million yuan (see literature [1]). Therefore, it is very necessary to detect mopeds in the intelligent traffic monitoring system, which will have positive significance for accident prevention and post-accident treatment. [0003] In recent years, there have been many studies on moped detection. Literature [2] an...
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): G06K9/00G06K9/66
Inventor 凌强严金丰张逸成李峰徐理想
Owner UNIV OF SCI & TECH OF CHINA