Video frequency objects recognition method and system based on supporting vectors machine

A technology of support vector machines and video objects, applied in character and pattern recognition, computer parts, instruments, etc., can solve the problems of no mention, and achieve the effect of satisfying recognition speed, fast calculation speed, and reliable computing performance.

Active Publication Date: 2008-03-12
HUAWEI TECH CO LTD
View PDF0 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0067] At present, the SVM algorithm is used in pattern recognition, regression estimation, probability density function estimation, etc. It shows many unique advantages in solving small sample, nonlinear and high-dimensional pattern recognition pro

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
  • Video frequency objects recognition method and system based on supporting vectors machine
  • Video frequency objects recognition method and system based on supporting vectors machine
  • Video frequency objects recognition method and system based on supporting vectors machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0110] FIG. 4 is a schematic flowchart of a video object recognition method based on a support vector machine according to an embodiment of the present invention. See Figure 4, the process includes:

[0111] Step 401, constructing training samples;

[0112] In this step, first determine the categories that need to be distinguished, such as: people, animals, cars, etc., then from the pre-stored training image library, you can also use other methods to obtain training images, and select a certain number of images containing this category for each category. The image of the object is shown in FIG. 5, which is a schematic diagram of training images pre-stored in the training image database according to the embodiment of the present invention. In this embodiment, about 300 images containing objects of this category are selected for each category.

[0113] Then, the selected training image is segmented, either by using an automatic segmentation method, or by combining automatic seg...

Embodiment 2

[0212] FIG. 12 is a schematic diagram of a recognition result of a video object recognition method based on a support vector machine according to Embodiment 2 of the present invention. Referring to FIG. 12 , in this embodiment, three video objects of people, animals and cars are classified respectively. According to the method flow of embodiment 1, at first, a training sample set is constructed for each video object, each training sample set contains about 100 training samples, and then each training image in the training sample is segmented, labeled, trained Sample generation, training sample outline feature extraction, and SVM model training, so as to obtain the required support vector machine recognition model, and use this model to recognize moving objects in the video.

[0213] The recognition results show that the recognition rate of the above three objects is above 97%, and the average recognition speed is 94ms, which can fully meet the needs of real-time monitoring.

Embodiment 3

[0215] FIG. 13 is a schematic diagram of the recognition rate of the support vector machine-based video object recognition method according to Embodiment 3 of the present invention. Referring to FIG. 13 , in the figure, the abscissa is the number of recognized objects, and the ordinate is the recognition rate (%). In this embodiment, the side of four-limbed animals, the side of a car, the standing posture of a person with legs together, the standing posture of a person with legs apart, the sitting posture of a person, the lying posture of a person, the bending posture of a person, the side of a person riding a bicycle, etc. Nine objects are recognized. It can be seen from FIG. 13 that with the increase of recognized objects, the recognition rate of Embodiment 3 of the present invention only slightly decreases, and the rate of decrease is very slow. The specific recognition rates for multiple objects are shown in Table 1.

[0216] Number of objects

2

3

...

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 video object identification method and a relevant system based on support vector machines; with structure training samples and according to resolution that is selected from the training samples, utilize a method combined with wavelet outline description symbol, shape factor and invariant torque, to describe outline characteristics of the training samples; gain a support vector machine model according to the outline characteristic training, and meanwhile, determine decision-making function parameters at the optimum category aspects in the support vector machine model; then, extract outline characteristics from the video object to be identified; the support vector machine model after training can follow the video object outline characteristics that is input, in order to perform category for the acquired video objects with a decision-making function operation for the optimum category face. The invention has advantages of high calculation speed, high identification accuracy, reliable arithmetic performance and multi-category identification; and moreover, with increase of objects to be identified, the identification performance can still be kept stable, and the identification speed can still meet real-time monitoring demands.

Description

technical field [0001] The invention relates to video object recognition technology, in particular to a video object recognition method and system based on a support vector machine. Background technique [0002] With the rapid growth of our country's economy and the continuous improvement of the level of science and technology, video security monitoring technology has become more and more common in people's life and work. In family life, this technology can be used to monitor family members (patients, the elderly, babies, etc.) In transportation, this technology can be used to conduct real-time supervision on automobiles, trains, subways and other means of transportation to eliminate various safety hazards and ensure the safety of people's travel; in public safety, it can be used to monitor large public places (railway stations, Subway stations, airports) to monitor to prevent the occurrence of vicious damage. Especially in today's frequent terrorist incidents and increasi...

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
IPC IPC(8): G06K9/62
Inventor 孔晓东罗青山曾贵华赵光耀
Owner HUAWEI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap