Model identification method based on video Fisher vector descriptors

Abstract

The invention discloses a model identification method based on video Fisher vector descriptors. The method comprises the following steps: first of all, tacking a vehicle for training, tracking an image of each model in a video, and extracting an SIFT characteristic of each frame of the image of the model; then, performing Fisher vector coding calculation on all the SIFT characteristics of the model image; then performing PCA dimension reduction on obtained Fisher vector descriptors; then performing binarization on the descriptors after the dimension reduction to obtain the video Fisher vector descriptors of the model; performing SVM training on all the obtained descriptors to obtain an identification system with N model types; and for a vehicle video for testing, extracting the video Fisher vector descriptors of the vehicle video, introducing the video Fisher vector descriptors into a well trained SVM classifier for the testing, and identifying the model of the test vehicle video.

Description

technical field [0001] The invention belongs to the technical field of pattern classification, in particular to a method for identifying vehicle types based on video Fisher vector descriptors. Background technique [0002] In the past 10 years, China's road transportation infrastructure has made great achievements and continues to develop at a high speed. With the rapid growth of the national economy and the continuous deepening of China's urbanization process, the number of vehicles in China has increased rapidly, which has brought enormous pressure to the environment and brought many problems to urban development and economic growth. In general, China's road transportation industry is facing the following challenges: (1) The ever-expanding population size and the continuous and rapid growth of the number of cars have increased the pressure on road traffic; (2) The energy consumption of road transportation is huge, and energy Insufficient utilization; (3) high incidence of...

AI Technical Summary

Problems solved by technology

Relatively mature technologies include loop coil detection, excitation infrared detection, ultrasonic / microwave detection, geomagnetic detection, etc., but these methods have their own advantages and disadvantages. The advantage is that the recognition accuracy is relatively high, but the disadvantages are also obvious. The main disadvantages are construction and The installation process is very complicated, affecting the normal traffic order, difficult to maintain, easy to damage the main equipment, costly, etc.

Images