Driving behaviour recognition based on orientation and position deviations
| Autor: | Xiaozheng He, Guoce Zhang, Wei Sun, Zhang Xu, Xiaorui Zhang |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
050210 logistics & transportation
Orientation (computer vision) Computer science business.industry Computer Networks and Communications 05 social sciences Kalman filter 010501 environmental sciences Linear discriminant analysis 01 natural sciences Hough transform law.invention Computer Science Applications Position (vector) law Control and Systems Engineering 0502 economics and business Computer vision Segmentation Artificial intelligence Polar coordinate system Vanishing point Electrical and Electronic Engineering business 0105 earth and related environmental sciences |
| Zdroj: | International Journal of Sensor Networks. 30:161 |
| ISSN: | 1748-1287 1748-1279 |
| DOI: | 10.1504/ijsnet.2019.100219 |
| Popis: | This paper proposes a driving behaviour recognition method, which applies vehicle orientation and position deviations to warn the driver against possible dangers. We integrate a gradient reinforcement method based on the linear discriminate analysis (LDA) to reinforce lane edges. An improved Canny operator based on adaptive threshold segmentation is exploited to extract the lane edges reliably. Based on an improved Hough transform algorithm, the reinforced lane edges help the detection of polar angle and polar radius of lanes that are used to calculate the vanishing point position. After that, the proposed method predicts current-frame lane parameters based on the previous-frame parameters through using the Kalman filter. Combining deviation angle and deviation distance, the proposed method categorises vehicle lane-keeping behaviour into three states: normal, left deviation, and right deviation. Experimental results of a variety of travelling scenes show that the proposed method outperforms other existing methods in precision. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|