A Novel Visual Measurement Framework for Land Vehicle Positioning Based on Multimodule Cascaded Deep Neural Network

• Published in: IEEE transactions on industrial informatics Vol. 17; no. 4; pp. 2347 - 2356
• Main Authors: Zheng, Zhiyong, Li, Xu, Sun, Zhengliang, Song, Xiang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.04.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Estimation; Extended Kalman filter; Eye (anatomy); Feature extraction; Global Positioning System; Lateral position; Micromechanical devices; multimodule cascaded deep neural network (MMC-DNN); Neural networks; Position measurement; Roads; Urban environments; vehicle positioning; visual measurement; Visualization; Yaw; yaw angle
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2020.2998107

This article proposes a novel visual measurement framework, multimodule cascaded deep neural network (MMC-DNN), to achieve accurate, reliable, and cost-effective vehicle positioning in complex urban environments. The MMC-DNN is inspired by the mechanism of the human eyes' lateral positioning, which consists of three modules called siamesed fully convolutional network (S-FCN), skip-connection fully convolutional autoencoder (SC-FCAE), and multitask neural network regressor (MT-NNR), respectively. The S-FCN is first designed to accurately detect the road area. Then, the segmented road was executed inverse perspective mapping and the result is fed to the developed SC-FCAE for extracting equivalent positioning features. Furthermore, the MT-NNR is proposed to efficiently estimate lateral position and yaw angle with the help of a road map. Based on the estimation results, the MEMS INS/GPS integration is significantly augmented by extended Kalman filter. Experimental results validate the effectiveness of the proposed framework in enhancing positioning performance.