Lane Image Detection Based on Convolution Neural Network Multi-Task Learning

Based on deep neural network multi-task learning technology, lane image detection is studied to improve the application level of driverless technology, improve assisted driving technology and reduce traffic accidents. The lane line database published by Caltech and Tucson company is used to extract the ROI (Region of Interest), scale, and inverse perspective transformation as well as to preprocess the image, so as to enrich the data set and improve the efficiency of the algorithm. In this study, ZFNet is used to replace the basic networks of VPGNet, and their structures are changed to improve the detection efficiency. Multi-label classification, grid box regression and object mask are used as three task modules to build a multi-task learning network named ZF-VPGNet. Considering that neural networks will be combined with embedded systems in the future, the network will be compressed to CZF-VPGNet without excessively affecting the accuracy. Experimental results show that the vision system of driverless technology in this study achieved good test results. In the case of fuzzy lane line and missing lane line mark, the improved algorithm can still detect and obtain the correct results, and achieves high accuracy and robustness. CZF-VPGNet can achieve high real-time performance (26FPS), and a single forward pass takes about 36 ms or less.

[1]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[2]  Mohammad Mahdi Bejani,et al.  Regularized Deep Networks in Intelligent Transportation Systems: A Taxonomy and a Case Study , 2019, ArXiv.

[3]  Pritee Parwekar,et al.  An improved and low-complexity neural network model for curved lane detection of autonomous driving system , 2021, Soft Computing.

[4]  A. Prabhu Chakkaravarthy,et al.  An Automatic Threshold Segmentation and Mining Optimum Credential Features by Using HSV Model , 2019 .

[5]  Mehdi Ghatee,et al.  A systematic review on overfitting control in shallow and deep neural networks , 2021, Artificial Intelligence Review.

[6]  Niall O' Mahony,et al.  Deep Learning vs. Traditional Computer Vision , 2019, CVC.

[7]  Hyunsoo Yoon,et al.  Random Untargeted Adversarial Example on Deep Neural Network , 2018, Symmetry.

[8]  Rosli Besar,et al.  Advances in lane marking detection algorithms for all-weather conditions , 2021 .

[9]  Carmen Vaca,et al.  Sign-regularized Multi-task Learning , 2021, ArXiv.

[10]  Yongseob Lim,et al.  An Urban Autodriving Algorithm Based on a Sensor-Weighted Integration Field with Deep Learning , 2020 .

[11]  Weidong Cao,et al.  A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods , 2020, Applied Sciences.

[12]  Ying Wang,et al.  A lane detection network based on IBN and attention , 2019, Multimedia Tools and Applications.

[13]  Fan Fan,et al.  A Robust Infrared Small Target Detection Algorithm Based on Human Visual System , 2014, IEEE Geoscience and Remote Sensing Letters.

[14]  Peng Liu,et al.  A review of lane detection methods based on deep learning , 2021, Pattern Recognit..

[15]  Mohamed Aly,et al.  Real time detection of lane markers in urban streets , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[16]  Sheng Liu,et al.  Lane departure warning systems and lane line detection methods based on image processing and semantic segmentation: A review , 2020 .

[17]  Degui Xiao,et al.  Attention deep neural network for lane marking detection , 2020, Knowl. Based Syst..