Deep Neural Network for Structural Prediction and Lane Detection in Traffic Scene

By Jun Li, Xue Mei, Danil V. Prokhorov, Dacheng Tao. IEEE Transactions on Neural Networks and Learning Systems, 2017

377 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Automotive Engineering, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/23fe2ab6aa5f0a19e5dd6fabe1a589c8bcb67808

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Stamatios Georgoulis
2. In-So Kweon
3. Jian Yang
4. Humaira Arshad
5. Qin Zou
6. Baofu Wu
7. Luc Van Gool
8. Aman Bin Jantan

In Automotive Engineering

1. Qin Zou
2. Baofu Wu
3. Luc Van Gool
4. Long Chen
5. Sidi Lu
6. Ren Zhong
7. Xiaolin Hu
8. Qingyan Zhang

In Environmental Engineering

1. Qin Zou
2. Baofu Wu
3. Luc Van Gool
4. Qun Liu
5. Long Chen
6. Sidi Lu
7. Ren Zhong
8. Marc Proesmans

Citations in the corpus

• State-of-the-art in artificial neural network applications: A survey (2018, methodology): “The comparison was made based on (i) author(s)/year of publication (ii) ANN modeling (iii) ANN area of application (iii) studied contribution to human challenges (with references to Supplementary Table 2) [11, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, ”
• Line-CNN: End-to-End Traffic Line Detection With Line Proposal Unit (2020, methodology): “[44] combines multitask CNN and RNN to detect traffic line segments.”
• Computing Systems for Autonomous Driving: State of the Art and Challenges (2020, background): “learning shows promising performance in complex scenarios requiring interaction with other vehicles [28], [100].”
• Complete Random Forest Based Class Noise Filtering Learning for Improving the Generalizability of Classifiers (2019, methodology): “We used the transfer learning based on the deep conventional neural networks (DCNN) to extract the features of these sixteen image data sets [24].”
• Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks (2019, methodology): “3) ‘CNN+RNN’: Considering that road lane is continuous on the pavement, a method combining CNN and RNN was presented in [8].”
• VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition (2017, methodology): “[21] uses both a CNN and a Recurrent Neural Network (RNN) to detect lane boundaries.”
• Deep Hyperspectral Image Sharpening (2018, neutral): “Especially, convolutional neural network (CNN) with deep architecture is very effective to exploit image characteristics [23], [26]–[29].”
• Towards End-to-End Lane Detection: an Instance Segmentation Approach (2018, background): “[22] propose the use of a multi-task deep convolutional network that focuses on finding geometric lane attributes, such as location and orientation, together with a Recurrent Neural Network (RNN) that detects the lanes.”