Skip to main content
placeholder image

Real-time pedestrian lane detection for assistive navigation using neural architecture search

Conference Paper


Abstract


  • Pedestrian lane detection is a core component in many assistive and autonomous navigation systems. These systems are usually deployed in environments that require real-time processing. Many state-of-the-art deep neural networks only focus on detection accuracy but not inference speed. Without further modifications, they are not suitable for real-time applications. Furthermore, the task of designing a high-performing deep neural network is time-consuming and requires experience. To tackle these issues, we propose a neural architecture search algorithm that can find the best deep network for pedestrian lane detection automatically. The proposed method searches in a network-level space using the gradient descent algorithm. Evaluated on a dataset of 5,000 images, the deep network found by the proposed algorithm achieves comparable segmentation accuracy, while being significantly faster than other state-of-the-art methods. The proposed method has been successfully implemented as a real-time pedestrian lane detection tool.

Publication Date


  • 2020

Citation


  • Ang, S. P., Phung, S. L., Bouzerdoum, A., Nguyen, T. N. A., Duong, S. T. M., & Schira, M. M. (2020). Real-time pedestrian lane detection for assistive navigation using neural architecture search. In Proceedings - International Conference on Pattern Recognition (pp. 8392-8399). doi:10.1109/ICPR48806.2021.9412741

Scopus Eid


  • 2-s2.0-85110516074

Web Of Science Accession Number


Start Page


  • 8392

End Page


  • 8399

Abstract


  • Pedestrian lane detection is a core component in many assistive and autonomous navigation systems. These systems are usually deployed in environments that require real-time processing. Many state-of-the-art deep neural networks only focus on detection accuracy but not inference speed. Without further modifications, they are not suitable for real-time applications. Furthermore, the task of designing a high-performing deep neural network is time-consuming and requires experience. To tackle these issues, we propose a neural architecture search algorithm that can find the best deep network for pedestrian lane detection automatically. The proposed method searches in a network-level space using the gradient descent algorithm. Evaluated on a dataset of 5,000 images, the deep network found by the proposed algorithm achieves comparable segmentation accuracy, while being significantly faster than other state-of-the-art methods. The proposed method has been successfully implemented as a real-time pedestrian lane detection tool.

Publication Date


  • 2020

Citation


  • Ang, S. P., Phung, S. L., Bouzerdoum, A., Nguyen, T. N. A., Duong, S. T. M., & Schira, M. M. (2020). Real-time pedestrian lane detection for assistive navigation using neural architecture search. In Proceedings - International Conference on Pattern Recognition (pp. 8392-8399). doi:10.1109/ICPR48806.2021.9412741

Scopus Eid


  • 2-s2.0-85110516074

Web Of Science Accession Number


Start Page


  • 8392

End Page


  • 8399