Abstract
Vehicle detection is a key component of environmental sensing systems for Intelligent Vehicles (IVs). The traditional shallow model and offline learning-based vehicle detection method are not able to satisfy the real-world challenges of environmental complexity and scene dynamics. Focusing on these problems, this work proposes a vehicle detection algorithm based on a multiple feature subspace distribution deep model with online transfer learning. Based on the multiple feature subspace distribution hypothesis, a deep model is established in which multiple Restricted Boltzmann Machines (RBMs) construct the lower layers and a Deep Belief Network (DBN) composes the superstructure. For this deep model, an unsupervised feature extraction method is applied, which is based on sparse constraints. Then, a transfer learning method with online sample generation is proposed based on the deep model. Finally, the entire classifier is retrained online with supervised learning. The experiment is actuated using the KITTI road image datasets. The performance of the proposed method is compared with many state-of-the-art methods and it is demonstrated that the proposed deep transfer learning-based algorithm outperformed existing state-of-the-art methods.
Highlights
With rapid economic and technological progress, the development of modern transportation tools, such as transportation vehicles, satisfactorily facilitate the requirements of life and work
A corresponding deep model is established based on this assumption and a sparse constraint-based unsupervised feature extraction algorithm is developed
This work proposes a vehicle detection algorithm based on a multiple subspace feature distribution deep model with online transfer learning
Summary
With rapid economic and technological progress, the development of modern transportation tools, such as transportation vehicles, satisfactorily facilitate the requirements of life and work. The IV environmental perception layer obtains road environment information through different sensors to achieve detection and tracking of surrounding obstacles such as road structures, vehicles, pedestrians, road lanes, traffic signs, and traffic signals. It provides critical information for the decision planning and operation control layers. The deep learning framework induced in vehicle detection taskstasks in which a deep network based based on the on multiple independent feature is induced in vehicle detection in which a deep network the multiple independent subspace distribution assumption being established.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
