Traffic Sign Recognition in Harsh Environment Using Attention Based Convolutional Pooling Neural Network
- Authors
- Chung, Jun Ho; Kim, Dong Won; Kang, Tae Koo; Lim, Myo Taeg
- Issue Date
- 6월-2020
- Publisher
- SPRINGER
- Keywords
- Convolutional neural network; Traffic sign recognition; Attention mechanism; Max pooling; Convolutional pooling
- Citation
- NEURAL PROCESSING LETTERS, v.51, no.3, pp.2551 - 2573
- Indexed
- SCIE
SCOPUS
- Journal Title
- NEURAL PROCESSING LETTERS
- Volume
- 51
- Number
- 3
- Start Page
- 2551
- End Page
- 2573
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/55417
- DOI
- 10.1007/s11063-020-10211-0
- ISSN
- 1370-4621
- Abstract
- Convolutional neural networks (CNNs) have achieved significant progress in computer vision systems, helping to efficiently obtain feature information by sliding filters on the input images. However, CNNs have difficulty capturing specific properties when the images are affected by various noises. This paper proposes an attention based convolutional pooling neural network (ACPNN) where an attention-mechanism is applied to feature maps to obtain key features, and max pooling is replaced with convolutional pooling to improve recognition accuracy in harsh environments. The ACPNN with attention mechanism and convolutional pooling structure is robust against external noises and maintains classification performance under such conditions. The proposed ACPNN was validated on the German traffic sign recognition benchmark with various cases. Considering the traffic signs are suffered from various noises, the recognition performances were demonstrated with conventional CNN and state-of-the art CNNs such as multi-scale CNN, committee of CNN, hierarchical CNN, and multi-column deep neural network. Under such harsh conditions, the proposed ACPNN shows 66.981% and 83.198% respectively, which are the best performances compared to other CNNs.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.