Abstract
Scene recognition is an essential part in the vision-based robot navigation domain. The successful application of deep learning technology has triggered more extensive preliminary studies on scene recognition, which all use extracted features from networks that are trained for recognition tasks. In the paper, we interpret scene recognition as a region-based image retrieval problem and present a novel approach for scene recognition with an end-to-end trainable Multi-column convolutional neural network (MCNN) architecture. The proposed MCNN utilizes filters with receptive fields of different sizes to have Multi-level and Multi-layer image perception, and consists of three components: front-end, middle-end and back-end. The first seven layers VGG16 are taken as front-end for two-dimensional feature extraction, Inception-A is taken as the middle-end for deeper learning feature representation, and Large-Margin Softmax Loss (L-Softmax) is taken as the back-end for enhancing intra-class compactness and inter-class-separability. Extensive experiments have been conducted to evaluate the performance according to compare our proposed network to existing state-of-the-art methods. Experimental results on three popular datasets demonstrate the robustness and accuracy of our approach. To the best of our knowledge, the presented approach has not been applied for the scene recognition in literature.
Highlights
With the rapid development of machine learning and artificial intelligence, the application of visual robots has attracted wide attention [1,2]
Visual robots are applied in the field of autonomous navigation, that is motivated by promising application in future autonomous driving
We proposed a novel approach for scene recognition with an end-to-end trainable multiproposed a novel approach for scene recognition with an end-to-end trainable multi-column Convolutional Neural Networks (CNNs)
Summary
With the rapid development of machine learning and artificial intelligence, the application of visual robots has attracted wide attention [1,2]. Many algorithms have been applied to scene recognition [4,5,6,7], and one of the most popular are Convolutional Neural Networks (CNNs). CNNs are a deep learning method specially designed for image classification and image recognition based on multi-layer neural network. Due to the limitation of spatial structure and computational consumption, the traditional multi-layer neural network cannot meet the basic needs of robot navigation, the emergence of CNNs effectively solves these problems. Traditional neural networks, object detection and scene recognition. The architecture as shown in in Figure inin a Figure 2 This network network utilizes utilizes filter filterof ofdifferent differentsize sizetotodeal dealwith withthe thescale scaleand andviewpoint viewpointchange change complex environment, as well as has a strong ability of multi-level and multi-layer scene perception. Loss becomes more discriminating, which is helpful to distinguish the different scenes information
Sign-in/Register to view highlights & summary 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.
