Abstract
With the development of society, intelligent urban construction is drawing attention globally. It embed sensors and equipment into various environmental monitoring target objects to achieve environmental management and decision-making wisdom in a more granular and dynamic manner. However, how to achieve target objects’ recognition in the dynamic environment is of essential importance for intelligent urban construction. Due to the shape, color and other characteristics for target objects are more similar, which make it difficult to identify the target types based on the low-level features such as color, shape, etc. In this paper, we attempt to apply the deep neural network composed of sparse autoencoders based unsupervised feature learning to identify the various types of target objects. On the other hand, due to the fact that the quantities of target objects which are obtained by environmental monitor may be not sufficient, cannot get more high-level visual feature through feature training, which affects the accuracy of the subsequent target recognition. A cross-domain feature learning scheme for target objects recognition using convolutional sparse auto-encoder has been presented. In order to improve the recognition speed, feature weights selection method based on a correlation analysis is further proposed for the purpose of reducing the amount of global features which are taken from target-domain images. Experimental results show that compared with non-transfer feature learning algorithm and underlying visual feature recognition algorithm, the new algorithm proposed in this paper has higher accuracy and robustness. Feature selection can reduce the computational time of global feature extraction and recognition by about 30% while improving recognition performance.
Highlights
As the Internet of Things and big data has been developed rapidly, the pace of intelligent urban construction has been promoted [1]–[3]
The innovations of this paper are as follows: 1) The deep neural network model composed of sparse autoencoder based unsupervised feature learning, convolutional neural network and classifier is used to identify the various types of target objects in intelligent urban; 2) A transferlearning feature learning scheme using SAE model has been presented to overcome the limitation of small amount of training data; 3) Since feature weights learned by SAE are irrelevant or redundant, feature weights selection based on correlation analysis method is proposed to reduce the computational complexity of global feature extraction based on Convolutional Neural Network model (CNN), and the time required for target objetcs recognition is reduced while the recognition performance has not be decreased
1) TRANSFER LEARNING CONVOLUTIONAL SAE BASED METHODS From the experimental results mentioned above in Section 3.2, it can be inferred that the traditional lower layer visualizing feature extraction methods, such as Color histogram, Generalized Search Trees (GIST), Local Binary Patterns (LBP), and multiple low-level visual features extraction combined is worse than the recognition performance by using both non-transfer and transfer learning based on the convolutional SAE model, which proves that Convolutional SAE can be used for the recognition of target objects
Summary
As the Internet of Things and big data has been developed rapidly, the pace of intelligent urban construction has been promoted [1]–[3]. The innovations of this paper are as follows: 1) The deep neural network model composed of sparse autoencoder based unsupervised feature learning, convolutional neural network and classifier is used to identify the various types of target objects in intelligent urban; 2) A transferlearning feature learning scheme using SAE model has been presented to overcome the limitation of small amount of training data; 3) Since feature weights learned by SAE are irrelevant or redundant, feature weights selection based on correlation analysis method is proposed to reduce the computational complexity of global feature extraction based on CNN, and the time required for target objetcs recognition is reduced while the recognition performance has not be decreased.
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.
