Fine-Tuned Residual Network-Based Features With Latent Variable Support Vector Machine-Based Optimal Scene Classification Model for Unmanned Aerial Vehicles

IEEE Access

卷:8

Manju Khari¹  K. Shankar²  Gyanendra Prasad Joshi³  A. Ramachandran⁴  Aghila Rajagopal⁵  Yongju Lee⁶  Sudan Jha⁷ 

[1] Computer Science Department, Ambedkar Institute of Technology, New Delhi, India;

[2] Department of Computer Applications, Alagappa University, Karaikudi, India;

[3] Department of Computer Science and Engineering, Sejong University, Seoul, South Korea;

[4] Department of Computer Science and Engineering, University College of Engineering Panruti, Panruti, India;

[5] Department of IT, Sethu Institute of Technology, Virudhunagar, India;

[6] School of Computer Science and Engineering, Kyungpook National University, Daegu, South Korea;

[7] School of Computer Science and Engineering, Lovely Professional University, Phagwara, India;

关键词: CNN;    Harmony Search;    LVSVM;    residual network-based features extraction;    RNBFE;    scene classification;   

DOI  :  10.1109/ACCESS.2020.3004233

来源: DOAJ

【 摘 要 】

In recent days, unmanned aerial vehicles (UAVs) becomes more familiar because of its versatility, automation abilities, and low cost. Dynamic scene classification gained significant interest among the UAV-based surveillance systems, e.g., high-voltage power line and forest fire monitoring, which facilitate the object detection, tracking process and drastically enhances the outcome of visual surveillance. This paper proposes a new optimal deep learning-based scene classification model captured by UAVs. The proposed model involves a residual network-based features extraction (RNBFE) which extracts features from the diverse convolution layers of a deep residual network. In addition, the several parameters in RNBFE lead to many configuration errors due to manual parameter tuning. So, self-adaptive global best harmony search (SGHS) algorithm is employed for tuning the parameters of the RNBFE. The resultant feature vectors undergo classification by the use of latent variable support vector machine (LVSVM) model. The presented optimal RNBFE (ORNBFE) model has been tested using two open access datasets namely UC Merced (UCM) Land Use Dataset and WHU-RS Dataset. The presented technique attains maximum scene classification accuracy over the other recently proposed methods.

【 授权许可】

Unknown