Enhanced pedestrian detection using optimized deep convolution neural network for smart building surveillance
- PDF / 2,259,588 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 86 Downloads / 274 Views
(0123456789().,-volV)(0123456789(). ,- volV)
METHODOLOGIES AND APPLICATION
Enhanced pedestrian detection using optimized deep convolution neural network for smart building surveillance Bubryur Kim1
•
N. Yuvaraj1
•
K. R. Sri Preethaa2
•
R. Santhosh3
•
A. Sabari4
Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Pedestrian detection and tracking is a critical task in the area of smart building surveillance. Due to advancements in sensors, the architects concentrate in construction of smart buildings. Pedestrian detection in smart building is greatly challenged by the image noises by various external environmental parameters. Traditional filter-based techniques for image classification like histogram of oriented gradients filters and machine learning algorithms suffer to perform well for huge volume of pedestrian input images. The advancements in deep learning algorithms perform exponentially good in handling the huge volume of image data. The current study proposes a pedestrian detection model based on deep convolution neural network (CNN) for classification of pedestrians from the input images. Proposed optimized version of VGG-16 architecture is evaluated for pedestrian detection on the INRIA benchmarking dataset consisting of 227 9 227 pixel images. The proposed model achieves an accuracy of 98.5%. It was found that proposed model performs better than the other pretrained CNN architectures and other machine learning models. Pedestrians are reasonably detected and the performance of the proposed algorithm is validated. Keywords Pedestrian detection Deep learning Convolution neural network Machine learning
1 Introduction
Communicated by V. Loia. & K. R. Sri Preethaa [email protected] Bubryur Kim [email protected] N. Yuvaraj [email protected] R. Santhosh [email protected] A. Sabari [email protected] 1
Department of Architectural Engineering, Kyungil University, Gyeongbuk, South Korea
2
Department of CSE, KPR Institute of Engineering and Technology, Coimbatore, India
3
Department of CSE, Faculty of Engineering, Karpagam Academy of Higher Education, Coimbatore, India
4
Department of IT, K S Rangasamy College of Technology, Tiruchengode, India
In recent years, researches are focused on imparting artificial intelligence to machines for many activities that does not involve humans. It includes object detection, animal tracking, weather forecasting, surveillance, civil structural health monitoring and so on. Smart buildings surveillance includes identification of suspicious objects and activity. Smart buildings integrate sensor technology and the IoT processing to provide solutions in overall building management. The biggest automotive and IT companies draws attention in investing huge money on autonomous selfdriving cars (Shen et al. 2019). They also involved in development of machines and applications for human– machine interaction. (Wu and Rehg 2011; Gall and Lempitsky 2013; Majaranta and Bulling 2014; Rautaray and Agrawal 2015; Boudjit and Larbes 2015; Rho
Data Loading...
