Title: Haar cascade-based deep learning model to predict in/out bound passenger flow and distance estimation for intelligent transport system

Authors: Vishnu Kumar Kaliappan; K.S. Gautam; M. Akila; K. Mohanasundaram

Addresses: Department of Computer Science and Engineering, KPR Institute of Engineering and Technology, Arasur, Coimbatore, 641047, Tamil Nadu, India ' Department of Information Science and Engineering, New Horizon College of Engineering, Bangalore, Karnataka, India ' Department of Computer Science and Engineering, KPR Institute of Engineering and Technology, Arasur, Coimbatore, 641047, Tamil Nadu, India ' Department of Electrical and Electronics Engineering, KPR Institute of Engineering and Technology, Arasur, Coimbatore, 641047, Tamil Nadu, India

Abstract: Managing crowd density in the transportation industry is still a research issue. One of the components of a smart city's intelligent transportation system (ITS) is the improvement of traffic efficiency. The ITS improves traffic congestion control by collecting real-time data. A dependable system capable of counting the number of passengers on a carrier is required for effective traffic congestion control. In this work, we present a unique approach named the intelligent centroid tracker and counter (ICTC) that could recognise, count, and compute the distances between people in a limited location. The proposed algorithm is vision-based, aiming to maximise congestion control inside passenger transportation systems. The algorithm collects data on population density in a public transit medium from commuters in each region, then delivers adequate transportation facilities to the general public. According to experimental investigation, the proposed approach operates on VISOR, Kaggle, CALTECH, Penn-Fudan, Daimler Mono, and INRIA with accuracy values of 0.81, 0.83, 0.85, 0.88, 0.82, and 0.89, respectively.

Keywords: deep learning; ITS; intelligent transportation system; Haar classifiers; passenger forecast; computer vision.

DOI: 10.1504/IJHVS.2024.137251

International Journal of Heavy Vehicle Systems, 2024 Vol.31 No.2, pp.210 - 221

Received: 10 Oct 2021
Accepted: 21 Jun 2022
Published online: 07 Mar 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article