Open Access

ARTICLE

A Region-Aware Deep Learning Model for Dual-Subject Gait Recognition in Occluded Surveillance Scenarios

Zeeshan Ali¹, Jihoon Moon², Saira Gillani³, Sitara Afzal⁴, Maryam Bukhari⁵, Seungmin Rho^6,*

1 Research and Development Setups, National University of Computer and Emerging Sciences, Islamabad, 44000, Pakistan
2 Department of Data Science, Duksung Women’s University, Seoul, 01369, Republic of Korea
3 Faculty of Information Technology and Computer Science, University of Central Punjab, Lahore, 54590, Pakistan
4 Department of Software, Sejong University, Seoul, 05006, Republic of Korea
5 Department of Computer Science, COMSATS University Islamabad, Attock Campus, Attock, 43600, Pakistan
6 Department of Industrial Security, Chung-Ang University, Seoul, 06974, Republic of Korea

* Corresponding Author: Seungmin Rho. Email:

(This article belongs to the Special Issue: Advanced Image Segmentation and Object Detection: Innovations, Challenges, and Applications)

Computer Modeling in Engineering & Sciences 2025, 144(2), 2263-2286. https://doi.org/10.32604/cmes.2025.067743

Received 11 May 2025; Accepted 08 August 2025; Issue published 31 August 2025

Abstract

Surveillance systems can take various forms, but gait-based surveillance is emerging as a powerful approach due to its ability to identify individuals without requiring their cooperation. In the existing studies, several approaches have been suggested for gait recognition; nevertheless, the performance of existing systems is often degraded in real-world conditions due to covariate factors such as occlusions, clothing changes, walking speed, and varying camera viewpoints. Furthermore, most existing research focuses on single-person gait recognition; however, counting, tracking, detecting, and recognizing individuals in dual-subject settings with occlusions remains a challenging task. Therefore, this research proposed a variant of an automated gait model for occluded dual-subject walk scenarios. More precisely, in the proposed method, we have designed a deep learning (DL)-based dual-subject gait model (DSG) involving three modules. The first module handles silhouette segmentation, localization, and counting (SLC) using Mask-RCNN with MobileNetV2. The next stage uses a Convolutional block attention module (CBAM)-based Siamese network for frame-level tracking with a modified gallery setting. Following the last, gait recognition based on region-based deep learning is proposed for dual-subject gait recognition. The proposed method, tested on Shri Mata Vaishno Devi University (SMVDU)-Multi-Gait and Single-Gait datasets, shows strong performance with 94.00% segmentation, 58.36% tracking, and 63.04% gait recognition accuracy in dual-subject walk scenarios.

---

Keywords

---