Open Access

ARTICLE

HybridLSTM: An Innovative Method for Road Scene Categorization Employing Hybrid Features

Sanjay P. Pande¹, Sarika Khandelwal², Ganesh K. Yenurkar^3,*, Rakhi D. Wajgi³, Vincent O. Nyangaresi^4,5,*, Pratik R. Hajare⁶, Poonam T. Agarkar⁷

1 Department of Computer Science & Engineering, G H Raisoni University, Amravati, 444701, Maharashtra, India
2 Department of Computer Science & Engineering, G H Raisoni College of Engineering, Nagpur, 440016, Maharashtra, India
3 Department of Computer Technology, Yeshwantrao Chavan College of Engineering, Wanadongri, Nagpur, 441110, Maharashtra, India
4 Department of Computer Science and Software Engineering, Jaramogi Oginga Odinga University of Science & Technology, Bondo, 40601, Kenya
5 Department of Applied Electronics, Saveetha School of Engineering, SIMATS, Chennai, 602105, Tamilnadu, India
6 Department of Electrical and Electronics Engineering, Mansarovar Global University, Bhopal, 466001, Madhya Pradesh, India
7 School of Computer Science and Engineering, Ramdeobaba University, Nagpur, 440013, Maharashtra, India

* Corresponding Authors: Ganesh K. Yenurkar. Email: ; Vincent O. Nyangaresi. Email:

Computers, Materials & Continua 2025, 84(3), 5937-5975. https://doi.org/10.32604/cmc.2025.064505

Received 17 February 2025; Accepted 06 May 2025; Issue published 30 July 2025

Abstract

Recognizing road scene context from a single image remains a critical challenge for intelligent autonomous driving systems, particularly in dynamic and unstructured environments. While recent advancements in deep learning have significantly enhanced road scene classification, simultaneously achieving high accuracy, computational efficiency, and adaptability across diverse conditions continues to be difficult. To address these challenges, this study proposes HybridLSTM, a novel and efficient framework that integrates deep learning-based, object-based, and handcrafted feature extraction methods within a unified architecture. HybridLSTM is designed to classify four distinct road scene categories—crosswalk (CW), highway (HW), overpass/tunnel (OP/T), and parking (P)—by leveraging multiple publicly available datasets, including Places-365, BDD100K, LabelMe, and KITTI, thereby promoting domain generalization. The framework fuses object-level features extracted using YOLOv5 and VGG19, scene-level global representations obtained from a modified VGG19, and fine-grained texture features captured through eight handcrafted descriptors. This hybrid feature fusion enables the model to capture both semantic context and low-level visual cues, which are critical for robust scene understanding. To model spatial arrangements and latent sequential dependencies present even in static imagery, the combined features are processed through a Long Short-Term Memory (LSTM) network, allowing the extraction of discriminative patterns across heterogeneous feature spaces. Extensive experiments conducted on 2725 annotated road scene images, with an 80:20 training-to-testing split, validate the effectiveness of the proposed model. HybridLSTM achieves a classification accuracy of 96.3%, a precision of 95.8%, a recall of 96.1%, and an F1-score of 96.0%, outperforming several existing state-of-the-art methods. These results demonstrate the robustness, scalability, and generalization capability of HybridLSTM across varying environments and scene complexities. Moreover, the framework is optimized to balance classification performance with computational efficiency, making it highly suitable for real-time deployment in embedded autonomous driving systems. Future work will focus on extending the model to multi-class detection within a single frame and optimizing it further for edge-device deployments to reduce computational overhead in practical applications.

---

Keywords

---