Citation :

Sadia Patka, Rahul Khokale, Mohammad Sharfoddin Khatib, "Intelligent Pathway Perception System using YOLO and Multi-Architecture Deep Learning for Obstacle and Floor Hazard Detection," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 10, pp. 319-338, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I10P123

Abstract

Independent and safe movement of the visually impaired people is a very urgent issue, especially in indoor areas, where the dynamic barriers and physical features like furniture, stairs and uneven surfaces are major hazards. The current assistive systems are usually concentrated on specific tasks, leading to a disjointed understanding of the environment and a lack of reliability. The proposed framework uses the YOLOv8 to detect obstacles in the indoor environment, then extracts features using parallel CNN and ResNet-50 and fuses them with an attention mechanism to get the surface of the pathway, which is helpful for context-aware perception. Training and evaluation are carried out on the selected categories of indoor objects from the Microsoft COCO dataset, derived from the task. The ResNet-50 model is initialized with ImageNet-pretrained weights, while pseudo-labels are introduced for surfaces to support surface inference by leveraging the COCO object-scene relationships in a weakly supervised manner. Therefore, it does not need an extra floor-hazard training data set, however, the feature initialization is based on the principle of transfer learning. The results of the experiments prove that APPF has a detection accuracy of 96.8%, a precision of 95.1% and, a recall of 94.3% and a mAP at 0.5 of 0.91 in object detection tasks. The context-aware surface inference module has an accuracy of classification of 95.5% and a false detection rate of 4.5%. Relative analysis with baseline CNN and single-stage detectors demonstrates 17.4% improvement in the detection performance and 36.5% decrease in the latency, maintaining real-time inference at 27 FPS. It is innovative in that it uses only the COCO dataset, but it allows dual-level perception to be done by architectural innovation and contextual learning to indoor settings.

Keywords

Assistive navigation systems, Object detection, Context-Aware surface inference, Deep learning for visual assistance, Obstacle detection for visually impaired.

References

1. David Ayemlo Esuga-Mopah et al., “Negative Obstacle Detection and Avoidance using YOLOv8 and Depth Profile Analysis for Autonomous Mobile Navigation,” Discover Applied Sciences, vol. 8, no. 3, pp. 1-20, 2026.
   [CrossRef] [Google Scholar] [Publisher Link] 
2. Carmen Gheorghe et al., “Analyzing Real-Time Object Detection with YOLO Algorithm in Automotive Applications: A Review,” Computer Modeling in Engineering and Science, vol. 141, no. 3, pp. 1939-1981, 2024.
   [CrossRef] [Google Scholar] [Publisher Link] 
3. Anupama V.P et al., “Redefining Mobility: Deep Learning-Assisted Obstacle Detection,” International Journal of Engineering Research and Technology, vol. 13, no. 5, pp. 1-5, 2024.
   [CrossRef] [Publisher Link] 
4. Afnan Ahmed Adil et al., “A Multi-Robot Collaborative Manipulation Framework for Dynamic and Obstacle-Dense Environments: Integration of Deep Learning for Real-Time Task Execution,” Frontiers in Robotics and AI, vol. 12, pp. 1-19, 2025.
   [CrossRef] [Google Scholar] [Publisher Link] 
5. Zhiwei Zheng, Jin Cheng, and Fanghua Jin, “TFP-YOLO: Obstacle and Traffic Sign Detection for Assisting Visually Impaired Pedestrians,” Sensors, vol. 25, no. 18, pp. 1-20, 2025.
   [CrossRef] [Google Scholar] [Publisher Link] 
6. Shalu et al., “An Intelligent Lane and Obstacle Detection using YOLO Algorithm,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 3s, pp. 641-648, 2023.
   [Google Scholar] [Publisher Link]
7. Khawla Almazrouei, Ibrahim Kamel, and Tamer Rabie, “Dynamic Obstacle Avoidance and Path Planning through Reinforcement Learning,” Applied Sciences, vol. 13, no. 14, pp. 1-20, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Giovanna Guaragnella et al., “Artificial Intelligence in Autonomous Mobile Robot Navigation: From Classical Approaches to Intelligent Adaptation,” Advanced Intelligent Systems, vol.  8, no. 5, pp. 1-26, 2026.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Mustufa Haider Abidi et al., “A Comprehensive Review of Navigation Systems for Visually Impaired Individuals,” Heliyon, vol. 10, no. 11, pp. 1-19, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
10. I. Komang Somawirata, Fitri Utaminingrum, and Ainandafiq Muhammad Alqadri, “Advanced Obstacle Detection based on YOLOv5 for Safer Navigation in Autonomous Smart Wheelchair,” Proceedings of the 2024 7^th International Conference on Artificial Intelligence and Pattern Recognition, Association for Computing Machinery, New York, United States, pp. 714-721, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Redhwan Algabri, and Mun-Taek Choi, “Deep-Learning-based Indoor Human Following of Mobile Robot using Color Feature,” Sensors, vol. 20, no. 9, pp. 1-19, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Aryanti Aryanti, Ming-Shyan Wang, and Muslikhin Muslikhin, “Navigating Unstructured Space: Deep Action Learning-based Obstacle Avoidance System for Indoor Automated Guided Vehicles,” Electronics, vol. 13, no. 2, pp. 1-22, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Sultan Daud Khan, and Kamal M. Othman, “Indoor Scene Classification through Dual-Stream Deep Learning: A Framework for Improved Scene Understanding in Robotics,” Computers, vol. 13, no. 5, pp. 1-20, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Chih-Hsiung Chang et al., “Indoor Safety Monitoring for Falls or Restricted Areas using Wi-Fi Channel State Information and Deep Learning Methods in Mega Building Construction Projects,” Sustainability, vol. 14, no. 22, pp. 1-20, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Iker Azurmendi et al., “Simultaneous Object Detection and Distance Estimation for Indoor Autonomous Vehicles,” Electronics, vol. 12, no. 23, pp. 1-18, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Yin Jia et al., “Deep-Learning-based Context-Aware Multi-Level Information Fusion Systems for Indoor Mobile Robots Safe Navigation,” Sensors, vol. 23, no. 4, pp. 1-13, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Rakesh Chandra Joshi et al., “Efficient Multi-Object Detection and Smart Navigation using Artificial Intelligence for Visually Impaired People,” Entropy, vol. 22, no. 9, pp. 1-17, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Wenming Zhu et al., “Design of Multimodal Obstacle Avoidance Algorithm based on Deep Reinforcement Learning,” Electronics, vol. 14, no. 1, pp. 1-20, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Samira Badrloo et al., “Image-based Obstacle Detection Methods for the Safe Navigation of Unmanned Vehicles: A Review,” Remote Sensing, vol. 14, no. 15, pp. 1-26, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Radu Păpară et al., “Testing of Indoor Obstacle-Detection Prototypes Designed for Visually Impaired Persons,” Applied Sciences, vol. 14, no. 5, pp. 1-23, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Husein Perez, Joseph H.M. Tah, and Amir Mosavi, “Deep Learning for Detecting Building Defects using Convolutional Neural Networks,” Sensors, vol. 19, no. 16, pp. 1-22, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Huu Thu Nguyen et al., “Multiple Object Detection based on Clustering and Deep Learning Methods,” Sensors, vol. 20, no. 16, pp. 1-14, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]