Comparative Analysis of Visual Positioning Techniques for Indoor Navigation Systems


  • Ritesh Kumar Jain Assistant Professor, Department of Computer Science and Engineering, Geetanjali Institute of Technical Studies, Udaipur, Rajasthan, India
  • Dr. Vishnu Agarwal Associate Professor, Department of Mechanical Engineering, Geetanjali Institute of Technical Studies, Udaipur, Rajasthan, India



VPS, Visual, Positioning, SLAM, Object Based


Indoor navigation is a significant challenge that requires specialized positioning systems due to the limitations of GPS in indoor environments. Visual Positioning Systems (VPS) have emerged as a promising solution to address this challenge, but the selection and optimization of appropriate visual positioning techniques pose significant challenges. To provide a comprehensive understanding of this research problem, it is essential to examine the existing literature on indoor navigation systems, including the challenges, limitations, and opportunities associated with VPS. A detailed discussion of the specific research objectives would also be helpful in framing the research problem. Therefore, the research objectives of this paper are to compare and evaluate different visual positioning techniques for indoor navigation based on various performance metrics such as positioning accuracy, computational complexity, and power consumption. The paper aims to provide insights into the advantages and limitations of these techniques, identify key challenges in implementing them, and propose potential solutions to overcome these challenges. Furthermore, the paper will explore the potential applications of VPS in indoor navigation beyond traditional environments such as hospitals, airports, and shopping malls. These applications could include robotic navigation, augmented reality, and autonomous vehicles. By achieving these research objectives, this paper aims to contribute to the field of indoor navigation and VPS by providing a comprehensive analysis of different visual positioning techniques and identifying the key challenges in their implementation. This knowledge could be beneficial to researchers, developers, and stakeholders in developing more accurate, efficient, and reliable indoor navigation systems.


J. Huang, J. Qin, H. Xie, and X. Wang, “Comparative analysis of visual SLAM algorithms for indoor navigation,” Sensors, Vol. 21, No. 1, p. 241, 2021.

C. Z. Guo, Z. Z. Liu, and L. F. Tian, “A feature-based localization method for indoor navigation using visual and inertial sensors,” IEEE Sensors Journal, Vol. 20, No. 19, pp. 11254-11264, 2020.

X. Sun, J. Zhang, X. Yang, and J. Zhu, “Object recognition-based indoor localization using convolutional neural network,” IEEE Transactions on Vehicular Technology, Vol. 69, No. 5, pp. 5148-5158, 2020.

X. Wang, M. Sun, H. Zhang, Z. Li, and Y. Liu, “Deep learning-based visual odometry with gradient descent optimization,” IEEE Access, Vol. 7, pp. 53016-53025, 2019.

S. S. Saha, S. Dutta, S. Paul, and S. K. Bandyopadhyay, “Indoor augmented reality: a visual positioning system approach,” Journal of Ambient Intelligence and Humanized Computing, Vol. 11, No. 6, pp. 2215-2228, 2020.

T. H. Le, H. K. Kim, and T. T. Nguyen, “Indoor air quality monitoring system based on visual SLAM,” Sensors, Vol. 19, No. 9, p. 1982, 2019.

X. Hu, H. Li, Y. Guo, Y. Wang, and X. Li, “A Novel Feature detection and tracking algorithm for visual positioning system based on human visual system,” IEEE Access, Vol. 8, pp. 145330-145339, 2020.

J. Zhang, Y. Guo, X. Yang, and Y. Wang, “An indoor positioning system based on visual SLAM and LiDAR mapping,” Sensors, Vol. 19, No. 17, p. 3687, 2019.

Y. Zheng, Y. Guo, and Y. Wang, “An improved indoor positioning system based on visual SLAM and beacon fusion,” IEEE Access, Vol. 8, pp. 90798-90806, 2020.

X. Ma, J. Luo, J. Chen, and Z. Chen, “An indoor navigation system for the visually impaired based on visual SLAM and audio feedback,” IEEE Access, Vol. 8, pp. 197192-197202, 2020.

Y. Li and K. J. Kim, “A review of visual positioning systems: Vision-based navigation and localization for indoor and outdoor applications,” IEEE Access, Vol. 7, pp. 175060-175082, 2019.

H. Zhang, Y. Wang and J. Yang, “Deep learning-based visual positioning system: A survey,” Journal of Visual Communication and Image Representation, Vol. 75, pp. 103116, 2021.

H. Zhang, Z. Li and Y. Wang, “A robust visual positioning system using deep learning and geometric constraints,” IEEE Transactions on Industrial Informatics, Vol. 16, No. 6, pp. 4176-4185, 2020.

J. Lin, J. Sun and R. Li, “A visual positioning system based on image feature extraction and deep learning,” IEEE Access, Vol. 9, pp. 18378-18389, 2021.

Q. Hu, Z. Yang and S. Wang, “Deep learning for visual positioning: A survey,” Neurocomputing, Vol. 307, pp. 135-153, 2018.




How to Cite

Jain, R. K., & Agarwal, V. (2023). Comparative Analysis of Visual Positioning Techniques for Indoor Navigation Systems. Asian Journal of Engineering and Applied Technology, 12(1), 18–22.