Vision based Indoor Localization Method via Convolution Neural Network

Zeyad Farisi, Lianfang Tian, Xiang‐Yang Li, Bin ZhuInternational Journal of Advanced Computer Science and Applications 2019 · DOI

Abstract

Existing indoor localization methods face significant constraints, including multipath effects in Wi-Fi, high costs for ultra-wide-band (UWB), and poor anti-interference for Bluetooth. To address these, we propose a vision-based indoor localization method. The environment is divided into regions, each with a location center. In offline mode, a VGG16 network is pre-trained on ImageNet and fine-tuned on a custom indoor dataset. In online mode, the converged network processes a mobile robot's RGB video stream to extract location-specific features, which are then classified by an ArcFace classifier. Experimental results demonstrate that this method accurately estimates locations in cluttered, unstructured scenes with 94.7% accuracy without additional hardware.

Introduction

Indoor localization is a notoriously difficult problem. While GPS is the standard for outdoor positioning, indoor environments obstruct satellite signals. Traditional workarounds like Wi-Fi fingerprinting or Bluetooth beacons are prone to signal bouncing (multipath effects) and interference. High-precision alternatives like UWB are often cost-prohibitive for large-scale deployment. Furthermore, traditional computer vision approaches often struggle with "visual aliasing," where different parts of a building look nearly identical.

This research introduces a low-cost, robust system requiring only a standard RGB camera. By treating localization as a feature-matching problem similar to facial recognition, the system achieves high reliability in complex industrial environments.

Methodology

The proposed pipeline utilizes transfer learning and advanced classification to turn visual data into spatial coordinates.

The proposed vision-based indoor localization pipeline, from pre-training to real-time classification.

Feature Extraction and Transfer Learning

Rather than training a model from scratch, the system uses a VGG16 architecture pre-trained on ImageNet. The first 13 convolutional layers are fine-tuned using a custom dataset of indoor images. This allows the model to retain general visual recognition capabilities while specializing in the specific architectural features of the target environment.

The ArcFace Classifier

A key innovation of this method is the replacement of the standard Softmax classifier with ArcFace (Additive Angular Margin Loss). While Softmax is effective for distinct object classes, it can struggle with the subtle differences between similar-looking rooms. ArcFace forces the network to learn more "compact" features for the same location and creates a wider angular margin between different locations, significantly improving discriminative power.

Comparison of decision boundaries: ArcFace provides a clearer angular margin compared to standard Softmax.

Experimental Setup and Results

The system was tested in an industrial warehouse environment divided into nine distinct regions. The custom dataset included 100 training images and 21 testing images per location, captured at various angles to ensure orientation robustness.

  • High Accuracy: The system achieved a peak localization accuracy of 94.7%.
  • Classifier Performance: The ArcFace method outperformed the standard Softmax classifier by 3.7%.
  • Efficiency: Through transfer learning, the model reached convergence in just 35 epochs with a training loss of 0.03.

Conclusion

This vision-based approach provides a high-accuracy, infrastructure-free solution for indoor robot navigation. By leveraging the discriminative power of ArcFace, the system effectively handles visual aliasing in cluttered scenes. Future work will focus on improving robustness against dynamic obstacles (such as humans blocking the camera view) and scaling the system to larger, more complex industrial complexes.

Summary updated

Abstract

Existing indoor localization methods have bottleneck constraints such as multipath effect for Wi-Fi based methods, high cost for ultra-wide-band based methods and poor anti-interference for Bluetooth-based methods and so on. In order to avoid these problems, a vision-based indoor localization method is proposed. Firstly, the whole deployment environment is departed into several regions and each region is assigned to a location center. Then, in offline mode, the VGG16NET is pre-trained by ImageNet dataset and it is fine-tuned by images on a custom dataset towards indoor localization. In online mode, the fully trained and converged VGG16NET takes as input a video stream captured by the front RGB camera of a mobile robot and outputs features specific to the current location. The features are then used as input to an ArcFace classifier which outputs the current location of the mobile robot. Experimental results show that our method can estimate the location of a mobile object with imaging capability accurately in cluttered unstructured scenes without any other additional device. The localization accuracy can reach to 94.7%.
BibTeX
@article{farisi2019vision,
  author = {Zeyad Farisi and Lianfang Tian and Xiang‐Yang Li and Bin Zhu},
  title = {{Vision based Indoor Localization Method via Convolution Neural Network}},
  journal = {International Journal of Advanced Computer Science and Applications},
  year = {2019},
  doi = {10.14569/ijacsa.2019.0100709},
}
Figure