Post natural disaster object recognition system using python-based scale invariant feature transform (SIFT) algorithm

Ahmad Zakaria, M F Fauzan, Samsul Wahidin, Alexandre Adam, B MukhlisIOP 2024 · DOI

Abstract The 2018 natural disaster in Palu, Indonesia, presented significant challenges in identifying damaged buildings at scale. Assessing structural integrity and reconstruction feasibility manually is a slow, labor-intensive process. This research presents an automated object recognition system utilizing the Scale Invariant Feature Transform (SIFT) algorithm implemented in Python. By comparing pre- and post-disaster imagery, the system identifies damage levels with high precision. Experimental results demonstrate that the SIFT-based approach achieves an average accuracy of 98.24% in distinguishing building states, providing a robust tool for government agencies and search-and-rescue teams.

Introduction: The Challenge of Rapid Assessment

In the immediate aftermath of a major earthquake or tsunami, rapid situational awareness is critical. For organizations like Indonesia's National Search and Rescue Agency, the sheer volume of destroyed infrastructure makes manual inspection a bottleneck. Traditional image comparison methods often fail due to variations in camera angle, lighting, and scale between historical photos and post-disaster aerial or ground-level shots. This study explores the application of SIFT to overcome these geometric and photometric variances, enabling automated damage detection.

Methodology

The proposed system leverages the SIFT algorithm to detect and describe local features in images. Unlike simple pixel-to-pixel comparisons, SIFT identifies "keypoints" that are invariant to image scaling and rotation.

The system's operational flowchart, from image upload to final matching results.

The workflow consists of several primary stages as outlined in the system architecture:

  1. Feature Detection: Utilizing the Difference of Gaussians (DoG) to locate stable points of interest.
  2. Feature Description: Generating descriptors based on local gradient orientations.
  3. Feature Matching: Identifying correspondences between the "before" and "after" image sets.
  4. Dimensional Analysis: Measuring changes in the object's pixel dimensions (height and width) to detect structural collapse or shifting.
  5. Damage Quantification: Calculating a final damage level based on the ratio of successful matches and dimensional errors.

Experimental Setup and Dataset

The system was tested using a curated dataset of JPEG images from the 2018 Palu disaster. Five major landmarks were analyzed: the Globe Monument, Mercure Hotel, Roa-roa Hotel, Tatura Mall, and Sya Hotel. These sites provided diverse examples of structural damage, from partial degradation to total collapse.

Key Insights and Results

The SIFT algorithm proved exceptionally capable of handling the chaotic visual environment of a disaster zone.

Feature Matching and Accuracy

The system achieved an impressive average accuracy of 98.24%. A critical finding was the behavior of feature matches in destroyed structures. For heavily damaged buildings, the percentage of successful feature matches dropped to between 0.83% and 2.28%, providing a clear mathematical threshold for catastrophic failure.

Visual representation of SIFT feature matching between pre-disaster (left) and post-disaster (right) images of Sya Hotel.

The "Rubble Effect"

Interestingly, the research noted that damage does not always lead to a decrease in detected keypoints. In several instances, the number of keypoints increased significantly post-disaster. This is attributed to the complex textures created by debris and rubble, which generate numerous edges and corners that the algorithm detects as features, even if they no longer match the original structure's descriptors.

Dimensional Distortion

By incorporating "Width Error" and "Height Error" metrics, the system could quantify physical deformation. For example, the Roa-roa Hotel—which collapsed entirely—showed a 23.79% Width Error, highlighting how structural shifts can be used as a secondary confirmation of damage.

Conclusion and Future Directions

The Python-based SIFT implementation offers a high-accuracy, automated alternative to manual building inspections. While highly effective on the tested landmarks, future iterations should focus on scaling the system to handle larger, more diverse datasets including residential areas. Additionally, integrating this logic into real-time drone or mobile platforms would significantly enhance its utility for field-based rescue operations.

Summary updated

Abstract

Abstract The natural disaster in Palu became a significant challenge in identifying damaged building objects. The large number of damaged buildings made it difficult for the government to identify the level of damage to buildings and the feasibility of the construction process after natural disasters. This research is an object recognition system after natural disasters using the Scale Invariant Feature Transform (SIFT) algorithm implemented in Python programming language. This research aims to assist the government or National Search and Rescue Agency team in identifying the level of damage to buildings after natural disasters. The methods used in this research include literature study, image capture, processing, testing, and data analysis. The SIFT algorithm was selected to see the accuracy of comparisons of images of buildings before and after natural disasters. The test results show that the SIFT method can identify the average accuracy level of damage to buildings before and after natural disasters, reaching 98.24%.
BibTeX
@inproceedings{zakaria2024post,
  author = {Ahmad Zakaria and M F Fauzan and Samsul Wahidin and Alexandre Adam and B Mukhlis},
  title = {{Post natural disaster object recognition system using python-based scale invariant feature transform (SIFT) algorithm}},
  booktitle = {IOP},
  year = {2024},
  doi = {10.1088/1755-1315/1355/1/012040},
}
Figure