INTEGRATING CNN AND DICTIONARY MECHANISMS FOR EFFECTIVE LOOP CLOSURE DETECTION
Loop closure detection (LCD) remains a critical challenge in visual Simultaneous Localization and Mapping (SLAM), particularly in environments with repetitive structures or sparse textures where traditional methods suffer from perceptual aliasing and computational inefficiency. This paper presents...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Zakho
2025-07-01
|
| Series: | Science Journal of University of Zakho |
| Subjects: | |
| Online Access: | https://sjuoz.uoz.edu.krd/index.php/sjuoz/article/view/1579 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849414298457079808 |
|---|---|
| author | Ayda Mohammed Sharif Sadegh Abdollah Aminifar |
| author_facet | Ayda Mohammed Sharif Sadegh Abdollah Aminifar |
| author_sort | Ayda Mohammed Sharif |
| collection | DOAJ |
| description |
Loop closure detection (LCD) remains a critical challenge in visual Simultaneous Localization and Mapping (SLAM), particularly in environments with repetitive structures or sparse textures where traditional methods suffer from perceptual aliasing and computational inefficiency. This paper presents a robust and scalable LCD framework that integrates a lightweight Convolutional Neural Network (CNN) with a dictionary-based voting mechanism, optimized for accuracy and real-time performance in resource-constrained settings. The proposed CNN architecture, featuring a single convolutional layer with 32 filters, achieves 98% classification accuracy on the Greenhouse Scene Dataset-a structured agricultural environment. Complementing the CNN, a dynamic dictionary tracks class frequencies to detect loop closures via adaptive thresholding, eliminating the need for complex feature matching or geometric verification. Experimental results demonstrate real-time operation (0.076 seconds per 70 frames) and resilience to spatial distortions, maintaining 92% accuracy under pixel-level shifts. Compared to state-of-the-art methods, our approach reduces computational overhead and memory usage
|
| format | Article |
| id | doaj-art-065e2df6a4794c3ab72d5f04fa012714 |
| institution | Kabale University |
| issn | 2663-628X 2663-6298 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | University of Zakho |
| record_format | Article |
| series | Science Journal of University of Zakho |
| spelling | doaj-art-065e2df6a4794c3ab72d5f04fa0127142025-08-20T03:33:52ZengUniversity of ZakhoScience Journal of University of Zakho2663-628X2663-62982025-07-0113310.25271/sjuoz.2025.13.3.1579INTEGRATING CNN AND DICTIONARY MECHANISMS FOR EFFECTIVE LOOP CLOSURE DETECTIONAyda Mohammed Sharif0Sadegh Abdollah Aminifar1Department of Computer, College of Science, University of Soran, 44008, Kurdistan, IraqDepartment of Computer, College of Science, University of Soran, 44008, Kurdistan, Iraq Loop closure detection (LCD) remains a critical challenge in visual Simultaneous Localization and Mapping (SLAM), particularly in environments with repetitive structures or sparse textures where traditional methods suffer from perceptual aliasing and computational inefficiency. This paper presents a robust and scalable LCD framework that integrates a lightweight Convolutional Neural Network (CNN) with a dictionary-based voting mechanism, optimized for accuracy and real-time performance in resource-constrained settings. The proposed CNN architecture, featuring a single convolutional layer with 32 filters, achieves 98% classification accuracy on the Greenhouse Scene Dataset-a structured agricultural environment. Complementing the CNN, a dynamic dictionary tracks class frequencies to detect loop closures via adaptive thresholding, eliminating the need for complex feature matching or geometric verification. Experimental results demonstrate real-time operation (0.076 seconds per 70 frames) and resilience to spatial distortions, maintaining 92% accuracy under pixel-level shifts. Compared to state-of-the-art methods, our approach reduces computational overhead and memory usage https://sjuoz.uoz.edu.krd/index.php/sjuoz/article/view/1579SLAMLoop ClosureMachine LearningCNNDictionary |
| spellingShingle | Ayda Mohammed Sharif Sadegh Abdollah Aminifar INTEGRATING CNN AND DICTIONARY MECHANISMS FOR EFFECTIVE LOOP CLOSURE DETECTION Science Journal of University of Zakho SLAM Loop Closure Machine Learning CNN Dictionary |
| title | INTEGRATING CNN AND DICTIONARY MECHANISMS FOR EFFECTIVE LOOP CLOSURE DETECTION |
| title_full | INTEGRATING CNN AND DICTIONARY MECHANISMS FOR EFFECTIVE LOOP CLOSURE DETECTION |
| title_fullStr | INTEGRATING CNN AND DICTIONARY MECHANISMS FOR EFFECTIVE LOOP CLOSURE DETECTION |
| title_full_unstemmed | INTEGRATING CNN AND DICTIONARY MECHANISMS FOR EFFECTIVE LOOP CLOSURE DETECTION |
| title_short | INTEGRATING CNN AND DICTIONARY MECHANISMS FOR EFFECTIVE LOOP CLOSURE DETECTION |
| title_sort | integrating cnn and dictionary mechanisms for effective loop closure detection |
| topic | SLAM Loop Closure Machine Learning CNN Dictionary |
| url | https://sjuoz.uoz.edu.krd/index.php/sjuoz/article/view/1579 |
| work_keys_str_mv | AT aydamohammedsharif integratingcnnanddictionarymechanismsforeffectiveloopclosuredetection AT sadeghabdollahaminifar integratingcnnanddictionarymechanismsforeffectiveloopclosuredetection |