Video frame feeding approach for validating the performance of an object detection model in real-world conditions
Guardado en:
| Publicado en: | Automatika vol. 65, no. 2 (Apr 2024), p. 627 |
|---|---|
| Autor principal: | |
| Otros Autores: | |
| Publicado: |
Taylor & Francis Ltd.
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full Text - PDF |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 2927058048 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 0005-1144 | ||
| 022 | |a 1848-3380 | ||
| 024 | 7 | |a 10.1080/00051144.2024.2314928 |2 doi | |
| 035 | |a 2927058048 | ||
| 045 | 2 | |b d20240401 |b d20240430 | |
| 100 | 1 | |a Jayan, Keerthi |u Department of Computing Technologies, School of Computing, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India | |
| 245 | 1 | |a Video frame feeding approach for validating the performance of an object detection model in real-world conditions | |
| 260 | |b Taylor & Francis Ltd. |c Apr 2024 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a The challenge of evaluating deep learning-based object detection models in complex traffic scenarios, characterized by changing weather and lighting conditions, is addressed in this study. Real-world testing proves time and cost-intensive, leading to the proposal of a Video Frame Feeding (VFF) approach as a solution. The proposed Video Frame Feeding approach acts as a bridge between object detection models and simulated environments, enabling the generation of realistic scenarios. Leveraging the CarMaker (CM) tool to simulate realistic scenarios, the framework utilizes a virtual camera to capture the simulated environment and feed video frames to an object identification model. The VFF algorithm, with automated validation using simulated ground truth data, enhances detection accuracy to over 95% at 30 frames per second within 130 meters. Employing the You Only Look Once (YOLO) version 4 and the German Traffic Sign Recognition Benchmark dataset, the study assesses a traffic signboard identification model across various climatic conditions. Notably, the VFF algorithm improves accuracy by 2% to 5% in challenging scenarios like foggy days and nights. This innovative approach not only identifies object detection issues efficiently but also offers a versatile solution applicable to any object detection model, promising improved dataset quality and robustness for enhanced model performance. | |
| 653 | |a Accuracy | ||
| 653 | |a Environment models | ||
| 653 | |a Datasets | ||
| 653 | |a Algorithms | ||
| 653 | |a Traffic signs | ||
| 653 | |a Virtual cameras | ||
| 653 | |a Traffic models | ||
| 653 | |a Frames (data processing) | ||
| 653 | |a Object recognition | ||
| 653 | |a Simulation | ||
| 653 | |a Automobile industry | ||
| 653 | |a Frames per second | ||
| 653 | |a Cameras | ||
| 653 | |a Deep learning | ||
| 653 | |a Vision systems | ||
| 653 | |a Street signs | ||
| 653 | |a Traffic control | ||
| 653 | |a Automation | ||
| 653 | |a Efficiency | ||
| 653 | |a Vehicles | ||
| 700 | 1 | |a Muruganantham, B |u Department of Computing Technologies, School of Computing, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India | |
| 773 | 0 | |t Automatika |g vol. 65, no. 2 (Apr 2024), p. 627 | |
| 786 | 0 | |d ProQuest |t Research Library | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/2927058048/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/2927058048/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |