Object Detection in Unstructured Driving Environments
DOI:
https://doi.org/10.36676/jrps.v15.i3.1459Keywords:
Object Detection, Unstructured Driving EnvironmentsAbstract
This paper conducts a comprehensive error analysis of the inference process performed on the YOLOv8 and RTDETR model, utilizing two distinct datasets: MS COCO, on which YOLOv8 and RT-DETR is originally trained, and IDD, a separate dataset. The primary focus lies on evaluating model performance using mean Average Precision (mAP) and Intersection over Union (IoU) metrics. Through rigorous experimentation and analysis, we investigate the discrepancies in model performance when applied to these diverse datasets. The findings shed light on the strengths and weaknesses of the YOLOv8 and RT-DETR model across different data domains, offering valuable insights for improving object detection systems in real-world applications.
References
Indian driving dataset. https://idd.insaan.iiit. ac.in/. 2
Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. Detr: End-to-end object detection with transformers. In Proceedings of the European Conference on Computer Vision (ECCV), 2020. 1 DOI: https://doi.org/10.1007/978-3-030-58452-8_13
Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Dolla´r, Piotr and Zitnick, C. Lawrence. Microsoft COCO: Common Objects in Context. http://cocodataset. org/, 2014. 2 DOI: https://doi.org/10.1007/978-3-319-10602-1_48
Aladdin Persson. Machine learning collection.
Ultralytics. YOLOv8 GitHub Repository. https:// github.com/ultralytics/yolov8, 2022. 1
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 International Journal for Research Publication and Seminar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Re-users must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. This license allows for redistribution, commercial and non-commercial, as long as the original work is properly credited.
