Overcoming Scene Context Constraints for Object Detection in wild using Defilters
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929312244957184 |
|---|---|
| author | Kancharla, Vamshi Krishna sinha, Neelam |
| author_facet | Kancharla, Vamshi Krishna sinha, Neelam |
| contents | This paper focuses on improving object detection performance by addressing the issue of image distortions, commonly encountered in uncontrolled acquisition environments. High-level computer vision tasks such as object detection, recognition, and segmentation are particularly sensitive to image distortion. To address this issue, we propose a novel approach employing an image defilter to rectify image distortion prior to object detection. This method enhances object detection accuracy, as models perform optimally when trained on non-distorted images. Our experiments demonstrate that utilizing defiltered images significantly improves mean average precision compared to training object detection models on distorted images. Consequently, our proposed method offers considerable benefits for real-world applications plagued by image distortion. To our knowledge, the contribution lies in employing distortion-removal paradigm for object detection on images captured in natural settings. We achieved an improvement of 0.562 and 0.564 of mean Average precision on validation and test data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08293 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Overcoming Scene Context Constraints for Object Detection in wild using Defilters Kancharla, Vamshi Krishna sinha, Neelam Computer Vision and Pattern Recognition This paper focuses on improving object detection performance by addressing the issue of image distortions, commonly encountered in uncontrolled acquisition environments. High-level computer vision tasks such as object detection, recognition, and segmentation are particularly sensitive to image distortion. To address this issue, we propose a novel approach employing an image defilter to rectify image distortion prior to object detection. This method enhances object detection accuracy, as models perform optimally when trained on non-distorted images. Our experiments demonstrate that utilizing defiltered images significantly improves mean average precision compared to training object detection models on distorted images. Consequently, our proposed method offers considerable benefits for real-world applications plagued by image distortion. To our knowledge, the contribution lies in employing distortion-removal paradigm for object detection on images captured in natural settings. We achieved an improvement of 0.562 and 0.564 of mean Average precision on validation and test data. |
| title | Overcoming Scene Context Constraints for Object Detection in wild using Defilters |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.08293 |