Reliable Detection of Minute Targets in High-Resolution Aerial Imagery across Temporal Shifts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918245844385792 |
|---|---|
| author | Gholizadeh, Mohammad Sadegh Rezapour, Amir Arsalan Shayegh, Hamidreza Pazouki, Ehsan |
| author_facet | Gholizadeh, Mohammad Sadegh Rezapour, Amir Arsalan Shayegh, Hamidreza Pazouki, Ehsan |
| contents | Efficient crop detection via Unmanned Aerial Vehicles is critical for scaling precision agriculture, yet it remains challenging due to the small scale of targets and environmental variability. This paper addresses the detection of rice seedlings in paddy fields by leveraging a Faster R-CNN architecture initialized via transfer learning. To overcome the specific difficulties of detecting minute objects in high-resolution aerial imagery, we curate a significant UAV dataset for training and rigorously evaluate the model's generalization capabilities. Specifically, we validate performance across three distinct test sets acquired at different temporal intervals, thereby assessing robustness against varying imaging conditions. Our empirical results demonstrate that transfer learning not only facilitates the rapid convergence of object detection models in agricultural contexts but also yields consistent performance despite domain shifts in image acquisition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11360 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reliable Detection of Minute Targets in High-Resolution Aerial Imagery across Temporal Shifts Gholizadeh, Mohammad Sadegh Rezapour, Amir Arsalan Shayegh, Hamidreza Pazouki, Ehsan Computer Vision and Pattern Recognition Efficient crop detection via Unmanned Aerial Vehicles is critical for scaling precision agriculture, yet it remains challenging due to the small scale of targets and environmental variability. This paper addresses the detection of rice seedlings in paddy fields by leveraging a Faster R-CNN architecture initialized via transfer learning. To overcome the specific difficulties of detecting minute objects in high-resolution aerial imagery, we curate a significant UAV dataset for training and rigorously evaluate the model's generalization capabilities. Specifically, we validate performance across three distinct test sets acquired at different temporal intervals, thereby assessing robustness against varying imaging conditions. Our empirical results demonstrate that transfer learning not only facilitates the rapid convergence of object detection models in agricultural contexts but also yields consistent performance despite domain shifts in image acquisition. |
| title | Reliable Detection of Minute Targets in High-Resolution Aerial Imagery across Temporal Shifts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.11360 |