BioDet: Boosting Industrial Object Detection with Image Preprocessing Strategies
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_ | 1866914111179194368 |
|---|---|
| author | Hu, Jiaqi Xu, Hongli Huang, Junwen Yu, Peter KT Ilic, Slobodan Busam, Benjamin |
| author_facet | Hu, Jiaqi Xu, Hongli Huang, Junwen Yu, Peter KT Ilic, Slobodan Busam, Benjamin |
| contents | Accurate 6D pose estimation is essential for robotic manipulation in industrial environments. Existing pipelines typically rely on off-the-shelf object detectors followed by cropping and pose refinement, but their performance degrades under challenging conditions such as clutter, poor lighting, and complex backgrounds, making detection the critical bottleneck. In this work, we introduce a standardized and plug-in pipeline for 2D detection of unseen objects in industrial settings. Based on current SOTA baselines, our approach reduces domain shift and background artifacts through low-light image enhancement and background removal guided by open-vocabulary detection with foundation models. This design suppresses the false positives prevalent in raw SAM outputs, yielding more reliable detections for downstream pose estimation. Extensive experiments on real-world industrial bin-picking benchmarks from BOP demonstrate that our method significantly boosts detection accuracy while incurring negligible inference overhead, showing the effectiveness and practicality of the proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21000 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BioDet: Boosting Industrial Object Detection with Image Preprocessing Strategies Hu, Jiaqi Xu, Hongli Huang, Junwen Yu, Peter KT Ilic, Slobodan Busam, Benjamin Computer Vision and Pattern Recognition Accurate 6D pose estimation is essential for robotic manipulation in industrial environments. Existing pipelines typically rely on off-the-shelf object detectors followed by cropping and pose refinement, but their performance degrades under challenging conditions such as clutter, poor lighting, and complex backgrounds, making detection the critical bottleneck. In this work, we introduce a standardized and plug-in pipeline for 2D detection of unseen objects in industrial settings. Based on current SOTA baselines, our approach reduces domain shift and background artifacts through low-light image enhancement and background removal guided by open-vocabulary detection with foundation models. This design suppresses the false positives prevalent in raw SAM outputs, yielding more reliable detections for downstream pose estimation. Extensive experiments on real-world industrial bin-picking benchmarks from BOP demonstrate that our method significantly boosts detection accuracy while incurring negligible inference overhead, showing the effectiveness and practicality of the proposed method. |
| title | BioDet: Boosting Industrial Object Detection with Image Preprocessing Strategies |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.21000 |