Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.00900 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908476572172288 |
|---|---|
| author | Samavati, Taha Soryani, Mohsen Mansouri, Sina |
| author_facet | Samavati, Taha Soryani, Mohsen Mansouri, Sina |
| contents | The global demand for medicinal plants, such as Damask roses, has surged with population growth, yet labor-intensive harvesting remains a bottleneck for scalability. To address this, we propose a novel 3D perception pipeline tailored for flower-harvesting robots, focusing on sparse 3D localization of rose centers. Our two-stage algorithm first performs 2D point-based detection on stereo images, followed by depth estimation using a lightweight deep neural network. To overcome the challenge of scarce real-world labeled data, we introduce a photorealistic synthetic dataset generated via Blender, simulating a dynamic rose farm environment with precise 3D annotations. This approach minimizes manual labeling costs while enabling robust model training. We evaluate two depth estimation paradigms: a traditional triangulation-based method and our proposed deep learning framework. Results demonstrate the superiority of our method, achieving an F1 score of 95.6% (synthetic) and 74.4% (real) in 2D detection, with a depth estimation error of 3% at a 2-meter range on synthetic data. The pipeline is optimized for computational efficiency, ensuring compatibility with resource-constrained robotic systems. By bridging the domain gap between synthetic and real-world data, this work advances agricultural automation for specialty crops, offering a scalable solution for precision harvesting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00900 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sparse 3D Perception for Rose Harvesting Robots: A Two-Stage Approach Bridging Simulation and Real-World Applications Samavati, Taha Soryani, Mohsen Mansouri, Sina Robotics Artificial Intelligence Computer Vision and Pattern Recognition I.4; I.2.10; I.6; C.3 The global demand for medicinal plants, such as Damask roses, has surged with population growth, yet labor-intensive harvesting remains a bottleneck for scalability. To address this, we propose a novel 3D perception pipeline tailored for flower-harvesting robots, focusing on sparse 3D localization of rose centers. Our two-stage algorithm first performs 2D point-based detection on stereo images, followed by depth estimation using a lightweight deep neural network. To overcome the challenge of scarce real-world labeled data, we introduce a photorealistic synthetic dataset generated via Blender, simulating a dynamic rose farm environment with precise 3D annotations. This approach minimizes manual labeling costs while enabling robust model training. We evaluate two depth estimation paradigms: a traditional triangulation-based method and our proposed deep learning framework. Results demonstrate the superiority of our method, achieving an F1 score of 95.6% (synthetic) and 74.4% (real) in 2D detection, with a depth estimation error of 3% at a 2-meter range on synthetic data. The pipeline is optimized for computational efficiency, ensuring compatibility with resource-constrained robotic systems. By bridging the domain gap between synthetic and real-world data, this work advances agricultural automation for specialty crops, offering a scalable solution for precision harvesting. |
| title | Sparse 3D Perception for Rose Harvesting Robots: A Two-Stage Approach Bridging Simulation and Real-World Applications |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition I.4; I.2.10; I.6; C.3 |
| url | https://arxiv.org/abs/2508.00900 |