Research map / Detection and segmentation / Open-set and few-shot detection
ForestPersons: A Large-Scale Dataset for Under-Canopy Missing Person Detection
Deokyun Kim, Jeongjun Lee, Jungwon Choi, Jonggeon Park, Giyoung Lee, Yookyung Kim, Myungseok Ki, Juho Lee, Jihun Cha
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train on ForestPersons instead of prior SAR/ground-level datasets | Faster R-CNN · ForestPersons test | AP: 3.0 (SARD), 0.2 (HERIDAL), 11.3 (WiSARD), 5.9 (CityPersons), 40.8 (COCOPerson) -> 64.4 | Improved |
| train on all poses instead of standing only (ablation) | Faster R-CNN · ForestPersons test, Lying subset | AP: 42.2 -> 61.0 | Improved |
| train on all poses instead of standing only (ablation) | Faster R-CNN · ForestPersons test, Sitting subset | AP: 47.0 -> 66.1 | Improved |
| train on all seasons instead of winter only (ablation) | Faster R-CNN · ForestPersons test, Summer subset | AP: 18.7 -> 65.9 | Improved |
| train on all seasons instead of summer only (ablation) | Faster R-CNN · ForestPersons test, Winter subset | AP: 34.6 -> 64.0 | Improved |
| add motion blur and ISO noise augmentation to ForestPersons training (ablation) | Faster R-CNN · Real MAV test set | AP: 61.4 -> 35.8 | Hurt |
| train on ForestPersons instead of prior SAR datasets | Faster R-CNN · Real MAV test set | AP: 23.2 (SARD), 0.0 (HERIDAL), 40.2 (WiSARD) -> 61.4 | Improved |
| higher occlusion visibility level of test persons | models trained on ForestPersons · ForestPersons test | AP | Improved |
Closest papers by meaning
- ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images (CVPR 2025 · similarity 0.83)
- Bringing SAM to new heights: leveraging elevation data for tree crown segmentation from drone imagery (NeurIPS 2025 · similarity 0.83)
- FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest Monitoring (AAAI 2025 · similarity 0.83)
- AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification (CVPR 2025 · similarity 0.82)
- Open-Canopy: Towards Very High Resolution Forest Monitoring (CVPR 2025 · similarity 0.82)
- WildlifeMapper: Aerial Image Analysis for Multi-Species Detection and Identification (CVPR 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
