# Promptable Fire Segmentation: Unleashing SAM2's Potential for Real-Time Mobile Deployment with Strategic Bounding Box Guidance

arXiv: https://arxiv.org/abs/2510.21782 · HTML: https://mlsanity.com/paper/2510.21782/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 18 Oct 2025.

## Builds on (most cited first, 15 of 15)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [TinySAM: Pushing the Envelope for Efficient Segment Anything Model](https://mlsanity.com/paper/2312.13789/) (2023)
- [SAM 2 in Robotic Surgery: An Empirical Evaluation for Robustness and Generalization in Surgical Video Segmentation](https://mlsanity.com/paper/2408.04593/) (2024)
- [YOLO Evolution: A Comprehensive Benchmark and Architectural Review of YOLOv12, YOLO11, and Their Previous Versions](https://mlsanity.com/paper/2411.00201/) (2024)
- [Is SAM 2 Better than SAM in Medical Image Segmentation?](https://mlsanity.com/paper/2408.04212/) (2024)
- [On Efficient Variants of Segment Anything Model: A Survey](https://mlsanity.com/paper/2410.04960/) (2024)
- [Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Survey](https://mlsanity.com/paper/2408.12889/) (2024)
- [Evaluating SAM2's Role in Camouflaged Object Detection: From SAM to SAM2](https://mlsanity.com/paper/2407.21596/) (2024)
- [Robust Box Prompt based SAM for Medical Image Segmentation](https://mlsanity.com/paper/2407.21284/) (2024)
- [Prompt-Based Segmentation at Multiple Resolutions and Lighting Conditions using Segment Anything Model 2](https://mlsanity.com/paper/2408.06970/) (2024)
- [PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications](https://mlsanity.com/paper/2506.18807/) (2025)
- [Detecting Wildfires on UAVs with Real-time Segmentation Trained by Larger Teacher Models](https://mlsanity.com/paper/2408.10843/) (2024)
- [Evaluation Study on SAM 2 for Class-agnostic Instance-level Segmentation](https://mlsanity.com/paper/2409.02567/) (2024)
- [Seeing Heat with Color -- RGB-Only Wildfire Temperature Inference from SAM-Guided Multimodal Distillation using Radiometric Ground Truth](https://mlsanity.com/paper/2505.01638/) (2025)

## Abstract (arXiv)

Fire segmentation remains a critical challenge in computer vision due to flames' irregular boundaries, translucent edges, and highly variable intensities. While the Segment Anything Models (SAM and SAM2) have demonstrated impressive cross-domain generalization capabilities, their effectiveness in fire segmentation -- particularly under mobile deployment constraints -- remains largely unexplored. This paper presents the first comprehensive evaluation of SAM2 variants for fire segmentation, focusing on bounding box prompting strategies to enhance deployment feasibility. We systematically evaluate four SAM2.1 variants (tiny, small, base_plus, large) alongside mobile-oriented variants (TinySAM, MobileSAM) across three fire datasets using multiple prompting strategies: automatic, single positive point (SP), single positive point + single negative point (SP+SN), multiple positive points (MP), bounding box (Box), and hybrid variants (Box+SP and Box+MP). Our experimental results demonstrate that bounding box prompts consistently outperform automatic and single point-based approaches, with Box+MP achieving the highest mean IoU (0.64) and Dice coefficient (0.75) on the Khan dataset. Lightweight variants such as TinySAM and MobileSAM further reduce memory and computational costs, making them more suitable for latency-tolerant edge scenarios. Overall, this work provides critical insights for deploying promptable segmentation models in fire monitoring systems and establishes benchmarks for future research in domain-specific SAM applications. Code is available at: https://github.com/UEmmanuel5/ProFSAM