MITE-Net实现在无人机上实时处理4K高清图像的微小目标检测，功耗极低。
MITE-Net: SWaP-Optimized 4K Video Tiny Target Perception for Embodied Edge SAR
- 采用生物启发式无学习区域建议网络与超轻量级检测头，降低计算开销。
- 在4K海景图像上实现30.33帧/秒、100%搜索成功率，功耗仅3.19瓦。
- 构建SAR-Tiny数据集，为微小目标检测提供标准评估基准。
高分辨率图像中实时微小目标感知对自主搜救任务至关重要。然而，无人机等边缘设备严格的尺寸、重量和功耗（SWaP）限制导致传统下采样造成特征丢失，分块处理则带来过高延迟。为此，本文提出综合框架：首先设计MITE-Net，一种面向SWaP优化的级联架构，结合生物启发、无需训练的微小目标运动区域提议网络（TTM-RPN）与参数少于0.14M的R-CNN类检测头；其次，构建SAR-Tiny数据集，重新标注两个挑战性无人机数据集——SeaDroneSee-Tiny（动态海面场景，目标大小64-256像素）和UAVID-Tiny（复杂城市场景，目标小于64像素），以标准化4K微小目标评估；最后，在NVIDIA Jetson AGX Xavier边缘设备上测试，MITE-Net直接处理4K海面图像，达到30.33帧/秒、100%搜索成功率，功耗仅3.19瓦（9.51帧/瓦），显著优于YOLO基线模型的目标召回率与能效。但在城市场景中，无学习前端表现受限，轻量头难以捕捉复杂特征。本工作提供了高效的机载感知范式与未来端到端搜救架构的基准指导。
原文摘要 · Abstract (English)
Real-time tiny target perception in high-resolution imagery is critical for embodied Search-and-Rescue (SAR) missions. However, strict Size, Weight, and Power (SWaP) constraints on edge devices like UAVs create a bottleneck: traditional image downsampling causes severe feature loss, while slice-based processing incurs prohibitive latency. To address this gap, this paper introduces a comprehensive framework encompassing a novel architecture, specialized datasets, and hardware-level benchmarks. First, we propose MITE-Net, a SWaP-optimized cascaded architecture, which couples a bio-inspired, learning-free Tiny Target Motion-Based Region Proposal Network (TTM-RPN) with a sub-0.14M-parameter R-CNN-like head. Second, to standardize 4K tiny target evaluation, we construct the SAR-Tiny Datasets by relabeling two challenging UAV datasets: SeaDroneSee-Tiny (dynamic maritime scenes, tiny targets predominantly of 64-256 pixels ) and UAVID-Tiny (cluttered urban scenes, extremely tiny targets, less than 64 pixels). Third, we benchmark against state-of-the-art YOLO models on an edge device, NVIDIA Jetson AGX Xavier, where MITE-Net directly processes 4K maritime imagery, achieving a 100\% search success rate at 30.33 FPS. Consuming merely 3.19 W (9.51 FPS/W), MITE-Net vastly outperforms YOLO baselines in target recall and energy efficiency. Conversely, UAVID-Tiny evaluations expose a compound structural limitation: the learning-free bionic front-end struggles against urban backgrounds, while the ultra-lightweight head lacks representational capacity for complex features. Ultimately, this work delivers an efficient onboard perception paradigm and a rigorous baseline guiding future end-to-end SAR architectures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。