MITE-Net: SWaP-Optimized 4K Video Tiny Target Perception for Embodied Edge SAR

2026-08-16

AI Summary

This study addresses feature loss and high-latency bottlenecks in 4K small object perception on edge devices by proposing MITE-Net, a SWaP-optimized cascaded architecture. The method integrates a bio-inspired, learning-free Temporal Motion Region Proposal Network (TTM-RPN) with an ultra-lightweight detection head containing fewer than 0.14M parameters, alongside a standardized SAR-Tiny evaluation benchmark. Deployed on a Jetson AGX Xavier platform, the system achieves real-time 4K processing at 30.33 FPS with a 100% search success rate and merely 3.19W power consumption. Demonstrating significantly superior energy efficiency and recall compared to YOLO baselines, this work effectively overcomes perception limitations under stringent resource constraints.

Abstract

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.

Problem

• Tiny Target Perception
• SWaP Constraints
• Embodied Edge SAR
• 4K Video
• Real-time Processing

Innovation

• SWaP-Optimized Architecture
• Learning-Free TTM-RPN
• 4K Tiny Target Perception
• SAR-Tiny Datasets
• Edge SAR Benchmark