通过关键异常点识别提升视觉伺服在恶劣条件下的鲁棒性
IKKA: Inversion Classification via Critical Anomalies for Robust Visual Servoing
- 将异常点视为结构信息，融合局部极值、边界穿透与多尺度持续性加权
- 在弱光和遮挡下，横向误差降低24%，推理速度提升至24.8Hz
- 适合嵌入式实时视觉伺服，尤其在资源受限场景下表现优异
我们提出IKKA（基于关键异常的反演分类），一种针对分布偏移下鲁棒视觉伺服的拓扑启发加权框架。不同于传统异常处理，IKKA将异常点视为具有结构信息的观测：微小扰动即可引发控制响应或类别判定质变的点。该方法将局部极值性、边界穿透性和多尺度持续性整合为单一异常权重W(x) = E(x) × T(x) × M(x)，用于调节模糊决策区域附近的控制更新。我们在Raspberry Pi 4上实现纯CPU嵌入式视觉伺服流水线，并在230次可复现实验中评估其在正常与压力条件下的表现。在弱光和瞬时遮挡的压力场景中，相较于混合基线，IKKA将95百分位横向误差从0.124降至0.094，降幅达24%，同时吞吐量从20.0提升至24.8 Hz。非参数分析确认效应量较大（Cliff's delta = 0.79）。
原文摘要 · Abstract (English)
We introduce IKKA (Inversion Classification via Critical Anomalies), a topologically motivated weighting framework for robust visual servoing under distribution shift. Unlike conventional outlier handling, IKKA treats maverick points as structurally informative observations: points where small perturbations can induce qualitatively different control responses or class assignments. The method combines local extremality, boundary transversality, and multi-scale persistence into a single anomaly weight, W(x) = E(x) x T(x) x M(x), which modulates control updates near ambiguous decision regions. We instantiate IKKA in a CPU-only embedded visual-servoing pipeline on Raspberry Pi 4 and evaluate it across 230 reproducible runs under nominal and stress conditions. In stress scenarios involving dim illumination and transient occlusion, IKKA reduces the 95th-percentile lateral error by 24% relative to a hybrid baseline (0.124 to 0.094) while increasing throughput from 20.0 to 24.8 Hz. Non-parametric analysis confirms a large effect size (Cliff's delta = 0.79).
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。