English(EN) Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection

新的TEP-SAM框架增强了红外小目标检测能力

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-26 02:18

研究人员开发了一个名为时序涌现提示分割一切模型（TEP-SAM）的新框架，以改进红外序列中小目标的检测。该方法利用目标随时间从背景中逐渐涌现的线索，这是现有技术常常忽略的。TEP-SAM同时模拟全局和局部运动模式以识别潜在目标，并通过运动差异增强其特征，从而实现非交互式分割。 AI

影响这一新框架有望提高在复杂红外成像场景下目标检测的准确性。

排序理由该集群包含一篇详细介绍新技术方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Yinghui Xing, Donghao Chu, Shizhou Zhang, Di Xu · 2026-06-29 04:00

Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection

arXiv:2606.27655v1 Announce Type: new Abstract: Accurately localizing and segmenting small targets in low signal-to-noise ratio (SNR) infrared sequences remains a challenging task. Since targets are often indistinguishable from the background in individual frames, existing method…
arXiv cs.CV TIER_1 English(EN) · Di Xu · 2026-06-26 02:18

用于多帧红外小目标检测的暂态涌现提示

Accurately localizing and segmenting small targets in low signal-to-noise ratio (SNR) infrared sequences remains a challenging task. Since targets are often indistinguishable from the background in individual frames, existing methods, even when equipped with advanced foundation m…