Problem
Research questions and friction points this paper is trying to address.
Monocular 6-DoF pose estimation
non-cooperative targets
on-orbit servicing
debris removal
near-symmetric spacecraft orientations
HAT: Hypothesis-Anchored Tracking for Video Monocular Spacecraft Pose Estimation
🤖 AI Summary
本文提出Hypothesis-Anchored Tracking (HAT)框架，通过帧间运动选择CAD姿态假设，解决单目非合作目标6-DoF姿态估计问题。
📝 Abstract
Monocular 6-DoF pose estimation of non-cooperative targets is important for on-orbit servicing and debris removal. A single-image estimator can confuse near-symmetric spacecraft orientations, and tracking can preserve an incorrect pose. We present Hypothesis-Anchored Tracking (HAT), a causal framework that uses inter-frame motion to select among competing CAD-based pose hypotheses before alignment and fusion. Rather than independently choosing the highest-scoring hypothesis in each image, HAT retains competing orientation histories and selects a pose to anchor the relative trajectory estimated by monocular SLAM. Sparse anchors and pose fusion provide per-frame estimates after initialization without revising past outputs. The method requires only a calibrated RGB sequence, a metric CAD model, and target image regions, which can be supplied by detection or segmentation. The pretrained pose and SLAM networks require no target-specific training or fine-tuning. We evaluate two versions, Mega-HAT and Pico-HAT, using MegaPose and PicoPose, on SPARK-2024, SwissCube and SHIRT, with YCB-Video assessing performance outside the space domain. Using one temporal configuration per method, the arithmetic means of the four dataset-wise comparisons show 9.4% lower mean pose error and 3.76 times the sustained input FPS for Mega-HAT relative to independent MegaPose, and 23.9% lower mean pose error and 2.42 times the FPS for Pico-HAT relative to independent PicoPose. Mega-HAT ablations on SPARK and an offline reference examine component contributions and the effect of revising past estimates.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Hypothesis-Anchored Tracking
monocular SLAM
pose estimation
CAD-based pose hypotheses
inter-frame motion
🔎 Similar Papers
No similar papers found.
