.png){kind=icon}
.png){kind=icon}
Return
NIM-STGCN: Differentiable motion decomposition for egocentric pedestrian trajectory prediction
.png){kind=icon}
OA
AI
F
B
Y
DOI：10.1007/s40747-025-02190-3.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Pedestrian trajectory prediction from egocentric monocular video is hindered by camera motion, intermittent occlusions, and complex social interactions. We present NIM-STGCN, a unified framework whose core contribution is a differentiable view normalization(GVN) that couples an enhanced differentiable PnP layer (ED-PnP) with an $$\textrm{SE}(3)$$ warp to align past observations into a single virtual static camera frame. Because GVN is trained end-to-end, forecasting losses back-propagate to pose estimation, yielding geometrically cleaner inputs. On the normalized histories, a lightweight Gated Convolutional Imputation Module (GCIM) recovers missing bounding-box measurements while preserving observed entries, and an efficient spatio-temporal GCN encodes agent dynamics and interactions (optionally augmented by a physics-guided kinematics–interaction prior, PKIM). A Gaussian-mixture predictor produces multi-modal futures and is optimized with a sequence-level negative log-likelihood together with a time-weighted position loss. Extensive experiments on the JAAD and PIE benchmarks show that NIM-STGCN reduces Average Displacement Error (ADE) and Final Displacement Error (FDE) by 12–18 % compared to state-of-the-art methods. Code is available at https://github.com/fantot/NIM-STGCN.
Keywords:
Egocentric vision
Pedestrian trajectory prediction
Ego-motion compensation
Occlusion-aware imputation
Autonomous driving
Computational Intelligence
Complexity
Data Structures and Information Theory
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.6
Papers:
2.1K
Citations:
6.6K
Organization
Cited Papers