Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor

  title={Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor},
  author={Masashi Okada and Shinji Takenaka and Tadahiro Taniguchi},
  journal={2020 IEEE International Conference on Robotics and Automation (ICRA)},
It is an effective strategy for the multi-person pose tracking task in videos to employ prediction and pose matching in a frame-by-frame manner. For this type of approach, uncertainty-aware modeling is essential because precise prediction is impossible. However, previous studies have relied on only a single prediction without incorporating uncertainty, which can cause critical tracking errors if the prediction is unreliable. This paper proposes an extension to this approach with Sequential… Expand
Probabilistic Human Motion Prediction via A Bayesian Neural Network
The key idea of the approach is to extend the conventional deterministic motion prediction neural network to a Bayesian one that could generate several future motions when given an observed motion sequence. Expand
"Let’s get ready to bundle!": Crowd-level Human Keypoint Tracking
This work examines the suitability of a state-of-the-art human pose tracking method for application within surveillance scenarios and focuses on public places in urban areas that tend to suffer fromExpand


PoseTrack: Joint Multi-person Pose Estimation and Tracking
This work proposes a novel method that jointly models multi-person pose estimation and tracking in a single formulation and introduces a challenging Multi-Person PoseTrack dataset, and proposes a completely unconstrained evaluation protocol that does not make any assumptions about the scale, size, location or the number of persons. Expand
Detect-and-Track: Efficient Pose Estimation in Videos
This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon theExpand
Pose Flow: Efficient Online Pose Tracking
An online optimization framework to build the association of cross-frame poses and form pose flows (PF-Builder) and a novel pose flow non-maximum suppression ( PF-NMS) is designed to robustly reduce redundant pose flows and re-link temporal disjoint ones. Expand
Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking
A simple network called Multi-Domain Pose Network (MDPN) is presented, which shows significant improvement over baselines and achieves the best performance on PoseTrack ECCV 2018 Challenge without additional datasets other than MPII and COCO. Expand
Efficient Online Multi-Person 2D Pose Tracking With Recurrent Spatio-Temporal Affinity Fields
This work proposes a novel temporal topology cross-linked across limbs which can consistently handle body motions of a wide range of magnitudes and makes the overall approach recurrent in nature, where the network ingests STAF heatmaps from previous frames and estimates those for the current frame. Expand
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
A novel benchmark "MPII Human Pose" is introduced that makes a significant advance in terms of diversity and difficulty, a contribution that is required for future developments in human body models. Expand
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learnExpand
Visual Articulated Tracking in the Presence of Occlusions
This paper proposes to use the per-pixel data-to-model associations provided from a random forest to avoid local minima during model fitting by training the random forest with artificial occlusions to achieve increased robustness to occlusion and clutter present in the scene. Expand
Pose estimator and tracker using temporal flow maps for limbs
This paper proposes temporal flow maps for limbs (TML) and a multi-stride method to estimate and track human poses and constructed a network to learn both spatial information and temporal information end-to-end. Expand
Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking
This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios. Using images from a monocular camera alone, we devise pairwise costs for objectExpand