2 个仓库
Awesome GitHub RepositoriesTemporal Pose Analysis
Using temporal convolutional networks to analyze human skeletal movement over a sequence of video frames.
Distinct from Temporal Convolutional Networks: Applies temporal convolutions specifically to pose sequences rather than general time-series forecasting
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Temporal Pose Analysis. Refine with filters or upvote what's useful.
Awesome Temporal Pose Analysis GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- mvig-sjtu/alphapose
MVIG-SJTU/AlphaPose
8,583在 GitHub 上查看AlphaPose 是一个深度学习姿态估计框架和 PyTorch 计算机视觉库，旨在检测和追踪图像及视频中的人体、面部、手部和足部关键点。它提供了一套用于骨骼姿态估计和多人姿态追踪的系统。 该项目实现了三维人体姿态重建工具，可从二维图像数据生成关节位置和人体网格形状。它还包含一个多人姿态追踪器，能够在连续的视频帧中保持多人的身份识别。 该框架涵盖了广泛的计算机视觉功能，包括多人关键点定位、人体运动追踪以及三维人体网格重建。
Matches detected skeletal poses across video frames by comparing spatial proximity and appearance features.
Python - facebookresearch/videopose3d
facebookresearch/VideoPose3D
3,986在 GitHub 上查看VideoPose3D is a machine learning framework designed for 3D human pose estimation. It functions as a motion reconstruction tool that predicts 3D joint positions from 2D video sequences using a temporal convolutional network to process body movement over time. The project includes a semi-supervised learning pipeline that improves pose accuracy by combining labeled datasets with unlabeled video data and projection consistency loss. It also features a video pose visualizer capable of rendering 3D skeleton reconstructions and 2D keypoints as overlays on original footage. The framework covers the
Uses temporal convolutions to estimate human motion over time from video sequences.
Python
