6 个仓库
Awesome GitHub RepositoriesHuman
Models that detect key body joints and limbs for each person in an image or video to reconstruct their pose.
Distinct from Pose Estimation Models: Distinct from Pose Estimation Models: focuses specifically on human body keypoints rather than general object or animal pose estimation.
Explore 6 awesome GitHub repositories matching artificial intelligence & ml · Human. Refine with filters or upvote what's useful.
Awesome Human 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。
- ultralytics/yolov3
ultralytics/yolov3
10,571在 GitHub 上查看This is a real-time object detection framework built on the YOLOv3 architecture, implemented in PyTorch. It provides a complete pipeline for identifying and localizing objects in images and video using a single neural network pass, combining a Darknet-53 backbone with multi-scale feature pyramids and anchor-based bounding box prediction. The framework extends beyond basic detection to include instance segmentation, human pose estimation, and multi-object tracking across video frames. It offers a model export toolkit that converts trained models through ONNX to CoreML, TensorFlow Lite, and Ten
Ships a human pose estimation model that detects body keypoints and reconstructs poses in images and video.
Pythondeep-learningmachine-learningobject-detection - 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。
Detects keypoints for the human body, face, hands, and feet across multiple people in images and videos.
Python - xingyizhou/centernet
xingyizhou/CenterNet
7,565在 GitHub 上查看CenterNet 是一个中心点目标检测框架和实时计算机视觉流水线。它通过预测中心点而不是使用锚框 (Anchor Boxes) 来识别对象和姿态。 该系统作为 3D 边界框估计器、人体姿态估计模型以及实时目标检测工具运行。它将关节的放置和对象位置视为中心点检测问题，以定位图像和三维空间中的实体。 能力涵盖 3D 目标检测、人体关键点估计和实时视频分析。该流水线使用单阶段前馈推理过程，对摄像头或视频文件进行持续分析。
Identifies human body joints and limbs by treating pose estimation as center point detection.
Python - paddlepaddle/paddlex
PaddlePaddle/PaddleX
6,163在 GitHub 上查看PaddleX is a PaddlePaddle-based framework for building, deploying, and fine-tuning AI model pipelines, with pre-built support for computer vision, OCR, document analysis, and time series tasks. It offers a toolkit of ready-to-use pipelines for image classification, object detection, segmentation, and pose estimation, alongside an end-to-end OCR document analysis pipeline that extracts text, tables, formulas, and layout information. The platform also includes a dedicated time series forecasting pipeline for analyzing historical data to detect anomalies, classify patterns, and predict future val
Identifies and locates specific body joints like shoulders and elbows in images to analyze human pose.
Pythonai-pipelinesclassificationdeployment - dmlc/gluon-cv
dmlc/gluon-cv
5,922在 GitHub 上查看Gluon-CV 是一个 MXNet 计算机视觉库，提供了一系列预实现的视觉架构和训练管线。它作为一个深度学习研究工具包和模型库，包含用于图像和视频分析的最先进预训练权重。 该项目包括一个专门的人体姿态估计库和模型压缩工具包。这些工具允许对深度学习模型进行剪枝和量化，以提高推理速度并促进在受限边缘硬件上的部署。 该库涵盖了广泛的视觉功能，包括图像分类、目标检测以及语义和实例分割。它还提供视频分析工具，如动作识别、目标跟踪和单目深度估计。 训练通过自动化管线和分布式多 GPU 工作负载提供支持，以加速模型收敛。
Includes specialized models for identifying anatomical keypoints and tracking human body movement.
Pythonaction-recognitioncomputer-visiondeep-learning - facebookresearch/sapiens
facebookresearch/sapiens
5,388在 GitHub 上查看Sapiens 是一个高分辨率人体视觉模型，专为高精度、以人为中心的计算机视觉任务而设计。它是一套用于估计人体姿态、深度和表面几何形状的工具集。 该项目利用视觉 Transformer 主干网络通过共享编码器执行多项任务。这种架构能够同时预测骨骼结构、关节位置以及相机与人体对象之间的距离。 该模型的功能涵盖了人体部位分割（从背景中分离解剖区域）和表面法线预测（从 2D 图像中恢复 3D 几何细节）。这些任务由一个采用像素级回归和语义分割掩码的多任务学习框架提供支持。
Delineates human anatomical regions and joint locations to separate people from backgrounds.
Python
