compliceu Goto Github PK

learnable-triangulation-pytorch

This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D human pose estimation!

learnbot-emotion-recognition-proposed-model

Landmarks - Masks - Cascades (Hog - Gabor - LBP) - Action Units - Xgboost

libmot

A Library of Multi-Object Tracking

libtorch-yolov3-deepsort

license-plate-recognition

License Plate Recognition For Car With Python And OpenCV

lightweight-human-pose-estimation-3d-demo.pytorch

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

materials-temporal-action-detection

temporal action detection: benchmark results, features download etc.

mediapipe

MediaPipe is a cross-platform framework for building multimodal applied machine learning pipelines

microcommunity

HC小区物业管理系统包含收费+报表，报修，门禁道闸，线上缴费，社区商圈，巡检，公众号欠费推送和公告微信推送功能，目前我们合作伙伴已经在安徽宿州4个小区， 深圳2个小区，西安11个小区，山东5个小区和哈尔滨1个小区等商业化运营平稳。欢迎您直接商用或者推荐您身边物业商用

mmdetection-mini

mmdetection最小学习版

mmfashion

Open-source toolbox for visual fashion analysis based on PyTorch

mmskeleton

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

mocapnet

We present MocapNET, an ensemble of SNN encoders that estimates the 3D human body pose based on 2D joint estimations extracted from monocular RGB images. MocapNET provides BVH file output which can be rendered in real-time or imported without any additional processing in most popular 3D animation software. The proposed architecture achieves 3D human pose estimations at state of the art rates of 400Hz using only CPU processing.

models

Models and examples built with TensorFlow

motionpathsextraction

Approach to extract motion paths (trajectories) of vehicles and pedestrians from videos (Multiple object detection & tracking)

multi-camera-vehicle-tracking-and-reidentification

This repository contains our source code of Track 3 in the NVIDIA AI City Challenge Workshop at CVPR 2018. Please find the full source code of both Track 1 and Track 3 here ->

multi-object-tracking

yolov3, deep_sort and optical flow

multi-object-tracking-paper-list

Paper list and source code for multi-object-tracking

multi-target-tracking

Multi target tracking with Opencv

mvpose

Code for "Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views" in CVPR'19

nanonets_object_tracking

norfair

Lightweight Python library for adding real-time 2D object tracking to any detector.

noscope

Accelerating network inference over video

object-detection-and-tracking

YOLO & RCNN Object Detection and Multi-Object Tracking

objectposeestimationsummary

Resources (papers, datasets, rendering methods) in the domain of object pose estimation.

opencv-practical-exercise

OpenCV practical exercise

openpose-based-gui-for-realtime-pose-estimate-and-action-recognition

GUI based on the python api of openpose in windows using cuda10 and cudnn7. Support body , hand, face keypoints estimation and data saving. Realtime gesture recognition is realized through two-layer neural network based on the skeleton collected from the gui.

openpose-deepsort-yolov3

openpose-plus

High-Performance and Flexible Pose Estimation Framework using TensorFlow, OpenPose and TensorRT

openpose_python

OpenPose Python API で手の形状認識