mfkiwl Goto Github PK

pose-graph-initialization

pose-tracking-for-aruco-markers-using-kalman-filter

A robust but simple object pose tracking algorithm based on Kalman filtering.

pose_ekf

Extented Kalman Filter for 6D pose estimation using gps, imu, magnetometer and sonar sensor.

pose_graph

pose_graph_backend

Multi-agent Pose-Graph Sensor Fusion - from "Multi-robot Coordination with Agent-Server Architecture for Autonomous Navigation in Partially Unknown Environments", IROS 2020

pose_initializer

Determine the pose (position + orientation) of the vehicle using GNSS

poseaug

Repository for the paper "PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation", CVPR 2021 (Oral, Best Paper Candidate).

posecontrast

(3DV 2021 oral) PyTorch implementation of paper "PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning"

poseflow

PoseFlow: Efficient Online Pose Tracking (BMVC'18)

posegraph-ceres

An offline tool for pose-graph-optimization.

poselib

Minimal solvers for calibrated camera pose estimation

posetriplet

[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

posit-hdl-arithmetic

Universal number Posit HDL Arithmetic Architecture generator

posit32-2-exact-multiply-accumulator

This is a hardware implementation of exact multiply accumulator for 32-bit posit number with es=2

posit_arith_hdl

Posit HDL Arithmetic Framework optimized for Decimal Accuracy

position-control-using-orbslam2-on-the-jetson-nano

Run ORBSLAM2 on the Jetson Nano, using recorded rosbags (e.g., EUROC) or live footage from a Bebop2 Drone

positionbaseddynamics

PositionBasedDynamics is a library for the physically-based simulation of rigid bodies, deformable solids and fluids.

positionbasedoncommunicationsatellite

This software has developed a positioning software based on the Iridium satellite signal based on the C/C++ language and windows + QT platform, which basically realizes the following functions: 1. Doppler information processing and extraction and image presentation after the hardware collects the input data; 2. TLE update tool mainly for Iridium; 3. Automatic identification, overhead satellite prediction and positioning based on the extracted Doppler information and the satellite number of the TLE file, and displayed on the graphical interface based on Baidu Map API;

positionfinder

This software is used to for finding your position . Currently, it is a pure traditional GNSS receiver. But in the future, we will combine other novel positioning techniques.

positioning

GENIVI Positioning

positioning-gnss-ins

GENIVI Positioning

positioning-system-project-with-gps-wifi-ins-fusion

In this project, five different sensors i.e. Accelerometer, Gyro meter, Magnetometer, GPS sensor, and WiFi sensor were used to apply sensor fusion. In particular, the sequential fusion method was studied and experimented with to find the positioning. To reduce the fluctuations and noise of INS sensors, averaging as preprocessing technique was implemented. To synchronize the sampling frequencies of different INS, a feature in the software application was added which allows users to adjust the sampling frequency of different sensors based on the application. The proposed algorithm estimates the distance using the Accelerometer and GPS sensor in short time intervals depending on the user-defined threshold. At the same time, the measurements from the magnetometer and gyro meter were fused to calculate the angular movements.

positionvelocitytime.jl

Calculate position velocity and time

posits_arithmetics

Provides a Hardware Description of basics arithmetics on posit format.

posmv

posmv-1

posmv reader and analysis

post-shannon-sdr

In this repository, you will find the source code for analyzing tracks during data transmission using Software Defined Radios. Metrics about error positioning and error syndrome are attached.

posture_recognition_cnn

To help machines learn what we human beings are doing via a camera is important. Once it comes true, machines can make different responses to all kinds of human's postures. But the process is very difficult as well, because usually it is very slow and power-consuming, and requires a very large memory space. Here we focus on real-time posture recognition, and try to make the machine "know" what posture we make. The posture recognition system is consisted of DE10-Nano SoC FPGA Kit, a camera, and an HDMI monitor. SoC FPGA captures video streams from the camera, recognizes human postures with a CNN model, and finally shows the original video and classification result (standing, walking, waving, etc.) via HDMI interface.

potato

Yet another RISC-V core

potato-riscv