PLVS is a real-time SLAM system with points, lines, volumetric mapping and 3D unsupervised incremental segmentation.

MIT Cheetah I Implementation

Fast Segment Anything

Camera-Radar-Lidar Fusion detection net based on ROS, YOLOv4, OpenPCDet.

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

Estimates pose, velocity, and accelerometer / gyroscope biases by fusing GPS position and/or 6DOF pose with IMU data. The fusion is done using GTSAM's sparse nonlinear incremental optimization (ISA…

This is a temporary repository, which contains all the files needed to simulate the Unitree Robotics' a1 quadrupedal robot.

Find-Object project

Tools for migrating packages from ROS1 to ROS2.

An Open Source Quadruped-Robot for Simulating and Real Environment

Leveraging system development and robot deployment for aerial autonomous navigation.

NN-based radar-camera post sensor fusion implemented by TensorRT

CenterFusion++ is a frustum propsal-based camera and radar sensor fusion network.

An efficient single/multi-agent trajectory planner for multicopters.

LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping

Leveraging system development and robot deployment for ground-based autonomous navigation and exploration.

WS2811, WS2812, WS2812B or compatible leds driver with STM32, TIM, PWM and DMA with minimum RAM required

STM32F103_WS2812(PWM+DMA)

Detect 6-DOF grasp poses in point clouds

Deep face segmentation in extremely hard conditions

🎓Automatically Update CV Papers Daily using Github Actions (Update Every 8th hours)

深度学习入门课、资深课、特色课、学术案例、产业实践案例、深度学习知识百科及面试题库The course, case and knowledge of Deep Learning and AI

Real-time video streaming mask detection based on Python. Designed to defeat COVID-19.

yolov3_radar_fusion

STM8s001j3 Software reading ADC values and controlling RGBW & power LED (for IAR Embedded Workbench)

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

make use of improved ros package for mmWave radar, finish raw data filter and position and velocity visualization of detected objects, and publish objects information.

VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residual (CVPR2020)

This project uses F103C8T6 MCU.