Stars
A simple demo of yolov5s running on rk3588/3588s using c++ (about 142 frames). / 一个使用c++在rk3588/3588s上运行的yolov5s简单demo(142帧/s)。
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
【A simple used C++ threadpool】一个简单好用，性能优异的，跨平台的C++线程池。欢迎 star & fork
rknn-3588部署yolov5，利用线程池实现npu推理加速；Deploying YOLOv5 on RKNN-3588, utilizing a thread pool to achieve NPU inference acceleration.
Code of "OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments".
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
An ROS implementation for paper "Curved-Voxel Clustering for Accurate Segmentation of 3D LiDAR Point Clouds with Real-Time Performance"
LiPC: LiDAR Point Cloud Clustering Benchmark Suite
A lidar perception system, including ground-filter, cluster, minbox, tracking and state estimation.
🚕 Fast and robust clustering of point clouds generated with a Velodyne sensor.
Kalman Filter C++ Implementation using Eigen Library
Header only C++ implementation of standard and extended Kalman filters.
Multiple Object Tracker, Based on Hungarian algorithm + Kalman filter.
A 3D detection Pointpillars ROS deployment on Nvidia Jetson TX1/Xavier
PointPillars TensorRT version pretrained on MMDetection3d with WaymoOpenDataset
convert hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d from mmdet3d to onnx
A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.
An automatic calibration algorithm for livox LiDAR
A REAL-TIME 3D detection network [Pointpillars] compiled by CUDA/TensorRT/C++.