A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8…

自动驾驶更新笔记，以解析各模块知识点、整合行业优秀解决方案进行阐述，以帮助自己及有需要的读者；包含 深度学习、deeplearning、无人驾驶、ADAS、 CVPR2022、特斯拉 AI DAY 等内容。由于水平有限，文中不妥之处恳请广大读者批评指正。 未完待续........ 如有合作意向，请联系 [email protected]；Roc 2022.10

An academic alternative to Tesla's occupancy network for autonomous driving.

A lightweight tool for labeling 3D bounding boxes in point clouds.

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

torch primitives for BEV style perception models for self driving tasks

Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline

A useful collection of CPP and PYTHON examples to learn ROS2 from zero

Make a minimal OpenCV runable on any where, WIP

An all-in-one toolkit for computer vision

yolov5 车牌检测 车牌识别 中文车牌识别 检测 支持13种中文车牌 支持双层车牌

A 3D detection Pointpillars ROS deployment on Nvidia Jetson TX1/Xavier

Our insights of Openpilot, a deepdive project on it

An open source library for face detection in images. The face detection speed can reach 1000FPS.

3D Point Cloud Annotation Platform for Autonomous Driving

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Lightweight DBSCAN for C++ for use with PCL pointclouds

Tips and tricks to optimize your C++ code

[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection

openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for over 200 supported car makes and models.

An open source advanced driver assistance system (ADAS) that uses Jetson Nano as the hardware. Features: Traffic sign detection, Forward collision warning, Lane departure warning.

Codes for “Fully Sparse 3D Object Detection” & “Embracing Single Stride 3D Object Detector with Sparse Transformer”

In this work, we proposed a framework for accurately predicting the object's pose based on the arrangement of parts. We apply this framework to estimate the yaw angle of vehicles, and we call it YA…

HybridNets: End-to-End Perception Network

OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving

Code for RA-L journal and IROS 2022 paper "DeepFusionMOT: A 3D Multi-Object Tracking Framework Based on Camera-LiDAR Fusion with Deep Association".

Official code for "Structured Bird’s-Eye-View Traffic Scene Understanding from Onboard Images" (ICCV 2021)