All Projects → fuenwang → 3d Boundingbox

fuenwang / 3d Boundingbox

PyTorch implementation for 3D Bounding Box Estimation Using Deep Learning and Geometry

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to 3d Boundingbox

DonkeyDrift
Open-source self-driving car based on DonkeyCar and programmable chassis
Stars: ✭ 15 (-84.21%)
Mutual labels:  car, self-driving-car
Autonomousdrivingcookbook
Scenarios, tutorials and demos for Autonomous Driving
Stars: ✭ 1,939 (+1941.05%)
Mutual labels:  self-driving-car, car
Self Driving Car
Automated Driving in NFS using CNN.
Stars: ✭ 105 (+10.53%)
Mutual labels:  self-driving-car, car
self-driving-car-nd
Udacity's Self-Driving Car Nanodegree project files and notes.
Stars: ✭ 50 (-47.37%)
Mutual labels:  car, self-driving-car
Genivi Dev Platform
GENIVI Development Platform
Stars: ✭ 81 (-14.74%)
Mutual labels:  car
Vehicle Detection
Vehicle detection using machine learning and computer vision techniques for Udacity's Self-Driving Car Engineer Nanodegree.
Stars: ✭ 1,093 (+1050.53%)
Mutual labels:  self-driving-car
Imbmw
BMW iBus .NET MF SDK and hardware
Stars: ✭ 50 (-47.37%)
Mutual labels:  car
Arduino Tachometer
Arduino car tachometer
Stars: ✭ 39 (-58.95%)
Mutual labels:  car
Kotlin Obd Api
🚙 A Kotlin OBD-II API for reading engine data
Stars: ✭ 91 (-4.21%)
Mutual labels:  car
Renault Radio Code List
List of all security codes required to activate Renault car radios.
Stars: ✭ 88 (-7.37%)
Mutual labels:  car
Advanced Lane Detection
An advanced lane-finding algorithm using distortion correction, image rectification, color transforms, and gradient thresholding.
Stars: ✭ 71 (-25.26%)
Mutual labels:  self-driving-car
Vehicle Detection And Tracking
Udacity Self-Driving Car Engineer Nanodegree. Project: Vehicle Detection and Tracking
Stars: ✭ 60 (-36.84%)
Mutual labels:  self-driving-car
Simulator
A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles
Stars: ✭ 1,260 (+1226.32%)
Mutual labels:  self-driving-car
Caranimation
A sample project about car animation in a route
Stars: ✭ 55 (-42.11%)
Mutual labels:  car
Lidarobstacledetection
Lidar Obstacle Detection
Stars: ✭ 90 (-5.26%)
Mutual labels:  self-driving-car
Uselfdrivingsimulator
Self-Driving Car Simulator
Stars: ✭ 48 (-49.47%)
Mutual labels:  self-driving-car
Didi challenge ros
Roslaunch to visualize a rosbag file from Udacity (DiDi Challenge)
Stars: ✭ 69 (-27.37%)
Mutual labels:  self-driving-car
Reinforcement Learning For Self Driving Cars
Project on design and implement neural network that maximises driving speed of self-driving car through reinforcement learning.
Stars: ✭ 85 (-10.53%)
Mutual labels:  self-driving-car
Node Bmw Client
A node.js powered interface for E38/E39/E53 + E6x/E9x BMW vehicles (Client side)
Stars: ✭ 68 (-28.42%)
Mutual labels:  car
Santosnet
A simple self driving car in GTAV that uses the Xception deep neural network model with DeepGTAV
Stars: ✭ 67 (-29.47%)
Mutual labels:  self-driving-car

3D Bounding Box Estimation Using Deep Learning and Geometry

Introduction

This repo is PyTorch implementation for this paper. In this paper, they collect KITTI 2D Object Dataset and introduce a flow to estimate object pose and dimension. If you are looking for TensorFlow implementation, here is a great repo.

Dependency

Usage

Before using this code, you need download data from KITTI and unzip it. After that, you need to add the kitti path of dataset to config.yaml.

kitti_path: somewhere # Root of kitti, where contrain trainning/ and testing/   

Also, you can set up parameters for training and weight of loss as describded in paper.

epochs: 8 # How many epoch for training?
bins: 2  # How many bins you want to split?
w: 0.8
alpha: 0.8
batches: 8             

After setting up, just type it for training

python Train.py

It will store model in ./models. For simple evaluation, type

python Eval.py

This will calculate average orientation and dimension error (in degree and meters).

Reference

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].