xiaojiean Goto Github PK
Type: User
Type: User
[CVPR'19] Dataset and code used in the research project Scan2CAD: Learning CAD Model Alignment in RGB-D Scans
The toolbox implements the data conversion from CAD models (such as .obj/.off file) to point cloud(surface voxels) with RGB value and labels.
Webpage for Selective Sensor Fusion
The Udacity open source self-driving car project
This nanodegree programs covered all the basic topics related to self-driving cars. Computer vision, deep learning, sensor fusion, localization, motion planning, control and systems integration.
SHAdow-Free Feature ExtractoR. "A Novel Shadow-Free Feature Extractor for Real-Time Road Detection" MM2016
sick_scan is an open-source project to support the laser scanner of the company SICK using the ROS-framework
A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles
Program that loads a character skin from a .skin file, skins a skeleton, and displays it in 3D. Allows for manipulation of 3 DOF rotational joints.
learning SLAM,curse,paper and others
This project includes monitoring temperature, humidity and moisture in agricultural field through sensors DHT11, YL69. It will turn ON/OFF motor on the basis of soil moisture and also visualise real time data by using ThingsBoard.
The Smart Mirror would help in developing smart houses with embedded artificial intelligence, as well as finding its applications in industries. Further, the mirror can also be used to control anything with your voice as it also gets Virtual Voice Assistant services.
Computerized systems being an integral part of the current era, an automated parking system is one of its most commonly used applications. The aim of this model is to build up and implement an automatic parking system that will detect the parking space with the help of image processing technique of the parking lot as well as reduce the human power. The smart parking system will able to have fewer interaction of humans. In additions to that, it has parking guidance system that can demonstrate and guide user towards a parking space. With the problems of ever increasing urban traffic congestion and the ever increasing shortage of space, the parking lots need to be well-equipped with parking space detection. The proposed system helps in counting the number of parked vehicles and, identifying the number of spots available. The system detects cars through images instead of electronic sensors embedded on the floors. A camera is installed at a high and fixed position in the parking lot. An image of empty parking lot is taken as reference and then image of parking lot with cars is taken. Both the images are subtracted to find the numbers of parking slots available.
Home surveillance systems available today notify homeowners of any motion detected by the cameras. This behavior leads to mostly false positives and annoying notifications. Worse, these systems suffer from the “one size fits all” approach and do not offer any ability to provide personalized feedback and make the notifications only appear for unknown persons and objects. The personalization can be based on the unique features of a home’s landscape, location and known persons and pets. Our team intends to address this gap. We are proposing to develop the building blocks for a smart home surveillance system. The system will use video streams from off-the-shelf outdoor IP cameras. It will analyze and interpret the content of the streams and employ feedback mechanisms to generate customizable notifications for the homeowner. We plan to implement an end to end pipeline that can detect objects and faces in the data streams in order to recognize unfamiliar faces, identify anomalous situations and notify the homeowner about the anomaly. The feedback loop will enable the system to improve its capabilities over time and generate notifications that are personalized for each homeowner.
Honours Thesis: Deanonymising Households Trading on a BlockchainSmart Grid
SmartHotel360 deployed Azure digital Twins to control lights and temperature of the hotel rooms.
A Low-cost Open-source High-speed Multi-camera Motion Capture System.
Source Code of Article "A Phase Congruency and Local Laplacian Energy Based Multi-Modality Medical Image Fusion Method in NSCT Domain"
SPFCN: Select and Prune the Fully Convolutional Networks for Real-time Parking Slot Detection
Surfel-based Mapping for 3d Laser Range Data (SuMa)
缺陷检测文献记录
📈 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.
An AR game that works on motor, balance and cognitive rehabilitation either in the hospital or at home.
Best (most accurate) trained LSTM models.
Global Texture Mapping for Dynamic Objects (Pacific Graphics 2019)
Automatic 2D Floorplan CAD Generation from 3D Point Clouds
Modify from https://github.com/eriklindernoren/PyTorch-YOLOv3 to support training with multi-GPUs
3D laser triangulation scanner using webcam and line laser
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.