RTD Dataset

Air Writing is a new writing technique where the character is written in the air and the character is recognized by the computer or mobile phone. Air writing is different from traditional writing style.

Writing in the air can be defined as to write digit or character in a 3D space by using a finger or marker movement. Air-writing is different from the traditional writing style.  Due to the extensive improvement of sensor technologies, it has become prominent to track finger and joint precisely.

We have collected 20k trajectory data from various people. An Intel RealSense SR300 camera has been used to collect the data. We have named this RealSense based 3D trajectory digit dataset as RTD.

The coordinate system for the RealSense camera is shown above. Z-axis is towards the observer.

Download Dataset: Google Drive, Dropbox

Understanding datasets:

The dataset contains two files. One is for the feature and the other one is for the label.

label: The label is a one-hot vector.


Features: Contains the original data as a sequence of trajectory. Each tuple represents one feature. The sequence is stored as :

Here n is the length of that sequence.

How to use this dataset:

The data has been published in binary form. You have to pickle it first. If you don’t know how to pickle, no problem, here is the sample code –

import numpy as np
import pickle

#opening features
with open(‘features’, ‘rb’) as fp:

#opening labels
with open(‘labels’, ‘rb’) as fp:

Original Research Paper

AUTHOR = {Alam, Md. Shahinur and Kwon, Ki-Chul and Alam, Md. Ashraful and Abbass, Mohammed Y. and Imtiaz, Shariar Md and Kim, Nam},
TITLE = {Trajectory-Based Air-Writing Recognition Using Deep Neural Network and Depth Sensor},
JOURNAL = {Sensors},
VOLUME = {20},
YEAR = {2020},
NUMBER = {2},
URL = {https://www.mdpi.com/1424-8220/20/2/376},
ISSN = {1424-8220},
ABSTRACT = {Trajectory-based writing system refers to writing a linguistic character or word in free space by moving a finger, marker, or handheld device. It is widely applicable where traditional pen-up and pen-down writing systems are troublesome. Due to the simple writing style, it has a great advantage over the gesture-based system. However, it is a challenging task because of the non-uniform characters and different writing styles. In this research, we developed an air-writing recognition system using three-dimensional (3D) trajectories collected by a depth camera that tracks the fingertip. For better feature selection, the nearest neighbor and root point translation was used to normalize the trajectory. We employed the long short-term memory (LSTM) and a convolutional neural network (CNN) as a recognizer. The model was tested and verified by the self-collected dataset. To evaluate the robustness of our model, we also employed the 6D motion gesture (6DMG) alphanumeric character dataset and achieved 99.32% accuracy which is the highest to date. Hence, it verifies that the proposed model is invariant for digits and characters. Moreover, we publish a dataset containing 21,000 digits; which solves the lack of dataset in the current research.},
DOI = {10.3390/s20020376}

Link: https://doi.org/10.3390/s20020376

Thank you for showing interest in this research.