Research and IP

Peer-reviewed evidence behind GaitAI.

Published work, patent protection, conference evidence, and technical depth across gait recognition, covariates, surveillance readiness, privacy, pose features, and deep learning pipelines.

0featured papers
0gait conferences
0research themes
0granted patent
Intellectual property

Granted patent connected to gait recognition and edge analytics.

Patent certificate preview from PDF

A Covariate-based Gait Recognition System and Method for Edge Analytics Using Optimized Deep Learning Pipeline

Indian Patent Granted, 2021

App No: 202111034240 | Filed: 29/07/2021 | Published: 27/08/2021

Strengthens the company moat around covariate-aware gait recognition, optimized deep learning pipelines, and edge analytics.

Publications

Featured gait intelligence papers.

Selected publications supporting the technology and commercial story.

8papers
Paper preview from PDF

Advancements in artificial intelligence for biometrics: A deep dive into model-based gait recognition techniques

Engineering Applications of Artificial Intelligence, 2024

Anubha Parashar and collaborators

A review of model-based gait recognition techniques connecting AI biometrics, pose representation, and real-world recognition constraints.

Paper preview from PDF

Deep Learning Pipelines for Recognition of Gait Biometrics with Covariates - A Comprehensive Review

Artificial Intelligence Review, 2022

Anubha Parashar and collaborators

A complete view of deep learning gait pipelines, from acquisition and preprocessing to covariate handling and recognition.

Paper preview from PDF

Real-time Gait Biometrics for Surveillance Applications: A Review

Image and Vision Computing, 2023

Anubha Parashar and collaborators

A deployment-oriented review focused on surveillance constraints such as camera viewpoint, occlusion, speed, and distance.

Paper preview from PDF

Preprocessing and feature selection in gait recognition

Pattern Recognition Letters, 2023

Anubha Parashar and collaborators

Supports feature engineering and signal-quality foundations for robust gait intelligence.

Paper preview from PDF

A journey into gait biometrics with deep learning

Digital Signal Processing, 2024

Anubha Parashar and collaborators

Connects signal processing, model design, and practical recognition for full-stack gait biometrics.

Paper preview from PDF

Intra-class Variations with Deep Learning-based Gait Analysis: A Comprehensive Survey of Covariates and Methods

Neurocomputing, 2022

Anubha Parashar and collaborators

Covers real-world variables such as view angle, clothing, carrying conditions, walking speed, and surface.

Paper preview from PDF

Protection of gait data set for preserving its privacy in deep learning pipeline

IET Biometrics, 2022

Anubha Parashar and collaborators

A privacy-preserving direction for biometric gait data handling.

Paper preview from PDF

A Robust Covariate-invariant Gait Recognition based on Pose Features

IET Biometrics, 2022

Anubha Parashar and collaborators

A pose-feature approach to covariate-invariant gait recognition.

Conference evidence

Gait-focused conference work across surveillance, pose, Parkinson's movement analysis, and locomotion classification.

2023Clothing attribute gait recognition

Deep Learning-based Framework for Accurate Clothing Attribute Recognition and Style Navigation for Gait Recognition

International Conference on Bio-engineering for Smart Technologies, 2023

Anubha Parashar, Apoorva Parashar, Imad Rida, Vidyadhar Aski et al.

Conference work linking clothing attributes and gait recognition, useful for real-world covariates where appearance changes affect movement-based identity systems.

2021Pose-based surveillance gait analysis

Optimized Pose-Based Gait Analysis for Surveillance

2nd International Conference on Innovations in Computational Intelligence and Computer Vision, Manipal University Jaipur, Aug 5-6, 2021

Apoorva Parashar, Anubha Parashar, Vidyadhar Aski

Pose-based gait analysis for surveillance, aligned with camera deployments where body landmarks and motion signatures are stronger signals than facial visibility.

2020Multi-view gait signatures

Surveillance System To Provide Secured Gait Signatures In Multi View Variations Using Deep Learning

International Conference on Modelling, Simulation & Intelligent Computing, BITS Dubai, Jan 29-31, 2020

Anubha Parashar, Apoorva Parashar, RS Shekhawat, Vidyadhar Aski

Multi-view gait signatures using deep learning, directly relevant to surveillance environments with changing camera angles and walking directions.

2018Parkinson gait features

Tracing Gesture and Extracting Gait Features to Recognize Parkinson's Disease Using Multi-layered Back Propagation Algorithm

International Conference on Innovative Technologies, Zagreb, Croatia, Sep 5-7, 2018

A. Parashar, RS. Shekhawat, A. Parashar

Best-paper conference work connecting gait features and neurological movement analysis, relevant to clinical mobility screening and medical motion analytics.

2018Human locomotion categories

Identification of gait data using machine learning technique to categories human locomotion

10th International Conference on Security of Information and Networks, Jaipur, India, Oct 13-15, 2018

A. Parashar, A. Parashar

Machine-learning work on identifying gait data and categorizing locomotion, supporting movement classification beyond identity recognition.

2016Gait data clustering

Clustering Gait Data using different machine learning techniques and finding the best technique

International Conference on Smart Trends for Information Technology and Computer Communications, Jaipur, India, Aug 6-7, 2016

Anubha Parashar, Deepak Goyal

Early gait-data clustering work comparing machine-learning approaches for grouping movement patterns and extracting useful locomotion structure.

2016Gait data classification

Classifying Gait Data using different machine learning techniques and finding the optimum technique of classification

International Conference on ICT for Sustainable Development, Panaji, Goa, India, Jul 1-2, 2016

A. Parashar, A. Parashar

Foundational gait classification work comparing machine-learning techniques for selecting reliable movement-recognition methods.