IMC Lab
DisasterNet: Disaster Event & Human Pose Recognition
Attention-Driven Framework with Hierarchical Feature Fusion
Ahmad Jalal Ishrat Zahra
Project Overview
An attention-driven framework for simultaneous disaster event classification and human pose estimation in emergency scenes using hierarchical feature fusion with deep ConvLSTM. The system processes multi-scale features through attention mechanisms for real-time identification of disaster types and victim poses.
System Architecture
Inputs
Aerial Footage
Pose Frames
Processing Pipeline
Attention Module
Hierarchical Fusion
ConvLSTM Network
Multi-Task Head
Outputs
Disaster Type
Victim Pose
Related Publications (8)
Curated from publications by Professor Dr. Hafiz Ahmad Jalal
2025journal
Human Pose Estimation and Event Recognition via Feature Extraction and Neuro-Fuzzy Classifier
IEEE Access, 2025
View on Scholar2025conference
SKEP-Net: Depth-based Human Pose Monitoring and Exercise Recognition using GMM- Segmentation
ICECT\'25, 2025
View on Scholar2024conference
Robust human pose estimation and action recognition over multi-level perceptron
2024 26th International Multi-Topic Conference (INMIC), 1-6, 2024
View on Scholar2024conference
Advanced Gait Event Recognition and Pose Estimation Model through Deep Learning
ICIT24, 2024
View on Scholar2024conference
A Novel Sports Event Recognition using Pose Estimation and Multi-Fused Features
ETECTE\'24, 2024
View on Scholar2020journal
Pose Estimation and Detection for Event Recognition using Sense-Aware Features and Adaboost Classifier
IBCAST, 2020
View on Scholar2015conference
A spatiotemporal motion variation features extraction approach for human tracking and pose-based action recognition
IEEE International Conference on Informatics, electronics and vision, 2015
View on Scholar2014conference
Dense Depth Maps-based Human Pose Tracking and Recognition in Dynamic Scenes Using Ridge Data
International Conference on Advanced Video and Signal-Based Surveillance+�n++ +�G�-�, 2014
View on Scholar