Skip to main content
Intelligent Media Center (IMC)
HomeIMC LabProject 10
IMC Lab

Vision Sensor for Human Activity Recognition via Hybrid Features

HOG + LBP + Optical Flow with Multi-Class SVM

Ahmad Jalal Saleha Kamal Junaid Javid

Project Overview

HOG, LBP and Optical Flow hybrid features with multi-class SVM for vision-based human activity recognition from RGB cameras. The system extracts complementary descriptors capturing shape, texture, and motion information for recognizing activities such as walking, running, sitting, and gesturing.

System Architecture

RGB Video
HOG Descriptor
LBP Texture
Optical Flow
Multi-Class SVM
Activity Class
Confidence

Related Publications (8)

Curated from publications by Professor Dr. Hafiz Ahmad Jalal

2025journal

Vision Sensor for Automatic Recognition of Human Activities via Hybrid Features and Multi-class SVM

K Saleha, A Haifa F, A Mohammed, A Mohammed, A Hanan, J Ahmad, ...

Sensors, 2025

View on Scholar
2025journal

IoT-based Multisensors Fusion for Activity Recognition via Key Features and Hybrid Transfer Learning

J Ahmad, K Danyal, S Touseef, A Moneerah, A Sultan Refa, A Hanan, ...

IEEE Access, 2025

View on Scholar
2016journal

Human depth sensors-based activity recognition using spatiotemporal features and hidden markov model for smart environments

A Jalal, S Kamal, D Kim

Journal of computer networks and communications 2016, 1-11, 2016

View on Scholar
2015conference

Human daily activity recognition with joints plus body features representation using Kinect sensor

A Jalal, Y Kim, S Kamal, A Farooq, D Kim

IEEE International Conference on Informatics, electronics and vision, 2015

View on Scholar
2016journal

A hybrid feature extraction approach for human detection, tracking and activity recognition using depth sensors

S Kamal, A Jalal

Arabian Journal for Science and Engineering (Springer), 2016

View on Scholar
2024conference

Wearable Sensor-Based Activity Recognition over Statistical Features Selection and MLP Approach

N Fakhra, J Ahmad

ETECTE, 2024

View on Scholar
2026journal

Multimodal Healthcare System for Human Activity Recognition using Multiple Features and Advanced Ensemble Classifier

N Fakhra, W Yanfeng, A Hanan, J Ahmad, L Hui

Digital Health, 2026

View on Scholar
2019conference

Multi-features descriptors for human activity tracking and recognition in Indoor-outdoor environments

A Jalal, M Maria, A Hasan

IEEE International Conference on Applied Sciences and Technology, 2019

View on Scholar