A5086073362- Human Pose and Action Recognition
- Video Surveillance and Tracking Methods
- Anomaly Detection Techniques and Applications
- Context-Aware Activity Recognition Systems
- Gait Recognition and Analysis
- Digital Media Forensic Detection
- Video Analysis and Summarization
- Generative Adversarial Networks and Image Synthesis
- Advanced Image and Video Retrieval Techniques
- Remote-Sensing Image Classification
- Semiconductor materials and devices
- Multimodal Machine Learning Applications
- Advanced Steganography and Watermarking Techniques
- Advancements in Semiconductor Devices and Circuit Design
- IoT and Edge/Fog Computing
- Remote Sensing and Land Use
- Advanced Image Fusion Techniques
- Brain Tumor Detection and Classification
- Image Enhancement Techniques
- AI in cancer detection
- Hand Gesture Recognition Systems
- Antenna Design and Analysis
- Advanced Vision and Imaging
- Coronary Interventions and Diagnostics
- Advanced Antenna and Metasurface Technologies
Guru Ghasidas Vishwavidyalaya
2020-2025
The University of Adelaide
2021-2025
Indian Institute of Technology Mandi
2024
Uttarakhand Technical University
2024
Chhattisgarh Kamdhenu Vishwavidyalaya
2024
Punjab Technical University
2017-2020
Indian Institute of Technology BHU
2012-2018
GLA University
2012-2017
Banaras Hindu University
2012-2016
Indian Institute of Technology Delhi
2015
Food preservation has been practised in many parts of the world for thousands years, and it applies to a wide range foods, including fruits, vegetables, cereals, meat. techniques are canning, freezing, pickling, curing (smoking or salting), drying. spoilage caused by moisture is growth mould, yeast, bacteria, enzymes food. The drying process removes enough from food significantly reduce humidity level’s likelihood these adverse outcomes. material's content measures how much present that...
Recognition of the human activities in videos has gathered numerous demands various applications computer vision such as Ambient Assisted Living, intelligent surveillance, Human Computer interaction. One most pioneering technique for Activity is based upon deep learning and this paper focuses on approaches that. Convolution Neural Network Recurrent Networks are mostly used architectures. Deep Learning have capacity automatic features from input modality. Analysis Methodology, Accuracy,...
Object Tracking is an important task in video processing because of its variety applications visual surveillance, human activity monitoring and recognition, traffic flow management etc. Multiple object detection tracking outdoor environment a challenging the problems raised by poor lighting conditions, variation poses object, shape, size, clothing, This paper proposes novel technique for multiple objects video. A classifier trained using Haar-like features from training image set. Human are...
Abstract Recognizing entities and their corresponding roles are important in human activity recognition. In light of recent advancements, the primary emphasis is recognizing abstract activities involving person‐person interaction. The contribution this work proposing an architecture, which utilizes knowledge body parts coordinates role detection each individual. network preprocesses to build intra‐body inter‐body features. extracted features relationship between interacting bodies learn...
In this paper, design and implantations of terahertz rectangular DRA using HFSS simulator have been presented. The aspect ratio has played deterministic role for desired resonant modes excitation at frequencies. antenna operates 10 THz, hence can be used high speed communications sensors. Design is simple due to geometry, efficient use DR, unique silicon as radiator.Mathematical modeling THz frequency Terahertz also presented along with simulations results S11 below -10dB , Gain 4.89 dBi...
Motion segmentation is a crucial step for video analysis and has many applications. This paper proposes method motion segmentation, which based on construction of statistical background model. Variance Covariance pixels are computed to construct the model scene background. We perform average frame differencing with this extract objects interest from frames. Morphological operations used smooth object results. The proposed technique adaptive dynamically changing because change in lighting...
Human activity recognition is an active research topic in computer vision due to its applicability wide range of application areas such as smart surveillance, robot learning, human interaction, health assessment. Identifying activities from video sequences constitutes one the most challenging tasks field vision, especially harsh nature real-world scenarios and high volumes data that need be worked upon. The techniques available literature for are broadly classified into two categories:...
In the last few decades, Human Activity Recognition (HAR) has been a centre of attraction in many research domains, and it is referred to as potential interpreting human body gestures through sensors ascertaining activity being. The present work proposed voting classifier system for recognition. For system, five machine learning classifiers are considered: Logistic Regression (LR), K-Nearest Neighbour (KNN), Random Forest (RF), Naive Bayes (NB), Support Vector Machine (SVM). These ensembled...