- Video Surveillance and Tracking Methods
- Fire Detection and Safety Systems
- Advanced Vision and Imaging
- Advanced MRI Techniques and Applications
- Sparse and Compressive Sensing Techniques
- Photoacoustic and Ultrasonic Imaging
- Smart Grid Energy Management
- Infrared Target Detection Methodologies
- Image Enhancement Techniques
- Impact of Light on Environment and Health
- Blind Source Separation Techniques
- Satellite Image Processing and Photogrammetry
- Electric Power System Optimization
- Energy Load and Power Forecasting
- Image Retrieval and Classification Techniques
- Advanced Adaptive Filtering Techniques
- Advanced Measurement and Detection Methods
- Vehicle License Plate Recognition
- Handwritten Text Recognition Techniques
- Image and Signal Denoising Methods
- Currency Recognition and Detection
- Neural Networks and Applications
- Power Line Communications and Noise
- Calibration and Measurement Techniques
- Smart Grid Security and Resilience
International Islamic University, Islamabad
2016-2023
The geographically spatial and controlled distribution of fossil fuel resources, catastrophic global warming, depletion resources have forced us to integrate zero- or low-emissions energy such as wind solar, in the generation mix. These renewable are unexhausted, available around globe, free cost. advancement solar technologies has caused an appreciable decrease installed levelized costs electricity via these sources. Therefore, penetration mix can provide a promising solution...
The traditional electric power system is examining a transformation process to an intelligent, efficient, and cost-effective smart grid (SG) system. SG has different subsystems for its accurate functionality. Among these subsystems, the communication subsystem plays vital role real-time data sharing between devices systems connected in domain. In this paper, survey of provided several technologies that have strong potential implementation future applications by utility companies are...
Urdu is a complex language as it an amalgam of many South Asian and East languages; hence, its character recognition huge difficult task. It bidirectional with numerals written from left to right while script in opposite direction which induces complexities the process. This paper presents classification novel numeral dataset using convolutional neural network (CNN) variants. We propose custom CNN model extract features are used by Softmax activation function support vector machine (SVM)...
Object tracking is still an intriguing task as the target undergoes significant appearance changes due to illumination, fast motion, occlusion and shape deformation. Background clutter numerous other environmental factors are major constraints which remain a riveting challenge develop robust effective algorithm. In present study, adaptive Spatio-temporal context (STC)-based algorithm for online proposed by combining context-aware formulation, Kalman filter, model learning rate. For...
Compressed Sensing (CS) theory breaks the Nyquist theorem through random under-sampling and enables us to reconstruct a signal from 10%-50% samples. Magnetic Resonance Imaging (MRI) is good candidate for application of compressed sensing techniques due i) implicit sparsity in MR images ii) inherently slow data acquisition process. In multi-slice MRI, strong inter-slice correlation has been exploited further scan time reduction interpolated (iCS). this paper, novel fast (FiCS) technique...
Visual object tracking (VOT) is a vital part of various domains computer vision applications such as surveillance, unmanned aerial vehicles (UAV), and medical diagnostics. In recent years, substantial improvement has been made to solve challenges VOT techniques change scale, occlusions, motion blur, illumination variations. This paper proposes algorithm in spatiotemporal context (STC) framework. To overcome the limitations STC based on scale variation, max-pooling-based scheme incorporated...
During recent years correlation tracking is considered fast and effective by the virtue of circulant structure sampling data for learning phase filter Fourier domain calculation correlation. occurrence occlusion, motion blur out view movement target, most based trackers start to learn using erroneous samples tracker starts drifting. Currently, adaptive algorithms are being combined with redetection modules. This hybridization helps in target long term tracking. The modules mostly classifier,...
Visual object tracking is still considered a challenging task in computer vision research society. The of interest undergoes significant appearance changes because illumination variation, deformation, motion blur, background clutter, and occlusion. Kernelized correlation filter- (KCF) based schemes have shown good performance recent years. accuracy robustness these trackers can be further enhanced by incorporating multiple cues from the response map. Response map computation complementary...
Noise cancellation algorithms have been frequently applied in many fields including image/video processing. Adaptive noise exploit the correlation property of and remove from input signal more effectively than non-adaptive algorithms. In this paper different techniques are to de-noise a video frame. Three variants gradient based adaptive filtering independent component analysis (ICA) procedure implemented compared on basis ratio (SNR) computational time. The common used filters least mean...
Despite eminent progress in recent years, various challenges associated with object tracking algorithms such as scale variations, partial or full occlusions, background clutters, illumination variations are still required to be resolved improved estimation for real-time applications. This paper proposes a robust and fast algorithm based on spatio-temporal context (STC). A pyramid representation-based correlation filter is incorporated overcome the STC’s inability rapid change of target. It...
Magnetic Resonance Imaging (MRI) is an important yet slow medical imaging modality. Compressed sensing (CS) theory has enabled to accelerate the MRI acquisition process using some nonlinear reconstruction techniques from even 10% of Nyquist samples. In recent years, interpolated compressed (iCS) further reduced scan time, as compared CS, by exploiting strong interslice correlation multislice MRI. this paper, improved efficient (EiCS) technique proposed radial undersampling schemes. The...
Magnetic Resonance Imaging (MRI) is used to produce detailed images of body tissues and organs using strong magnets radio waves, but with a very slow acquisition process. Compressed Sensing (CS) has efficiently accelerated the MRI process by employing different reconstruction strategies fraction Nyquist samples. This scan time can be further reduced new technique called interpolated compressed sensing (iCS) exploiting inter-slice correlation multi-slice MRI. In this paper, modified fast...
Correlation algorithm can directly match and locate low level features such as templates against similarly structured in a particular search area. However, the implementation of this template matching techniques have few problems which need to be addressed. One these is that it impaired when areas are severely distorted. In paper performance technique using shape similarity cross correlation studied relation known geometrical distortions imagery obtained from High Resolution Picture...