shadan khattak | COMSATS Institute of Information Technology (original) (raw)

Papers by shadan khattak

IEEE Signal Processing Letters, 2013

View synthesis prediction (VSP) is a coding mode that predicts video blocks from synthesised fram... more View synthesis prediction (VSP) is a coding mode that predicts video blocks from synthesised frames. It is particularly useful in a multi-camera setup with large inter-camera distances. Adding a VSP-based SKIP mode to a standard Multiview Video Coding (MVC) framework improves the rate-distortion (RD) performance but increases the time complexity of the encoder. This letter proposes an early mode decision technique for VSP SKIP-enhanced MVC. Our method uses the correlation between the RD costs of the VSP SKIP mode in neighbouring views and Bayesian decision theory to reduce the number of candidate coding modes for a given macroblock. Simulation results showed that our technique can save up to 36.20% of the encoding time without any significant loss in RD performance.

CRC Press eBooks, Jun 10, 2022

IEEE Sensors Journal, 2020

2019 International Conference on Applied and Engineering Mathematics (ICAEM), 2019

Automatic License Plate Detection (ALPD) is a crucial step, which significantly affects the recog... more Automatic License Plate Detection (ALPD) is a crucial step, which significantly affects the recognition rate and speed of the Intelligent Transport System (ITS). This paper presents a robust license plate detection method using an intelligent combination of Faster R-CNN and image processing operations. In the proposed method, initially, a vehicle is detected in the input colored RGB images using the Faster R-CNN. Next, the image with detected vehicle is fed to our developed License Plate Localization Module (LPLM) to search the possible existence of the license plate. The LPLM converts the detected vehicle image from RGB to the HSV domain and applies color segmentation along with morphological operations, and finally uses the dimensions analysis to locate the license plate. Simulations on the challenging PKU dataset reveal that the proposed technique outperforms recent state-of-the-art methods in terms of detection accuracy, precision, recall, and execution time.

Face images that appear in multimedia applications, such as digital entertainments usually exhibi... more Face images that appear in multimedia applications, such as digital entertainments usually exhibit dramatic nonuniform illumination, occlusions, low-resolution, and pose/expression variations that result in substantial performance degradation for traditional face recognition algorithms. Recent research is focused to develop robust face recognition algorithms to solve the aforementioned issues with maximum effort to mimic the human vision system. This paper presents a near real-time and novel face recognition method to recognize the occluded and low-resolution face images. Proposed face recognition algorithm initially uses 68 points to locate a face in the input image. Meanwhile, the adaptive boosting and Linear Discriminant Analysis (LDA) are used to extract face features. In the final stage, classic nearest centre classifier is used for face classification. Detailed experiments are performed on two publicly available LFW and the AR databases. Simulation results reveal that the prop...

2017 International Multi-topic Conference (INMIC), 2017

Symmetry, 2019

The Multi-View extension of High Efficiency Video Coding (MV-HEVC) has improved the coding effici... more The Multi-View extension of High Efficiency Video Coding (MV-HEVC) has improved the coding efficiency of multi-view videos, but this comes at the cost of the extra coding complexity of the MV-HEVC encoder. This coding complexity can be reduced by efficiently reducing time-consuming encoding operations. In this work, we propose two methods to reduce the encoder complexity. The first one is Early Coding unit Splitting (ECS), and the second is the Efficient Reference Picture Selection (ERPS) method. In the ECS method, the decision of Coding Unit (CU) splitting for dependent views is made on the CU splitting information obtained from the base view, while the ERPS method for dependent views is based on selecting reference pictures on the basis of the temporal location of the picture being encoded. Simulation results reveal that our proposed methods approximately reduce the encoding time by 58% when compared with HTM (16.2), the reference encoder for MV-HEVC.

IEEE Transactions on Circuits and Systems for Video Technology, 2016

Multiview plus depth (MVD) is an emerging video format with many applications, including 3D telev... more Multiview plus depth (MVD) is an emerging video format with many applications, including 3D television and free viewpoint television. During broadcast of compressed MVD video, transmission errors may cause the loss of whole frames, resulting in significant degradation of video quality. Error concealment techniques have been widely used to deal with transmission errors in video communication. However, the existing solutions do not address the requirement that the reconstructed frames be consistent with neighbouring frames, i.e., corresponding pixels have consistent color information. We propose a new consistency model for error concealment of MVD video that allows to maintain a high level of consistency between frames of the same view (temporal consistency) and those of neighbouring views (inter-view consistency). We then propose an algorithm that uses our model to implement concealment in a consistent way. Simulations with the reference software for the Multiview Video Coding project of the Joint Video Team (JVT) of the ISO/IEC MPEG and ITU-T VCEG show that our method outperforms benchmark techniques, including a baseline approach based on the Boundary Matching Algorithm, with respect to both reconstruction quality and view consistency.

2012 Picture Coding Symposium, 2012

Keywords: LTS4 Reference EPFL-CONF-174803 Record created on 2012-02-09, modified on 2017-05-10

Signal Processing: Image Communication, 2013

Multiview Video Coding (MVC) is a technique that permits efficient compression of multiview video... more Multiview Video Coding (MVC) is a technique that permits efficient compression of multiview video. MVC uses variable block size motion and disparity estimation for block matching. This requires an exhaustive search process that involves all possible macroblock partition sizes. We analyze the time complexity of MVC and the methods that have been proposed to speed up motion and disparity estimation. We then propose two new methods: Previous Disparity Vector Disparity Estimation (PDV-DE) and Stereo-Motion Consistency Constraint Motion and Disparity Estimation (SMCC-MDE). PDV-DE exploits the correlation between temporal levels and disparity vectors to speed up the disparity estimation process while SMCC-MDE exploits the geometrical relationship of consecutive frame pairs to speed up motion and disparity estimation. We build a complete low complexity MVC encoding solution that combines our two methods with complementary previous methods to speed up motion and disparity search. We evaluate the complexity of our solution in terms of encoding time and number of search points. Our experimental results show that our solution can reduce the encoding time and number of search points of the standard MVC implementation (JMVM 6.0) using the fast TZ search mode by up to 93.7% and 96.9%, respectively, with negligible degradation in the rate-distortion performance. Compared to the best published results, this is an improvement of up to 11% and 7%, respectively.

Electronics

Static Random-Access Memory (SRAM)-based Field Programmable Gate Arrays (FPGAs) are increasingly ... more Static Random-Access Memory (SRAM)-based Field Programmable Gate Arrays (FPGAs) are increasingly being used in many application domains due to their higher logic density and reconfiguration capabilities. However, with state-of-the-art FPGAs being manufactured in the latest technology nodes, reliability is becoming an important issue, particularly for safety-critical avionics, automotive, aerospace, industrial robotics, medical, and financial systems. Therefore, fault tolerant system design methodologies have become essential in the aforementioned application domains. The Isolation Design Flow (IDF) is one such design methodology that has promising prospects due to its ability to isolate logic design modules at the physical level for fault containment purposes. This paper proposes a methodology to evaluate the effectiveness of the IDF. To do so, reverse engineering is used to enable fault injection on the IDF designs with minimal changes in the bit-stream. This reduces the time neede...

IEEE Transactions on Very Large Scale Integration (VLSI) Systems