Regression-based convolutional 3D pose estimation from single image

, Article Electronics Letters ; Volume 54, Issue 5 , March , 2018 , Pages 292-293 ; 00135194 (ISSN) Ershadi Nasab, S ; Kasaei, S ; Sanaei, E ; Sharif University of Technology

Institution of Engineering and Technology 2018

Abstract

Estimation of 3D human pose from a single image is a challenging task because of ambiguities in projection from 3D space to the 2D image plane. A new two-stage deep convolutional neural network-based method is proposed for regressing the distance and angular difference matrices among body joints. Using the angular difference between body joints in addition to the distance between them in articulated objects such as human body can better model the structure of the shapes and increases the modelling capability of the learning method. Experimental results on HumanEva I and Human3.6M datasets show that the proposed method has substantial improvement in the mean per joint position error measure...

Uncalibrated multi-view multiple humans association and 3D pose estimation by adversarial learning

, Article Multimedia Tools and Applications ; 2020 Ershadi Nasab, S ; Kasaei, S ; Sanaei, E ; Sharif University of Technology

Springer 2020

Abstract

Multiple human 3D pose estimation is a useful but challenging task in computer vison applications. The ambiguities in estimation of 2D and 3D poses of multiple persons can be verified by using multi-view frames, in which the occluded or self-occluded body parts of some persons might be visible in other camera views. But, when cameras are moving and uncalibrated, estimating the association of multiple human body parts among different camera views is a challenging task. This paper presents novel methods for multiple human 3D pose estimation and pose association in multi-view camera frames in an uncalibrated camera setup using an adversarial learning framework. The generator is a 3D pose...

Uncalibrated multi-view multiple humans association and 3D pose estimation by adversarial learning

, Article Multimedia Tools and Applications ; Volume 80, Issue 2 , 2021 , Pages 2461-2488 ; 13807501 (ISSN) Ershadi Nasab, S ; Kasaei, S ; Sanaei, E ; Sharif University of Technology

Springer 2021

Abstract

Multiple human 3D pose estimation is a useful but challenging task in computer vison applications. The ambiguities in estimation of 2D and 3D poses of multiple persons can be verified by using multi-view frames, in which the occluded or self-occluded body parts of some persons might be visible in other camera views. But, when cameras are moving and uncalibrated, estimating the association of multiple human body parts among different camera views is a challenging task. This paper presents novel methods for multiple human 3D pose estimation and pose association in multi-view camera frames in an uncalibrated camera setup using an adversarial learning framework. The generator is a 3D pose...

Multiple human 3D pose estimation from multiview images

, Article Multimedia Tools and Applications ; Volume 77, Issue 12 , June , 2018 , Pages 15573-15601 ; 13807501 (ISSN) Ershadi Nasab, S ; Noury, E ; Kasaei, S ; Sanaei, E ; Sharif University of Technology

Springer New York LLC 2018

Abstract

Multiple human 3D pose estimation is a challenging task. It is mainly because of large variations in the scale and pose of humans, fast motions, multiple persons in the scene, and arbitrary number of visible body parts due to occlusion or truncation. Some of these ambiguities can be resolved by using multiview images. This is due to the fact that more evidences of body parts would be available in multiple views. In this work, a novel method for multiple human 3D pose estimation using evidences in multiview images is proposed. The proposed method utilizes a fully connected pairwise conditional random field that contains two types of pairwise terms. The first pairwise term encodes the spatial...

Multiple human 3D pose estimation from multiview images

, Article Multimedia Tools and Applications ; 2017 , Pages 1-29 ; 13807501 (ISSN) Ershadi Nasab, S ; Noury, E ; Kasaei, S ; Sanaei, E ; Sharif University of Technology

2017

Abstract

Multiple human 3D pose estimation is a challenging task. It is mainly because of large variations in the scale and pose of humans, fast motions, multiple persons in the scene, and arbitrary number of visible body parts due to occlusion or truncation. Some of these ambiguities can be resolved by using multiview images. This is due to the fact that more evidences of body parts would be available in multiple views. In this work, a novel method for multiple human 3D pose estimation using evidences in multiview images is proposed. The proposed method utilizes a fully connected pairwise conditional random field that contains two types of pairwise terms. The first pairwise term encodes the spatial...

3D Reconstruction of Human Pose in Multi-View Dynamic Scenes

, Ph.D. Dissertation Sharif University of Technology Ershadi Nasab, Sara (Author) ; Sanaei, Esmaeil (Supervisor) ; Kasaei, Shohreh (Co-Advisor)

Abstract

In this thesis, 3D pose reconstruction of one or multiple humans in multi-view dynamic scene is considered. Inputs are multi-view frames of multi-view camera systems. Outputs are the 3D reconstructed human poses in 3D space. The pose is the location of 14 human body joints in the 3D space. In this research, it is not allowed to use Kinect sensor data or other Markers or GPS sensors. It is supposed that only multi-view images are used. 3D reconstruction of human body pose can be performed with different assumptions. For example, the scene is indoor only or the camera calibration information is provided at first.Cameras are moving or fixed. In this research, each of this assumption is regarded...

LESS-MICS: A low energy standby-sparing scheme for mixed-criticality systems

, Article IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems ; Volume 39, Issue 12 , 2020 , Pages 4601-4610 Safari, S ; Hessabi, S ; Ershadi, G ; Sharif University of Technology

Institute of Electrical and Electronics Engineers Inc 2020

Abstract

Multicore platforms are becoming the dominant trend in mixed-criticality systems (MCSs). Multicores provide great opportunities to realize task-level redundancy for reliability enhancement. However, they may experience limited utility in battery-powered mixed-criticality embedded systems. Hence, joint energy and reliability management is a crucial issue in designing MCSs. In this article, we propose the low energy standby-sparing mechanism in mixed-criticality system (LESS-MICS) scheme, which uses the inherent redundancy of multicores to apply the standby-sparing technique for fault-tolerance. Also, by using the inherent redundancy, the LESS-MICS scheme proposes the Parallelism and Reduction...

RGB-D scene segmentation with conditional random field

, Article 2014 6th Conference on Information and Knowledge Technology, IKT 2014 ; 2014 , pp. 134-139 ; ISBN: 9781479956609 Nasab, S. E ; Kasaei, S ; Sanaei, E ; Sharif University of Technology

2014

Abstract

Segmentation of a scene to the part made is a challenging work. In this paper a graphical model is used for this task. The methods based on geometrical derivatives such as curvature and normal often haven't good result in segmentation of geometrically-complex architecture and lead to over-segmentation and even failure. Proposed method for segmentation contains two steps. At first region growing based on curvature, normal and color is used for growing region. This segmented cloud is used for unary potential in graphical model. Fully connected graph for Conditional Random Field with Gaussian kernel for pair wise potentials is used for correcting this segmentation. Gaussian kernels are based on...

Thermal stresses and kinetics of phase transformation on the run-out table after hot strip rolling of low-carbon steels

, Article International Journal of Advanced Manufacturing Technology ; Volume 83, Issue 9-12 , 2016 , Pages 1725-1736 ; 02683768 (ISSN) Hasan Nasab, M ; Serajzadeh, S ; Sharif University of Technology

2016

Abstract

A thermo-elastic analysis coupled with a phase change model is employed to evaluate thermal stresses as well as progress of austenite decomposition after hot strip rolling operations. The thermo-mechanical finite element analysis is utilized to assess the distributions of temperature and thermal stresses during cooling while at the same time, a model based on the additivity rule is used to determine the rate of austenite to ferrite decomposition. The proposed model is applicable to multi-pass rolling schedules while the effects of different process parameters including the rolling speed and cooling configuration of the run-out table can be taken into account. In order to verify the...

A Multi-Output high voltage dc power supply with fast regenerative rectifier

, Article 26th Iranian Conference on Electrical Engineering, ICEE 2018, 8 May 2018 through 10 May 2018 ; 2018 , Pages 1264-1268 ; 9781538649169 (ISBN) Naghibi Nasab, J ; Kaboli, S ; Sharif University of Technology

Institute of Electrical and Electronics Engineers Inc 2018

Abstract

A major problem in a multiple output converter structure is the different power flow via its various outputs. This problem leads to unwanted input DC-link voltage. This paper studies full bridge based DC-DC converters with multiple outputs. The effect of power flow variation is studied and a regenerative converter topology which controls the DC-link voltage by space voltage vector modulation technique is proposed. The proposed converter has a fast response to control the DC-link voltage in an acceptable band. Simulation and experimental results are presented to verify the analytical studies. © 2018 IEEE

New half-pixel accuracy motion estimation algorithms for low bitrate video communications

, Article Scientia Iranica ; Volume 15, Issue 6 , 2008 , Pages 507-516 ; 10263098 (ISSN) Mahdavi Nasab, H ; Kasaei, S ; Sharif University of Technology

Sharif University of Technology 2008

Abstract

Fractional-pixel accuracy Motion Estimation (ME) has been shown to result in higher quality reconstructed image sequences in hybrid video coding systems. However, the higher quality is achieved by notably increased Motion Field (MF) bitrate and more complex computations. In this paper, new half-pixel block matching ME algorithms are proposed to improve the rate-distortion characteristics of low bitrate video communications. The proposed methods tend to decrease the required video bandwidth, while improving the motion compensation quality. The key idea is to put a deeper focus on the search origin of the ME process, based on center-bias characteristics of low bitrate video MFs. To employ the...

Half-pixel accuracy block matching motion estimation algorithms for low bitrate video communications

, Article First IEEE and IFIP International Conference in Central Asia on Internet, 2005, Bishkek, 26 September 2005 through 28 September 2005 ; Volume 2005 , 2005 ; 0780391799 (ISBN); 9780780391796 (ISBN) Mahdavi Nasab, H ; Kasaei, S ; Sharif University of Technology

2005

Abstract

Motion estimation at fractional-pixel accuracy results in higher quality video sequences. However, the higher quality is achieved by more computations and increased required motion field bitrates. In this paper, new half-pixel accuracy block matching-based motion estimation algorithms are proposed to improve the rate-distortion characteristics of low-bitrate video communications. The proposed methods especially tend to decrease the required video bandwidth, with no degradation in quality of reconstructed image sequences. The key idea is to put a deeper focus on the origin (zero motion) based on the center-bias characteristics of low bitrate video motion fields. The experimental results show...

An efficient adaptive interpolation scheme for fast mesh-based motion estimation

, Article First IEEE and IFIP International Conference in Central Asia on Internet, 2005, Bishkek, 26 September 2005 through 28 September 2005 ; Volume 2005 , 2005 , Pages 4-7 ; 0780391799 (ISBN); 9780780391796 (ISBN) Mahdavi Nasab, H ; Kasaei, S ; Sharif University of Technology

IEEE Computer Society 2005

Abstract

Motion estimation and compensation is an essential part of existing video coding systems. Compared to the widely used block-matching algorithms (BMA), the mesh-based motion estimation (MME) produces better subjective and objective qualified image sequences in many cases, especially at low bitrates. However, the iterative refinement step of the MME is computationally too expensive. In this paper, we propose a fast MME scheme, which adjusts its interpolation patterns to the motion features of image sequences to achieve higher quality reconstructed results. Experimental results show notable rate-distortion improvement over both the BMA and the conventional non-iterative MME schemes, especially...

An efficient inference in meanfield approximation by adaptive manifold filtering: (Machine learning & data mining)

, Article Proceedings of the 4th International Conference on Computer and Knowledge Engineering, ICCKE 2014 ; 2014 , p. 581-585 Nasab, S. E ; Ramezanpur, S ; Kasaei, S ; Sanaei, E ; Sharif University of Technology

2014

Abstract

A new method for speeding up the approximate maximum posterior marginal (MPM) inference in meanfield approximation of a fully connected graph is introduced. Weight of graph edges is measured by mixture of Gaussian kernels. This fully connected graph is used for segmentation of image data. The bottleneck of the inference in meanfield approximation is where the similar bilateral filtering is needed for updating the marginal in the message passing step. To speed up the inference, the adaptive manifold high dimensional Gaussian filter is used. As its time complexity is 0(ND), it leads to accelerating the marginal update in the message passing step. Its time complexity is linear and relative to...

On the scheduling of energy-aware fault-tolerant mixed-criticality multicore systems with service guarantee exploration

, Article IEEE Transactions on Parallel and Distributed Systems ; Volume 30, Issue 10 , 2019 , Pages 2338-2354 ; 10459219 (ISSN) Safari, S ; Ansari, M ; Ershadi, G ; Hessabi, S ; Sharif University of Technology

IEEE Computer Society 2019

Abstract

Advancement of Cyber-Physical Systems has attracted attention to Mixed-Criticality Systems (MCSs), both in research and in industrial designs. As multicore platforms are becoming the dominant trend in MCSs, joint energy and reliability management is a crucial issue. In addition, providing guaranteed service level for low-criticality tasks in critical mode is of great importance. To address these problems, we propose LETR-MC scheme that simultaneously supports certification, energy management, fault-tolerance, and guaranteed service level in mixed-criticality multicore systems. In this paper, we exploit task-replication to not only satisfy reliability requirements, but also to improve the QoS...

Economic and economic-statistical designs of phase II profile monitoring

, Article Quality and Reliability Engineering International ; Vol. 30, issue. 5 , July , 2014 , pp. 645-655 ; ISSN: 07488017 Noorossana, R ; Niaki, S. T. A ; Ershadi, M. J ; Sharif University of Technology

2014

Abstract

In economic design of profiles, parameters of a profile are determined such that the total implementation cost is minimized. These parameters consist of the number of set points, n, the interval between two successive sampling, h, and the parameters of a control chart used for monitoring. In this paper, the Lorenzen-Vance cost function is extended to model the costs associated with implementing profiles. The in-control and the out-of-control average run lengths, ARL0 and ARL1, respectively, are used as two statistical measures to evaluate the statistical performances of the proposed model. A genetic algorithm (GA) is developed for solving both the economic and the economic-statistical...

A particle swarm optimization approach on economic and economic-statistical designs of MEWMA control charts

, Article Scientia Iranica ; Volume 18, Issue 6 , December , 2011 , Pages 1529-1536 ; 10263098 (ISSN) Niaki, S. T. A ; Malaki, M ; Ershadi, M. J ; Sharif University of Technology

2011

Abstract

Control charts are the best tools to monitor main process parameters, and the Multivariate Exponentially Weighted Moving Average, MEWMA, type of this tool is used when there are several correlated quality characteristics to be monitored simultaneously where detecting small deviations of the characteristics is desired. In this paper, the models of both the economic and the economic-statistical design problems of MEWMA control charts are solved by a Particle Swarm Optimization (PSO) approach. The comparison study between the economic and the economic-statistical designs shows better statistical performances of the economic-statistical design with negligible increase in cost. Furthermore, in...

Economic-statistical design of simple linear profiles with variable sampling interval

, Article Journal of Applied Statistics ; Volume 43, Issue 8 , 2016 , Pages 1400-1418 ; 02664763 (ISSN) Ershadi, M. J ; Noorossana, R ; Akhavan Niaki, S. T ; Sharif University of Technology

Taylor and Francis Ltd 2016

Abstract

Control charts are statistical tools to monitor a process or a product. However, some processes cannot be controlled by monitoring a characteristic; instead, they need to be monitored using profiles. Economic-statistical design of profile monitoring means determining the parameters of a profile monitoring scheme such that total costs are minimized while statistical measures maintain proper values. While varying sampling interval usually increases the effectiveness of profile monitoring, economic-statistical design of variable sampling interval (VSI) profile monitoring is investigated in this paper. An extended Lorenzen–Vance function is used for modeling total costs in VSI model where the...

Economic design of phase 2 simple linear profiles with variable sample size

, Article International Journal of Productivity and Quality Management ; Volume 18, Issue 4 , 2016 , Pages 518-536 ; 17466474 (ISSN) Ershadi, M. J ; Noorossana, R ; Akhavan Niaki, S. T ; Sharif University of Technology

Inderscience Enterprises Ltd 2016

Abstract

Employing profiles using variable sample size (VSS) may improve its effectiveness and hence is investigated in this paper. Besides, the implementation cost of a profile is an important factor in determining the main parameters. In this paper, the Lorenzen-Vance function is first extended to model implementation cost of VSS linear profiles. Then, the resulted economic model is solved using a genetic algorithm (GA). The average run length criterion when process is in control, ARL0 and the average run length measure when process goes out of control, ARL1 , is used to evaluate statistical properties of the designed profile. Moreover, a sensitivity analysis on the main parameters of the...

An investigation on the quality of output voltage waveform in a nanosecond pulse generator using reverse recovery diodes

, Article 9th Annual International Power Electronics, Drive Systems, and Technologies Conference, PEDSTC 2018 ; Volume 2018-January , 19 April , 2018 , Pages 516-521 ; 9781538646977 (ISBN) Naghibi Nasab, J ; Kaboli, S ; Eskandary, A ; Sharif University of Technology

Institute of Electrical and Electronics Engineers Inc 2018

Abstract

Nanosecond pulsed-power generators have many applications in industries. As the rise time and fall time of conventional semiconductor switches are usually more than a few nanoseconds, it is necessary to employ special switches or new pulse generating methods to achieve nanosecond pulses. A common method for producing narrow pulse voltage waveforms is using the reverse recovery process of diodes. In this method, a super fast recovery diode is used as an opening switch in an inductor current path. A drift step recovery diode can form a rapid cut-off current front; Hence this method can be an effective solution to generate narrow pulses. This paper describes an investigation about the effect of...