Reza Hoseinnezhad | RMIT University (original) (raw)

Papers by Reza Hoseinnezhad

Proceedings of the 16th International Conference on Information Fusion, 2013

This paper builds on the recently developed adaptive multi-Bernoulli filter, proposing a novel se... more This paper builds on the recently developed adaptive multi-Bernoulli filter, proposing a novel sensor control solution within the multi-object filtering scheme. Our sensor control method does not need any prior information on clutter and sensor field-of-view parameters. In addition, our control objective is based on the novel strategy of minimizing the uncertainties (quantified by variance) of the cardinality, and object state estimates as well as the estimated rate of clutter. In terms of computation, our method is efficient, as it does not need to perform Monte Carlo sampling in the space of measurement sets. This method is particular useful in space situational awareness applications such as detection and tracking of space junk, as currently, there is limited information on the distribution of traceable objects in the space and clutters, and our method can effectively handle such uncertainties.

International Journal of Vehicle Design, 2015

Computer Vision and Image Understanding, Aug 1, 2011

Several high breakdown robust estimators have been developed to solve computer vision problems in... more Several high breakdown robust estimators have been developed to solve computer vision problems involving parametric modeling and segmentation of multi-structured data. Since the cost functions of these estimators are not differentiable functions of parameters, they are commonly optimized by random sampling. This random search can be computationally cumbersome in cases involving segmentation of multiple structures. This paper introduces a high breakdown M-estimator (called HBM for short) with a differentiable cost function that can be directly optimized by iteratively reweighted least squares regression. The fast convergence and high breakdown point of HBM make this estimator an outstanding choice for segmentation of multi-structured data. The results of a number of experiments on range image segmentation and fundamental matrix estimation problems are presented. Those experiments involve both synthetic and real image data and benchmark the performance of HBM estimator both in terms of accurate segmentation of numerous structures in the data and convergence speed in comparison against a number of modern robust estimators developed for computer vision applications (e.g. pbM and ASKC). The results show that HBM outperforms other estimators in terms of computation time while exhibiting similar or better accuracy of estimation and segmentation.

This paper proposes a new approach for calibration of dead reckoning process. Using the well-know... more This paper proposes a new approach for calibration of dead reckoning process. Using the well-known UMBmark (University of Michigan Benchmark) is not sufficient for a desirable calibration of dead reckoning. Besides, existing calibration methods usually require explicit measurement of actual motion of the robot. Some recent methods use the smart encoder trailer or long range finder sensors such as ultrasonic or laser range finders for automatic calibration. Manual measurement is necessary in the case of the robots that are not equipped with long-range detectors or such smart encoder trailer. Our proposed approach uses an environment map that is created by fusion of proximity data, in order to calibrate the odometry error automatically. In the new approach, the systematic part of the error is adaptively estimated and compensated by an efficient and incremental maximum likelihood algorithm. Actually, environment map data are fused with the odometry and current sensory data in order to acquire the maximum likelihood estimation. The advantages of the proposed approach are demonstrated in some experiments with Khepera robot. It is shown that the amount of pose estimation error is reduced by a percentage of more than 80%.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015

Identifying the underlying model in a set of data contaminated by noise and outliers is a fundame... more Identifying the underlying model in a set of data contaminated by noise and outliers is a fundamental task in computer vision. The cost function associated with such tasks is often highly complex, hence in most cases only an approximate solution is obtained by evaluating the cost function on discrete locations in the parameter (hypothesis) space. To be successful at least one hypothesis has to be in the vicinity of the solution. Due to noise hypotheses generated by minimal subsets can be far from the underlying model, even when the samples are from the said structure. In this paper we investigate the feasibility of using higher than minimal subset sampling for hypothesis generation. Our empirical studies showed that increasing the sample size beyond minimal size ( p ), in particular up to p+2, will significantly increase the probability of generating a hypothesis closer to the true model when subsets are selected from inliers. On the other hand, the probability of selecting an all inlier sample rapidly decreases with the sample size, making direct extension of existing methods unfeasible. Hence, we propose a new computationally tractable method for robust model fitting that uses higher than minimal subsets. Here, one starts from an arbitrary hypothesis (which does not need to be in the vicinity of the solution) and moves until either a structure in data is found or the process is re-initialized. The method also has the ability to identify when the algorithm has reached a hypothesis with adequate accuracy and stops appropriately, thereby saving computational time. The experimental analysis carried out using synthetic and real data shows that the proposed method is both accurate and efficient compared to the state-of-the-art robust model fitting techniques.

International Journal of Vehicle Autonomous Systems, 2015

This paper presents a labeled multi-Bernoulli filter for track-before-detect with a special focus... more This paper presents a labeled multi-Bernoulli filter for track-before-detect with a special focus on visual tracking of multiple targets in video. We show that labeled multi-Bernoulli distribution is a conjugate prior for an image likelihood function with a specific separable form. Following a previously formulated likelihood function (with the desirable separable form) using background subtraction, we apply our proposed labeled multi-Bernoulli filter. Our simulation results show that the proposed solution can successfully track multiple targets in a public visual tracking dataset. Comparative results show superior tracking performance compared with recent competing methods.

This paper presents a sensor-control method for choosing the best next state of the sensor(s), th... more This paper presents a sensor-control method for choosing the best next state of the sensor(s), that provide(s) accurate estimation results in a multi-target tracking application. The proposed solution is formulated for a multi-Bernoulli filter and works via minimization of a new estimation error-based cost function. Simulation results demonstrate that the proposed method can outperform the state-of-the-art methods in terms of computation time and robustness to clutter while delivering similar accuracy.

Autodriver algorithm Anna Bourmistrova, Milan Simic, Reza Hoseinnezhad, Reza N. Jazar The autodri... more Autodriver algorithm Anna Bourmistrova, Milan Simic, Reza Hoseinnezhad, Reza N. Jazar The autodriver algorithm is an intelligent method to eliminate the need of steering by a driver on a well-defined road. The proposed method performs best on a four-wheel steering (4WS) vehicle, though it is also applicable to two-wheel-steering (TWS) vehicles. The algorithm is based on coinciding the actual vehicle center of rotation and road center of curvature, by adjusting the kinematic center of rotation. The road center of curvature is assumed prior information for a given road, while the dynamic center of rotation is the output of dynamic equations of motion of the vehicle using steering angle and velocity measurements as inputs. We use kinematic condition of steering to set the steering angles in such a way that the kinematic center of rotation of the vehicle sits at a desired point. At low speeds the ideal and actual paths of the vehicle are very close. With increase of forward speed the ro...

IET Computer Vision, 2015

2012 International Conference on Control, Automation and Information Sciences (ICCAIS), 2012

This paper introduces a novel electronic differential control method designed to adjust the vehic... more This paper introduces a novel electronic differential control method designed to adjust the vehicle sideslip angle. With the new electronic differential on board, the electric car with independent driving motors can achieve a next-to-zero side-slip angle, which is of great significance in enhancing vehicle handling. The proposed electronic differential is implemented in the form of a closed-loop control system that constantly regulates the torque commands sent to the independent driving motors. These commands are generated to tune the difference between the road-tire reaction forces at the amount associated with zero side-slip angle. Comparative simulations manifest that the proposed method outperforms the common equal torque scheme in various challenging steering scenarios.

2012 International Conference on Control, Automation and Information Sciences (ICCAIS), 2012

Most of parametric motion segmentation methods, formulated based on RANSAC technique, are designe... more Most of parametric motion segmentation methods, formulated based on RANSAC technique, are designed to estimate and segment multiple motions in a sequential manner. This paper introduces a new random set theoretical approach to simultaneously estimate the parameters of, and segment multiple motions in a single run. In this approach, the parameters of multiple motions are modelled as a random finite set with multi-Bernoulli distribution. Simulation results involving segmentation of numerous motions show that our method outperforms state-of-art methods in terms of estimation error and correct estimation rate. In addition, it is highly parallelizable and well-suited for implementation by parallel processors. The fast convergence and highly parallelizable nature of the proposed approach make it an excellent choice for real-time estimation and segmentation of multiple motions in computer vision and robotic applications.

Signal, Image and Video Processing, 2014

ABSTRACT In many image processing applications, such as parametric range and motion segmentation,... more ABSTRACT In many image processing applications, such as parametric range and motion segmentation, multiple instances of a model are fitted to data points. The most common robust fitting method, RANSAC, and its extensions are normally devised to segment the structures sequentially, treating the points belonging to other structures as outliers. Thus, the ratio of inliers is small and successful fitting requires a very large number of random samples, incurring cumbrous computation. This paper presents a new method to simultaneously fit multiple structures to data points in a single run. We model the parameters of multiple structures as a random finite set with multi-Bernoulli distribution. Simultaneous search for all structure parameters is performed by Bayesian update of the multi-Bernoulli parameters. Experiments involving segmentation of numerous structures show that our method outperforms well-known methods in terms of estimation error and computational cost. The fast convergence and high accuracy of our method make it an excellent choice for real-time estimation and segmentation of multiple structures in image processing applications.

2008 Digital Image Computing: Techniques and Applications, 2008

All high breakdown robust estimators, at their core, include an isolated search in either the dat... more All high breakdown robust estimators, at their core, include an isolated search in either the data or the parameter space. In this paper, we devise a high breakdown robust estimation technique, called fast least k-th order statistics (FLkOS) that employs the derivatives of order statistics of squared residuals to implement Newton's optimization method for its search. It is mathematically shown that Newton's optimization of the order statistics leads to a very simple and substantially fast search algorithm that bridges the data and parameter spaces. The proposed search involves replacing a p-tuple with another p-tuple in the data space, while moving towards the minimum point of the estimator's cost function in the parameter space. An important practical implication of this strategy is that we can limit the required search in the parameter space to the specific manifold spanned by data. FLkOS is shown to be an effective tool to perform multi-structured data fitting and segmentation via a number of experiments including range image segmentation experiments involving both synthetic and real images and fundamental matrix estimation involving real image pairs. The results show that FLkOS is remarkably efficient and substantially faster than state-of-the-art high breakdown estimators.

Nonlinear Approaches in Engineering Applications 2, 2013

Nonlinear Engineering, 2012

2008 4th International Conference on Wireless Communications, Networking and Mobile Computing, 2008

high speed respectively by proper fuzzy controller. Finally, a series of MATLAB/SIMULINK simulati... more high speed respectively by proper fuzzy controller. Finally, a series of MATLAB/SIMULINK simulation will carried out to evaluate the performance of the proposed structure.

International Journal of Electric and Hybrid Vehicles, 2014

Proceedings of the 16th International Conference on Information Fusion, 2013

This paper builds on the recently developed adaptive multi-Bernoulli filter, proposing a novel se... more This paper builds on the recently developed adaptive multi-Bernoulli filter, proposing a novel sensor control solution within the multi-object filtering scheme. Our sensor control method does not need any prior information on clutter and sensor field-of-view parameters. In addition, our control objective is based on the novel strategy of minimizing the uncertainties (quantified by variance) of the cardinality, and object state estimates as well as the estimated rate of clutter. In terms of computation, our method is efficient, as it does not need to perform Monte Carlo sampling in the space of measurement sets. This method is particular useful in space situational awareness applications such as detection and tracking of space junk, as currently, there is limited information on the distribution of traceable objects in the space and clutters, and our method can effectively handle such uncertainties.

International Journal of Vehicle Design, 2015

Computer Vision and Image Understanding, Aug 1, 2011

Several high breakdown robust estimators have been developed to solve computer vision problems in... more Several high breakdown robust estimators have been developed to solve computer vision problems involving parametric modeling and segmentation of multi-structured data. Since the cost functions of these estimators are not differentiable functions of parameters, they are commonly optimized by random sampling. This random search can be computationally cumbersome in cases involving segmentation of multiple structures. This paper introduces a high breakdown M-estimator (called HBM for short) with a differentiable cost function that can be directly optimized by iteratively reweighted least squares regression. The fast convergence and high breakdown point of HBM make this estimator an outstanding choice for segmentation of multi-structured data. The results of a number of experiments on range image segmentation and fundamental matrix estimation problems are presented. Those experiments involve both synthetic and real image data and benchmark the performance of HBM estimator both in terms of accurate segmentation of numerous structures in the data and convergence speed in comparison against a number of modern robust estimators developed for computer vision applications (e.g. pbM and ASKC). The results show that HBM outperforms other estimators in terms of computation time while exhibiting similar or better accuracy of estimation and segmentation.

This paper proposes a new approach for calibration of dead reckoning process. Using the well-know... more This paper proposes a new approach for calibration of dead reckoning process. Using the well-known UMBmark (University of Michigan Benchmark) is not sufficient for a desirable calibration of dead reckoning. Besides, existing calibration methods usually require explicit measurement of actual motion of the robot. Some recent methods use the smart encoder trailer or long range finder sensors such as ultrasonic or laser range finders for automatic calibration. Manual measurement is necessary in the case of the robots that are not equipped with long-range detectors or such smart encoder trailer. Our proposed approach uses an environment map that is created by fusion of proximity data, in order to calibrate the odometry error automatically. In the new approach, the systematic part of the error is adaptively estimated and compensated by an efficient and incremental maximum likelihood algorithm. Actually, environment map data are fused with the odometry and current sensory data in order to acquire the maximum likelihood estimation. The advantages of the proposed approach are demonstrated in some experiments with Khepera robot. It is shown that the amount of pose estimation error is reduced by a percentage of more than 80%.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015

Identifying the underlying model in a set of data contaminated by noise and outliers is a fundame... more Identifying the underlying model in a set of data contaminated by noise and outliers is a fundamental task in computer vision. The cost function associated with such tasks is often highly complex, hence in most cases only an approximate solution is obtained by evaluating the cost function on discrete locations in the parameter (hypothesis) space. To be successful at least one hypothesis has to be in the vicinity of the solution. Due to noise hypotheses generated by minimal subsets can be far from the underlying model, even when the samples are from the said structure. In this paper we investigate the feasibility of using higher than minimal subset sampling for hypothesis generation. Our empirical studies showed that increasing the sample size beyond minimal size ( p ), in particular up to p+2, will significantly increase the probability of generating a hypothesis closer to the true model when subsets are selected from inliers. On the other hand, the probability of selecting an all inlier sample rapidly decreases with the sample size, making direct extension of existing methods unfeasible. Hence, we propose a new computationally tractable method for robust model fitting that uses higher than minimal subsets. Here, one starts from an arbitrary hypothesis (which does not need to be in the vicinity of the solution) and moves until either a structure in data is found or the process is re-initialized. The method also has the ability to identify when the algorithm has reached a hypothesis with adequate accuracy and stops appropriately, thereby saving computational time. The experimental analysis carried out using synthetic and real data shows that the proposed method is both accurate and efficient compared to the state-of-the-art robust model fitting techniques.

International Journal of Vehicle Autonomous Systems, 2015

This paper presents a labeled multi-Bernoulli filter for track-before-detect with a special focus... more This paper presents a labeled multi-Bernoulli filter for track-before-detect with a special focus on visual tracking of multiple targets in video. We show that labeled multi-Bernoulli distribution is a conjugate prior for an image likelihood function with a specific separable form. Following a previously formulated likelihood function (with the desirable separable form) using background subtraction, we apply our proposed labeled multi-Bernoulli filter. Our simulation results show that the proposed solution can successfully track multiple targets in a public visual tracking dataset. Comparative results show superior tracking performance compared with recent competing methods.

This paper presents a sensor-control method for choosing the best next state of the sensor(s), th... more This paper presents a sensor-control method for choosing the best next state of the sensor(s), that provide(s) accurate estimation results in a multi-target tracking application. The proposed solution is formulated for a multi-Bernoulli filter and works via minimization of a new estimation error-based cost function. Simulation results demonstrate that the proposed method can outperform the state-of-the-art methods in terms of computation time and robustness to clutter while delivering similar accuracy.

Autodriver algorithm Anna Bourmistrova, Milan Simic, Reza Hoseinnezhad, Reza N. Jazar The autodri... more Autodriver algorithm Anna Bourmistrova, Milan Simic, Reza Hoseinnezhad, Reza N. Jazar The autodriver algorithm is an intelligent method to eliminate the need of steering by a driver on a well-defined road. The proposed method performs best on a four-wheel steering (4WS) vehicle, though it is also applicable to two-wheel-steering (TWS) vehicles. The algorithm is based on coinciding the actual vehicle center of rotation and road center of curvature, by adjusting the kinematic center of rotation. The road center of curvature is assumed prior information for a given road, while the dynamic center of rotation is the output of dynamic equations of motion of the vehicle using steering angle and velocity measurements as inputs. We use kinematic condition of steering to set the steering angles in such a way that the kinematic center of rotation of the vehicle sits at a desired point. At low speeds the ideal and actual paths of the vehicle are very close. With increase of forward speed the ro...

IET Computer Vision, 2015

2012 International Conference on Control, Automation and Information Sciences (ICCAIS), 2012

This paper introduces a novel electronic differential control method designed to adjust the vehic... more This paper introduces a novel electronic differential control method designed to adjust the vehicle sideslip angle. With the new electronic differential on board, the electric car with independent driving motors can achieve a next-to-zero side-slip angle, which is of great significance in enhancing vehicle handling. The proposed electronic differential is implemented in the form of a closed-loop control system that constantly regulates the torque commands sent to the independent driving motors. These commands are generated to tune the difference between the road-tire reaction forces at the amount associated with zero side-slip angle. Comparative simulations manifest that the proposed method outperforms the common equal torque scheme in various challenging steering scenarios.

2012 International Conference on Control, Automation and Information Sciences (ICCAIS), 2012

Most of parametric motion segmentation methods, formulated based on RANSAC technique, are designe... more Most of parametric motion segmentation methods, formulated based on RANSAC technique, are designed to estimate and segment multiple motions in a sequential manner. This paper introduces a new random set theoretical approach to simultaneously estimate the parameters of, and segment multiple motions in a single run. In this approach, the parameters of multiple motions are modelled as a random finite set with multi-Bernoulli distribution. Simulation results involving segmentation of numerous motions show that our method outperforms state-of-art methods in terms of estimation error and correct estimation rate. In addition, it is highly parallelizable and well-suited for implementation by parallel processors. The fast convergence and highly parallelizable nature of the proposed approach make it an excellent choice for real-time estimation and segmentation of multiple motions in computer vision and robotic applications.

Signal, Image and Video Processing, 2014

ABSTRACT In many image processing applications, such as parametric range and motion segmentation,... more ABSTRACT In many image processing applications, such as parametric range and motion segmentation, multiple instances of a model are fitted to data points. The most common robust fitting method, RANSAC, and its extensions are normally devised to segment the structures sequentially, treating the points belonging to other structures as outliers. Thus, the ratio of inliers is small and successful fitting requires a very large number of random samples, incurring cumbrous computation. This paper presents a new method to simultaneously fit multiple structures to data points in a single run. We model the parameters of multiple structures as a random finite set with multi-Bernoulli distribution. Simultaneous search for all structure parameters is performed by Bayesian update of the multi-Bernoulli parameters. Experiments involving segmentation of numerous structures show that our method outperforms well-known methods in terms of estimation error and computational cost. The fast convergence and high accuracy of our method make it an excellent choice for real-time estimation and segmentation of multiple structures in image processing applications.

2008 Digital Image Computing: Techniques and Applications, 2008

All high breakdown robust estimators, at their core, include an isolated search in either the dat... more All high breakdown robust estimators, at their core, include an isolated search in either the data or the parameter space. In this paper, we devise a high breakdown robust estimation technique, called fast least k-th order statistics (FLkOS) that employs the derivatives of order statistics of squared residuals to implement Newton's optimization method for its search. It is mathematically shown that Newton's optimization of the order statistics leads to a very simple and substantially fast search algorithm that bridges the data and parameter spaces. The proposed search involves replacing a p-tuple with another p-tuple in the data space, while moving towards the minimum point of the estimator's cost function in the parameter space. An important practical implication of this strategy is that we can limit the required search in the parameter space to the specific manifold spanned by data. FLkOS is shown to be an effective tool to perform multi-structured data fitting and segmentation via a number of experiments including range image segmentation experiments involving both synthetic and real images and fundamental matrix estimation involving real image pairs. The results show that FLkOS is remarkably efficient and substantially faster than state-of-the-art high breakdown estimators.

Nonlinear Approaches in Engineering Applications 2, 2013

Nonlinear Engineering, 2012

2008 4th International Conference on Wireless Communications, Networking and Mobile Computing, 2008

high speed respectively by proper fuzzy controller. Finally, a series of MATLAB/SIMULINK simulati... more high speed respectively by proper fuzzy controller. Finally, a series of MATLAB/SIMULINK simulation will carried out to evaluate the performance of the proposed structure.

International Journal of Electric and Hybrid Vehicles, 2014