Mahdi Rezaei

Mahdi Rezaei
University of Leeds · Institute for Transport Studies (ITS)

Assistant Professor in Computer Science
Senior Researcher & Project Leader in Computer Vision and AI-based Projects in Vehicle Automation and Self-Driving Cars

About

62
Publications
192,682
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
754
Citations
Introduction
I am an Assitant Professor and University Academic Fellow (UAF) at the University of Leeds, UK, Institute for Transport Studies. My research interest includes but not limited to: Computer vision | Applied Machine Learning | Deep Learning | Autonomous Vehicles | Smart Cars. More information about me: https://environment.leeds.ac.uk/transport/staff/9408/dr-mahdi-rezaei
Additional affiliations
January 2016 - December 2020
Auckland University of Technology
Position
  • Honorary Academic Staff
October 2014 - October 2016
University of Auckland
Position
  • Honorary Academic Staff
September 2006 - February 2020
Qazvin Islamic Azad University
Position
  • Professor (Assistant)
Education
October 2010 - May 2014
University of Auckland
Field of study
  • Computer Science

Publications

Publications (62)
Book
Full-text available
https://www.amazon.com/Computer-Vision-Driver-Assistance-Computational/dp/3319505491/ref=sr_1_1?s=books&ie=UTF8&qid=1488803742&sr=1-1
Preprint
Full-text available
The challenge of learning a new concept without receiving any examples beforehand is called zero-shot learning (ZSL). One of the major issues in deep learning based methodologies is the requirement of feeding a vast amount of annotated and labelled images by a human to train the network model. ZSL is known for having minimal human intervention by r...
Preprint
Full-text available
One of the most challenging and non-trivial tasks in robotics-based rescue operations is Hazardous Materials or HAZMATs sign detection within the operation field, in order to prevent other unexpected disasters. Each Hazmat sign has a specific meaning that the rescue robot should detect and interpret it to take a safe action, accordingly. Accurate H...
Preprint
Full-text available
Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-meter physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop...
Article
Full-text available
Automated human action recognition is one of the most attractive and practical research fields in computer vision. In such systems, the human action labelling is based on the appearance and patterns of the motions in the video sequences; however, majority of the existing research and most of the conventional methodologies and classic neural network...
Preprint
Full-text available
Computer Vision has played a major role in Intelligent Transportation Systems (ITS) and traffic surveillance. Along with the rapidly growing automated vehicles and crowded cities, the automated and advanced traffic management systems (ATMS) using video surveillance infrastructures have been evolved by the implementation of Deep Neural Networks. In...
Article
Full-text available
One of the most challenging and non-trivial tasks in robot-based rescue operations is the Hazardous Materials (HAZMAT) sign detection in dangerous operation fields, in order to prevent further unexpected disasters. Each HAZMAT sign has a specific meaning that the rescue robot should detect and interpret it to take a safe action, accordingly. Accura...
Preprint
Full-text available
Reward engineering and designing an incentive reward function are non-trivial tasks to train agents in complex environments. Furthermore, an inaccurate reward function may lead to a biased behaviour which is far from an efficient and optimised behaviour. In this paper, we focus on training a single agent to score goals with binary success/failure r...
Conference Paper
Full-text available
In this paper, we present an active vision method using a deep reinforcement learning approach for a humanoid soccer-playing robot. The proposed method adaptively optimises the viewpoint of the robot to acquire the most useful landmarks for self-localisation while keeping the ball into its viewpoint. Active vision is critical for humanoid decision-...
Article
Full-text available
Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-m physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop a hy...
Article
Full-text available
The challenge of learning a new concept, object, or a new medical disease recognition without receiving any examples beforehand is called Zero-Shot Learning (ZSL). One of the major issues in deep learning based methodologies such as in Medical Imaging and other real-world applications is the requirement of large annotated datasets prepared by clini...
Preprint
Full-text available
Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-meter physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop...
Preprint
Full-text available
Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-meter physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop...
Preprint
Full-text available
Automated human action recognition is one of the most attractive and practical research fields in computer vision, in spite of its high computational costs. In such systems, the human action labelling is based on the appearance and patterns of the motions in the video sequences; however, the conventional methodologies and classic neural networks ca...
Preprint
Full-text available
CAPTCHA is a human-centred test to distinguish a human operator from bots, attacking programs, or any other computerised agent that tries to imitate human intelligence. In this research, we investigate a way to crack visual CAPTCHA tests by an automated deep learning based solution. The goal of the cracking is to investigate the weaknesses and vuln...
Chapter
Full-text available
Ball detection is one of the most important tasks in the context of soccer-playing robots. The ball is a small moving object which can be blurred and occluded in many situations. Several neural network based methods with different architectures are proposed to deal with the ball detection. However, they are either neglecting to consider the computa...
Article
Full-text available
This paper highlights the role of ground manifold modeling for stixel calculations; stixels are medium-level data representations used for the development of computer vision modules for self-driving cars. By using single-disparity maps and simplifying ground manifold models, calculated stixels may suffer from noise, inconsistency, and false-detecti...
Conference Paper
Full-text available
Accurate license plate localization is the most important prerequisite in ANPR (Automatic Number Plate Recognition) systems. Majority of the existing algorithms use a single feature to obtain the license plate location which causes to potential false detections. In this article we propose a robust methodology using 16 statistical features while we...
Technical Report
Full-text available
As part of the published research in [1], [2] titled Mahdi Rezaei, Mutsuhiro Terauchi, "Vehicle Detection Based on Multi-Feature Clues and Dempster-Shafer Fusion Theory", Image and Video Technology, Springer, Volume 8333, pp 60-72, 2014, we release the iROADS as a comprehensive vehicle-dataset with 4656 image frames, in 7 categories, recorded from...
Conference Paper
Full-text available
Stixel-based segmentation is specifically designed towards obstacle detection which combines road surface estimation in traffic scenes, stixel calculations, and stixel clustering. Stixels are defined by observed height above road surface. Road surfaces (ground manifolds) are represented by using an occupancy grid map. Stixel-based segmentation may...
Conference Paper
Full-text available
We present a novel method for stixel construction using a calibrated collinear trinocular vision system. Our method takes three conjugate stereo images at the same time to measure the consistency of disparity values by means of the transitivity error in disparity space. Unlike previous stixel estimation methods that are built based on a single disp...
Conference Paper
Full-text available
Face appearance is one of the most important visual features of human which varies significantly over the aging. Therefore, automatic age estimation is a demanding research topic in the field of facial feature analysis. In the task of age estimation, feature extraction is the first influential step which highly effects on a learning method and its...
Chapter
This chapter mainly proposes a comprehensive method for detecting driver’s distraction and inattention. We introduce an asymmetric appearance-modelling method and an accurate 2D-to-3D registration technique to obtain the driver’s head pose, yawing detection, and head-nodding detection. Chapter 5 and this chapter present the first major objective of...
Chapter
In this chapter we present and discuss the basic computer vision concepts, techniques, and mathematical background that we use in this book. The chapter introduces image notations, the concept of integral images, colour space conversions, the Hough transform for line detection, camera coordinate systems, and stereo computer vision.
Chapter
This chapter outlines the general context of the book. Autonomous driving is still at a stage where drivers are expected to be in control of the vehicle at all times, but provided automated control features of the vehicle (based on input data generated by different sensors) already enhance safety and driver comfort. We especially consider automated...
Chapter
This book focuses in particular on driver-environment understanding as briefly outlined at the end of the previous chapter. This chapter provides a more detailed introduction, motivations, and a review of the state-of-the-art in this area of vision-based driver-assistance systems. The chapter also discusses existing challenges and outlines the stru...
Chapter
In this chapter we propose a method to assess driver drowsiness based on face and eye-status analysis. The chapter starts with a detailed discussion on effective ways to create a strong classifier (the “training phase”), and it continues with a novel optimization method for the “application phase” of the classifier. Both together significantly impr...
Chapter
In this chapter we discuss how to assess the risk level in a given driving scenario based on the eight possible inputs: driver’s direction of attention (yaw, roll, pitch), signs of fatigue or drowsiness (yawning, head nodding, eye closure), and from road situations (distance, and the angle of the detected vehicles to the ego-vehicle). Using a fuzzy...
Chapter
In this chapter we outline object detection and object recognition techniques which are of relevance for the remainder of the book. We focus on supervised and unsupervised learning approaches. The chapter provides technical details for each method, discussions on the strengths and weaknesses of each method, and gives examples and various applicatio...
Chapter
“Collision warning systems” are actively researched in the area of computer vision and the automotive industry. Using monocular vision only, this chapter discusses the part of our study that aims at detecting and tracking the vehicles ahead, to identify safety distances, and to provide timely information to assist a distracted driver under various...
Thesis
Full-text available
Computer-vision based driver assistance is an emerging technology, in both automotive industry and academia. Despite the existence of some commercial safety systems such as night vision, adaptive cruise control, and lane departure warning systems, we are at the beginning of a long research pathway toward future generation of intelligent vehicles. C...
Article
Full-text available
Avoiding high computational costs and calibration issues involved in stereo-vision based algorithms, this article proposes real-time monocular-vision based techniques for simultaneous vehicle detection and inter-vehicle distance estimation, in which the performance and robustness of the system remain competitive, even for highly challenging benchma...
Conference Paper
Full-text available
Fatigue and driver drowsiness monitoring is an important subject for designing driver assistance systems. The measurement of eye closure is a fundamental step for driver awareness detection. We propose a method which is based on eyelid detection and the measurement of the distance between the eyelids. First, the face and the eyes of the driver are...
Conference Paper
Full-text available
Eye gaze detection under challenging lighting conditions is a non-trivial task. Pixel intensity and the shades around the eye region may change depending on the time of day, location, or due to artificial lighting. This paper introduces a lighting-adaptive solution for robust eye gaze detection. First, we propose a binarization and cropping techniq...
Conference Paper
Full-text available
[Best PhD Student Published Paper Award 2014] The paper proposes an advanced driver-assistance system that correlates the driver’s attention to the road and traffic conditions by analyzing both simultaneously. In particular, we aim at the prevention of rear-end crashes due to driver fatigue or distraction. We propose an asymmetric appearance-modeli...
Data
Please refer to the updated iROADS dataset with the added Ground Truth information via the following link: https://www.researchgate.net/publication/260219141_iROADS_Datasetzip
Data
Please refer to the updated iROADS dataset with the added Ground Truth information via the following link: https://www.researchgate.net/publication/260219141_iROADS_Datasetzip
Article
Full-text available
Artistic rendering of human portraits is different and more challenging than that of landscapes or flowers. Issues are eye, nose, and mouth regions (i.e., facial features) where we need to represent their natural emotions. Shades or darkness around eyes, or shininess at nose tips may negatively impact the rendering result if not properly dealt with...
Conference Paper
Full-text available
On-road vehicle detection and rear-end crash prevention are demanding subjects in both academia and automotive industry. The paper focuses on monocular vision-based vehicle detection under challenging lighting conditions, being still an open topic in the area of driver assistance systems. The paper proposes an effective vehicle detection method bas...
Conference Paper
Full-text available
This paper addresses the problem of detecting human faces in noisy images. We propose a method that includes a denoising preprocessing step, and a new face detection approach based on a novel extension of Haar-like features. Preprocessing of the input images is focused on the removal of different types of noise while preserving the phase data. For...
Conference Paper
Full-text available
The paper develops a novel technique that significantly improves the performance of Haar-like feature-based object detectors in terms of speed, detection rate under difficult lighting conditions, and reduced number of false-positives. The method is implemented and validated for driver monitoring under very dark, very bright, and normal conditions....
Conference Paper
Full-text available
The paper introduces a novel methodology to enhance the accuracy, performance and effectiveness of Haar-like classifiers, especially for complicated lighting conditions. Performing a statistical intensity analysis on input image sequences, the technique provides a very fast and robust eye-status detection via a low-resolution VGA camera, without ap...
Conference Paper
Full-text available
Artistic painting of human portraits are more challenging than landscapes or flowers. Challenges are eye and nose areas where we need to avoid alterations from their natural appearance. Shades or darkness around eyes, or shininess at the nose tip may negatively impact the rendering result if not properly dealt with. The proposed computerized method...
Article
Full-text available
The design of intelligent driver assistance systems is of increasing importance for the vehicle-producing industry and road-safety solutions. This article starts with a review of road-situation monitoring and driver's behaviour analysis. This article also discusses lane tracking using vision (or other) sensors, and the strength or weakness of diffe...
Conference Paper
Full-text available
Eye status detection and localization is a fundamental step for driver awareness detection. The efficiency of any learning-based object detection method highly depends on the training dataset as well as learning parameters. The research develops optimum values of Haar-training parameters to create a nested cascade of classifiers for real-time eye s...
Chapter
Full-text available
This article contributes to a novel computerized and heuristic algorithm to make pretty geometrics used in traditional building patterns and tiling. Starting with some basic sketch or an ornamental pattern, it depicts how a designer may analyze the sketch structure and approaches to an analytical representation. In return, this analytical represent...
Chapter
Full-text available
This article contributes to a novel computerized and heuristic algorithm to make pretty geometrics used in traditional building patterns and tiling. Starting with some basic sketch or an ornamental pattern, it depicts how a designer may analyze the sketch structure and approaches to an analytical representation. In return, this analytical represent...
Article
Full-text available
The complexity of the driving task and uncertainty of the driving environment make driving as a very dangerous task. Various investigations show that speeding and lane departure are two main causes of road accidents. These would be more challenging in curvy roads. The paper describes a multi sensor systematic framework to solve the mentioned proble...
Conference Paper
Full-text available
Achieving secure vehicles equipped with accident prevention systems is one of the greatest passions of researchers in automotive laboratories. This article provides a detail description on the state of the art techniques for road situation monitoring and driver's behavior analysis (human factors). The focus would be to gain a practical multifaceted...
Conference Paper
Full-text available
The Line follower robot is a mobile machine that can detect and follow the line drawn on the floor. Generally, the path is predefined and can be either visible like a black line on a white surface with a high contrasted color or it can be invisible like a magnetic field. Therefore, this kind of Robot should sense the line with its Infrared Ray (IR)...
Chapter
Full-text available
As the cars play an important and wide spreading role in transportation systems of all countries, the chance of having accident is also greatly increased. A number of cars, automobiles, bicycles and also pedestrians may involve in such accidents which sometimes cause miserable disasters. This fact attracts increasing numbers of researchers to work...
Article
Full-text available
Driving, one of our daily activities is a complex task involving a great amount of interaction between the driver, vehicle and environment. Drivers regularly share their attention among operating the vehicle, monitoring traffic and nearby obstacles, and performing secondary tasks such as conversing, adjusting comfort settings (e.g. temperature, rad...
Conference Paper
Full-text available
This paper presents a vision system for a ping-pong player robot, called Robo-Pong. The robot employs color object detection techniques based on neural networks in its vision system. In this approach a quite simple architecture is employed to detect and localize objects in robotpsilas work space. The architecture is designed to be very easy-impleme...
Conference Paper
Full-text available
This paper presents a vision system for a Ping-Pong player robot, called Robo-Pong. The robot employs color object detection techniques based on fuzzy neural networks in its vision system. In this research a neuro-fuzzy approach is employed to detect and localize objects in robot's work space and map them in real world coordinates. The architecture...
Conference Paper
Full-text available
Driving is a very complex task which, at its core, involves the interaction between the driver and his/her environment. It is therefore extremely important to develop driver assistance systems that are centered on the driver. In this regards, various state of the art methods such as multi data sensor fusion techniques are applied on various types o...
Conference Paper
Full-text available
Because of high volume of graphic information, retrieval of compressed images is one of the needs of information era. One of the rapid methods for image compression which has the capability to maintain important information of images for retrieval is block truncation coding (BTC). In this article a new method for retrieval of images compressed by B...
Conference Paper
Full-text available
Because of high volume of graphic information, the retrieval of compressed images is one of the needs of information era. One of the rapid methods for image compression which has the capability to maintain important information of images for retrieval is Block Truncation Coding (BTC). In this article a new method for retrieval of images compressed...