Hayder Radha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hayder Radha has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Shirish Karande
Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA
10 shared publications - Muhammad Usman Ilyas
Department of Computer and Network Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia
6 shared publications - Kiran Misra
Michigan State University, East Lansing, MI, USA
5 shared publications - Syed Ali Khayam
Department of Electrical & Computer Engineering, Michigan State University, East Lansing, MI 48824 USA
3 shared publications - Beom-Jin Kim
Yonsei University
2 shared publications - Jin Woo Hong
Soonchoul Kim, ), Bumsuk Choi (), Youngho Jeong (), and Jinwoo Hong () are with the Broadcasting & Telecommunications Media Research Laboratory, ETRI, Daejeon, Rep. of Korea
2 shared publications
Latest Publications
- Open Access
Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving
Monocular Depth Estimation (MDE) is a pivotal component of vision-based Autonomous Driving (AD) systems, enabling vehicles to estimate the depth of surrounding objects using a single camera image. This estimation guides essential driving decisions, such as braking before an obstacle or changing lanes to avoid collisions. In this paper, we explore vulnerabilities of MDE algorithms in AD systems, presenting LensAttack, a novel physical attack that strategically places optical lenses on the camera of an autonomous vehicle to manipulate the perceived object depths. LensAttack encompasses two attack formats: concave lens attack and convex lens attack, each utilizing different optical lenses to induce false depth perception. We first develop a mathematical model that outlines the parameters of the attack, followed by simulations and real-world evaluations to assess its efficacy on state-of-the-art MDE models. Additionally, we adopt an attack optimization method to further enhance the attack success rate by optimizing the attack focal length. To better evaluate the implications of LensAttack on AD, we conduct comprehensive end-to-end system simulations using the CARLA platform. The results reveal that LensAttack can significantly disrupt the depth estimation processes in AD systems, posing a serious threat to their reliability and safety. Finally, we discuss some potential defense methods to mitigate the effects of the proposed attack.
Open AccessOptical Lens Attack on Monocular Depth Estimation for Autonomous Driving
Monocular Depth Estimation (MDE) is a pivotal component of vision-based Autonomous Driving (AD) systems, enabling vehicles to estimate the depth of surrounding objects using a single camera image. This estimation guides essential driving decisions, such as braking before an obstacle or changing lanes to avoid collisions. In this paper, we explore vulnerabilities of MDE algorithms in AD systems, presenting LensAttack, a novel physical attack that strategically places optical lenses on the camera of an autonomous vehicle to manipulate the perceived object depths. LensAttack encompasses two attack formats: concave lens attack and convex lens attack, each utilizing different optical lenses to induce false depth perception. We first develop a mathematical model that outlines the parameters of the attack, followed by simulations and real-world evaluations to assess its efficacy on state-of-the-art MDE models. Additionally, we adopt an attack optimization method to further enhance the attack success rate by optimizing the attack focal length. To better evaluate the implications of LensAttack on AD, we conduct comprehensive end-to-end system simulations using the CARLA platform. The results reveal that LensAttack can significantly disrupt the depth estimation processes in AD systems, posing a serious threat to their reliability and safety. Finally, we discuss some potential defense methods to mitigate the effects of the proposed attack.
- Open Access
Object Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging Techniques
Advanced automotive active-safety systems, in general, and autonomous vehicles, in particular, rely heavily on visual data to classify and localize objects such as pedestrians, traffic signs and lights, and other nearby cars, to assist the corresponding vehicles maneuver safely in their environments. However, the performance of object detection methods could degrade rather significantly under challenging weather scenarios including rainy conditions. Despite major advancements in the development of deraining approaches, the impact of rain on object detection has largely been understudied, especially in the context of autonomous driving. The main objective of this paper is to present a tutorial on state-of-the-art and emerging techniques that represent leading candidates for mitigating the influence of rainy conditions on an autonomous vehicle's ability to detect objects. Our goal includes surveying and analyzing the performance of object detection methods trained and tested using visual data captured under clear and rainy conditions. Moreover, we survey and evaluate the efficacy and limitations of leading deraining approaches, deep-learning based domain adaptation, and image translation frameworks that are being considered for addressing the problem of object detection under rainy conditions. Experimental results of a variety of the surveyed techniques are presented as part of this tutorial.
Open AccessObject Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging Techniques
Advanced automotive active-safety systems, in general, and autonomous vehicles, in particular, rely heavily on visual data to classify and localize objects such as pedestrians, traffic signs and lights, and other nearby cars, to assist the corresponding vehicles maneuver safely in their environments. However, the performance of object detection methods could degrade rather significantly under challenging weather scenarios including rainy conditions. Despite major advancements in the development of deraining approaches, the impact of rain on object detection has largely been understudied, especially in the context of autonomous driving. The main objective of this paper is to present a tutorial on state-of-the-art and emerging techniques that represent leading candidates for mitigating the influence of rainy conditions on an autonomous vehicle's ability to detect objects. Our goal includes surveying and analyzing the performance of object detection methods trained and tested using visual data captured under clear and rainy conditions. Moreover, we survey and evaluate the efficacy and limitations of leading deraining approaches, deep-learning based domain adaptation, and image translation frameworks that are being considered for addressing the problem of object detection under rainy conditions. Experimental results of a variety of the surveyed techniques are presented as part of this tutorial.
- 28 December 2015
- Published by Springer Nature in Machine Translation
- Vol. 29 (3-4) , 189-223
Survey of data-selection methods in statistical machine translation
- 28 December 2015
- Published by Springer Nature in Machine Translation
- Vol. 29 (3-4) , 189-223
Survey of data-selection methods in statistical machine translation
- Open Access
The Entropy of Attention and Popularity in YouTube Videos
The vast majority of YouTube videos never become popular, languishing in obscurity with few views, no likes, and no comments. We use information theoretical measures based on entropy to examine how time series distributions of common measures of popularity in videos from YouTube's "Trending videos" and "Most recent" video feeds relate to the theoretical concept of attention. While most of the videos in the "Most recent" feed are never popular, some 20% of them have distributions of attention metrics and measures of entropy that are similar to distributions for "Trending videos". We analyze how the 20% of "Most recent" videos that become somewhat popular differ from the 80% that do not, then compare these popular "Most recent" videos to different subsets of "Trending videos" to try to characterize and compare the attention each receives.
Open AccessThe Entropy of Attention and Popularity in YouTube Videos
The vast majority of YouTube videos never become popular, languishing in obscurity with few views, no likes, and no comments. We use information theoretical measures based on entropy to examine how time series distributions of common measures of popularity in videos from YouTube's "Trending videos" and "Most recent" video feeds relate to the theoretical concept of attention. While most of the videos in the "Most recent" feed are never popular, some 20% of them have distributions of attention metrics and measures of entropy that are similar to distributions for "Trending videos". We analyze how the 20% of "Most recent" videos that become somewhat popular differ from the 80% that do not, then compare these popular "Most recent" videos to different subsets of "Trending videos" to try to characterize and compare the attention each receives.
- 21 August 2011
- Published by Springer Nature in Journal of Signal Processing Systems
- Vol. 65 (2) , 159-169
A Distortion-Sensitive Seam Carving Algorithm for Content-Aware Image Resizing
- 21 August 2011
- Published by Springer Nature in Journal of Signal Processing Systems
- Vol. 65 (2) , 159-169
A Distortion-Sensitive Seam Carving Algorithm for Content-Aware Image Resizing
- 21 April 2011
- Published by Springer Nature in Wireless Networks
- Vol. 17 (5) , 1173-1189
On enabling cooperative communication and diversity combination in IEEE 802.15.4 wireless networks using off-the-shelf sensor motes
- 21 April 2011
- Published by Springer Nature in Wireless Networks
- Vol. 17 (5) , 1173-1189
On enabling cooperative communication and diversity combination in IEEE 802.15.4 wireless networks using off-the-shelf sensor motes
- 27 July 2010
- Published by Springer Nature in Journal of Computer Virology and Hacking Techniques
- Vol. 7 (2) , 159-172
Joint network-host based malware detection using information-theoretic tools
- 27 July 2010
- Published by Springer Nature in Journal of Computer Virology and Hacking Techniques
- Vol. 7 (2) , 159-172
Joint network-host based malware detection using information-theoretic tools
- Open Access
- 7 April 2010
- Published by Wiley in ETRI Journal
- Vol. 32 (2) , 273-280
Multihop Rate Adaptive Wireless Scalable Video Using Syndrome-Based Partial Decoding
- 7 April 2010
- Published by Wiley in ETRI Journal
- Vol. 32 (2) , 273-280
Open AccessMultihop Rate Adaptive Wireless Scalable Video Using Syndrome-Based Partial Decoding
- 31 December 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 58 (4) , 2088-2101
Design of Regular Wavelets Using a Three-Step Lifting Scheme
We propose structural multidimensional multichannel filter banks with desirable numbers of vanishing moments for the analysis and synthesis banks. For a two-channel filter bank, we use a three-step lifting scheme as opposed to the conventional two-step lifting method in order to provide more symmetry between the analysis and synthesis filters. We show that the resulting filters have more regularity, lower frame bounds ratio, and better frequency selectivity. We also extend our design to a general multichannel framework. Three steps of lifting scheme provides us a degree of freedom which we can benefit from toward a more flexible design.
- 31 December 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 58 (4) , 2088-2101
Design of Regular Wavelets Using a Three-Step Lifting Scheme
We propose structural multidimensional multichannel filter banks with desirable numbers of vanishing moments for the analysis and synthesis banks. For a two-channel filter bank, we use a three-step lifting scheme as opposed to the conventional two-step lifting method in order to provide more symmetry between the analysis and synthesis filters. We show that the resulting filters have more regularity, lower frame bounds ratio, and better frequency selectivity. We also extend our design to a general multichannel framework. Three steps of lifting scheme provides us a degree of freedom which we can benefit from toward a more flexible design.
- 2 July 2009
- Published by Springer Nature in Wireless Personal Communications
- Vol. 51 (3) , 535-548
Comparison of Conventional and Cross-Layer Multimedia Transport Schemes for Wireless Networks
- 2 July 2009
- Published by Springer Nature in Wireless Personal Communications
- Vol. 51 (3) , 535-548
Comparison of Conventional and Cross-Layer Multimedia Transport Schemes for Wireless Networks