Seyed Mojtaba Marvasti-Zadeh

Dr. Seyed Mojtaba Marvasti-Zadeh

University of Alberta, Edmonton, Alberta, Canada
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 January 2021 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
Seyed Mojtaba Marvasti-ZadehSeyed Mojtaba Marvasti-Zadeh
Seyed Mojtaba Marvasti-Zadeh
LCLi Cheng
Li Cheng
HGHossein Ghanei-Yakhdan
Hossein Ghanei-Yakhdan
SKShohreh Kasaei
Shohreh Kasaei
Visual target tracking is one of the most sought-after yet challenging research topics in computer vision. Given the ill-posed nature of the problem and its popularity in a broad range of real-world scenarios, a number of large-scale benchmark datasets have been established, on which considerable methods have been developed and demonstrated with significant progress in recent years – predominantly by recent deep learning (DL)-based methods. This survey aims to systematically investigate the current DL-based visual tracking methods, benchmark datasets, and evaluation metrics. It also extensively evaluates and analyzes the leading visual tracking methods. First, the fundamental characteristics, primary motivations, and contributions of DL-based methods are summarized from nine key aspects of: network architecture, network exploitation, network training for visual tracking, network objective, network output, exploitation of correlation filter advantages, aerial-view tracking, long-term tracking, and online tracking. Second, popular visual tracking benchmarks and their respective properties are compared, and their evaluation metrics are summarized. Third, the state-of-the-art DL-based methods are comprehensively examined on a set of well-established benchmarks of OTB2013, OTB2015, VOT2018, LaSOT, UAV123, UAVDT, and VisDrone2019. Finally, by conducting critical analyses of these state-of-the-art trackers quantitatively and qualitatively, their pros and cons under various common scenarios are investigated. It may serve as a gentle use guide for practitioners to weigh when and under what conditions to choose which method(s). It also facilitates a discussion on ongoing issues and sheds light on promising research directions.

1 January 2020
Verified
Book Chapter
Closed access
PDF file
MKMatej Kristan
Matej Kristan
ALAleš Leonardis
Aleš Leonardis
JMJiří Matas
Jiří Matas
MFMichael Felsberg
Michael Felsberg
RPRoman Pflugfelder
Roman Pflugfelder
ZMZiang Ma
Ziang Ma

10 November 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
Seyed Mojtaba Marvasti-ZadehSeyed Mojtaba Marvasti-Zadeh
Seyed Mojtaba Marvasti-Zadeh
DGDevin William Goodsman
Devin William Goodsman
NRNilanjan Ray
Nilanjan Ray
NENadir Erbilgin
Nadir Erbilgin
Bark beetle outbreaks can have serious consequences on forest ecosystem processes, biodiversity, forest structure and function, and economies. Thus, accurate and timely detection of bark beetle infestations in the early stage (known as green-attack detection) is crucial to mitigate the further impact, develop proactive forest management activities, and minimize economic losses. Incorporating remote sensing (RS) data with machine learning (ML) (or deep learning (DL)) can provide a great alternative to the current approaches that primarily rely on aerial surveys and field surveys, which can be impractical over vast areas. Existing approaches that exploit RS and ML/DL exhibit substantial diversity due to the wide range of factors involved. This article provides a comprehensive review of past and current advances in green-attack detection from three primary perspectives: bark beetle and host interactions, RS, and ML/DL. In contrast to prior efforts, this review encompasses all RS systems and emphasizes ML/DL methods to investigate their strengths and weaknesses. We parse existing literature based on multi- or hyperspectral analyses and distill their knowledge based on bark beetle species and attack phases with a primary emphasis on early stages of attacks, host trees, study regions, RS platforms and sensors, spectral/spatial/temporal resolutions, spectral signatures, spectral vegetation indices, ML approaches, learning schemes, task categories, models, algorithms, classes/clusters, features, and DL networks and architectures. Although DL-based methods and the random forest algorithm showed promising results, highlighting their potential to detect subtle changes across visible, thermal, and short-wave infrared spectral regions, their effectiveness remains limited, and high uncertainties persist due to the subtle distinctions between healthy and attacked trees. To inspire novel solutions to these shortcomings, we delve into the principal challenges and opportunities from different perspectives, enabling a deeper understanding of the current state of research and guiding future research directions.

27 February 2021
Verified
Book Chapter
Closed access
PDF file
Seyed Mojtaba Marvasti-ZadehSeyed Mojtaba Marvasti-Zadeh
Seyed Mojtaba Marvasti-Zadeh
JKJavad Khaghani
Javad Khaghani
HGHossein Ghanei-Yakhdan
Hossein Ghanei-Yakhdan
SKShohreh Kasaei
Shohreh Kasaei
LCLi Cheng
Li Cheng

19 May 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
RKRudraksh Kapil
Rudraksh Kapil
Guillermo CastillaGuillermo Castilla
Guillermo Castilla
Seyed Mojtaba Marvasti-ZadehSeyed Mojtaba Marvasti-Zadeh
Seyed Mojtaba Marvasti-Zadeh
DGDevin William Goodsman
Devin William Goodsman
NENadir Erbilgin
Nadir Erbilgin
NRNilanjan Ray
Nilanjan Ray
Operational forest monitoring often requires fine-detail information in the form of an orthomosaic, created by stitching overlapping nadir images captured by aerial platforms such as drones. RGB drone sensors are commonly used for low-cost, high-resolution imaging that is conducive to effective orthomosaicking, but only capture visible light. Thermal sensors, on the other hand, capture long-wave infrared radiation, which is useful for early pest detection among other applications. However, these lower-resolution images suffer from reduced contrast and lack of descriptive features for successful orthomosaicking, leading to gaps or swirling artifacts in the orthomosaic. To tackle this, we propose a thermal orthomosaicking workflow that leverages simultaneously acquired RGB images. The latter are used for producing a surface mesh via structure from motion, while thermal images are only used to texture this mesh and yield a thermal orthomosaic. Prior to texturing, RGB-thermal image pairs are co-registered using an affine transformation derived from a machine learning technique. On average, the individual RGB and thermal images achieve a mutual information of 0.2787 after co-registration using our technique, compared to 0.0591 before co-registration, and 0.1934 using manual co-registration. We show that the thermal orthomosaic generated from our workflow (1) is of better quality than other existing methods, (2) is geometrically aligned with the RGB orthomosaic, (3) preserves radiometric information (i.e., surface temperatures) from the original thermal imagery, and (4) enables easy transfer of downstream tasks—such as tree crown detection from the RGB to the thermal orthomosaic. We also provide an open-source tool that implements our workflow to facilitate usage and further development.

1 May 2023 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
Seyed Mojtaba Marvasti-ZadehSeyed Mojtaba Marvasti-Zadeh
Seyed Mojtaba Marvasti-Zadeh
DGDevin William Goodsman
Devin William Goodsman
NRNilanjan Ray
Nilanjan Ray
NENadir Erbilgin
Nadir Erbilgin
Visual explanation of “black-box” models allows researchers in explainable artificial intelligence (XAI) to interpret the model’s decisions in a human-understandable manner. In this paper, we propose interpretable class activation mapping for tree crown detection (Crown-CAM) that overcomes inaccurate localization & computational complexity of previous methods while generating reliable visual explanations for the challenging and dynamic problem of tree crown detection in aerial images. It consists of an unsupervised selection of activation maps, computation of local score maps, and non-contextual background suppression to efficiently provide fine-grain localization of tree crowns in scenarios with dense forest trees or scenes without tree crowns. Additionally, two Intersection over Union (IoU)-based metrics are introduced to effectively quantify both the accuracy and inaccuracy of generated explanations with respect to regions with or even without tree crowns in the image. Empirical evaluations demonstrate that the proposed Crown-CAM outperforms the Score-CAM, Augmented Score-CAM, and Eigen-CAM methods by an average IoU margin of 8.7, 5.3, and 21.7 (and 3.3, 9.8, and 16.5) respectively in improving the accuracy (and decreasing inaccuracy) of visual explanations on the challenging NEON tree crown dataset.