arXiv subjects

Abolfazl Razi

Publications and source records attributed to Abolfazl Razi.

At least 73 records · Page 4Linked to original sources

arXiv2023

Actuator Trajectory Planning for UAVs with Overhead Manipulator using Reinforcement Learning

In this paper, we investigate the operation of an aerial manipulator system, namely an Unmanned Aerial Vehicle (UAV) equipped with a controllable arm with two degrees of freedom to carry out actuation tasks on the fly. Our solution is based on employing a Q-learning method to control the trajectory of the tip of the arm, also called end-effector. More specifically, we develop a motion planning model based on Time To Collision (TTC), which enables a quadrotor UAV to navigate around obstacles while ensuring the manipulator's reachability. Additionally, we utilize a model-based Q-learning model to independently track and control the desired trajectory of the manipulator's end-effector, given an arbitrary baseline trajectory for the UAV platform. Such a combination enables a variety of actuation tasks such as high-altitude welding, structural monitoring and repair, battery replacement, gutter cleaning, skyscrapper cleaning, and power line maintenance in hard-to-reach and risky environments while retaining compatibility with flight control firmware. Our RL-based control mechanism results in a robust control strategy that can handle uncertainties in the motion of the UAV, offering promising performance. Specifically, our method achieves 92% accuracy in terms of average displacement error (i.e. the mean distance between the target and obtained trajectory points) using Q-learning with 15,000 episodes

cs.RO↗

arXiv2023

RD-DPP: Rate-Distortion Theory Meets Determinantal Point Process to Diversify Learning Data Samples

In some practical learning tasks, such as traffic video analysis, the number of available training samples is restricted by different factors, such as limited communication bandwidth and computation power. Determinantal Point Process (DPP) is a common method for selecting the most diverse samples to enhance learning quality. However, the number of selected samples is restricted to the rank of the kernel matrix implied by the dimensionality of data samples. Secondly, it is not easily customizable to different learning tasks. In this paper, we propose a new way of measuring task-oriented diversity based on the Rate-Distortion (RD) theory, appropriate for multi-level classification. To this end, we establish a fundamental relationship between DPP and RD theory. We observe that the upper bound of the diversity of data selected by DPP has a universal trend of $\textit{phase transition}$, which suggests that DPP is beneficial only at the beginning of sample accumulation. This led to the design of a bi-modal method, where RD-DPP is used in the first mode to select initial data samples, then classification inconsistency (as an uncertainty measure) is used to select the subsequent samples in the second mode. This phase transition solves the limitation to the rank of the similarity matrix. Applying our method to six different datasets and five benchmark models suggests that our method consistently outperforms random selection, DPP-based methods, and alternatives like uncertainty-based and coreset methods under all sampling budgets, while exhibiting high generalizability to different learning tasks.

cs.LG↗

arXiv2023

Obscured Wildfire Flame Detection By Temporal Analysis of Smoke Patterns Captured by Unmanned Aerial Systems

This research paper addresses the challenge of detecting obscured wildfires (when the fire flames are covered by trees, smoke, clouds, and other natural barriers) in real-time using drones equipped only with RGB cameras. We propose a novel methodology that employs semantic segmentation based on the temporal analysis of smoke patterns in video sequences. Our approach utilizes an encoder-decoder architecture based on deep convolutional neural network architecture with a pre-trained CNN encoder and 3D convolutions for decoding while using sequential stacking of features to exploit temporal variations. The predicted fire locations can assist drones in effectively combating forest fires and pinpoint fire retardant chemical drop on exact flame locations. We applied our method to a curated dataset derived from the FLAME2 dataset that includes RGB video along with IR video to determine the ground truth. Our proposed method has a unique property of detecting obscured fire and achieves a Dice score of 85.88%, while achieving a high precision of 92.47% and classification accuracy of 90.67% on test data showing promising results when inspected visually. Indeed, our method outperforms other methods by a significant margin in terms of video-level fire classification as we obtained about 100% accuracy using MobileNet+CBAM as the encoder backbone.

cs.CV↗

arXiv2023

Diversity Maximized Scheduling in RoadSide Units for Traffic Monitoring Applications

This paper develops an optimal data aggregation policy for learning-based traffic control systems based on imagery collected from Road Side Units (RSUs) under imperfect communications. Our focus is optimizing semantic information flow from RSUs to a nearby edge server or cloud-based processing units by maximizing data diversity based on the target machine learning application while taking into account heterogeneous channel conditions (e.g., delay, error rate) and constrained total transmission rate. As a proof-of-concept, we enforce fairness among class labels to increase data diversity for classification problems. The developed constrained optimization problem is non-convex. Hence it does not admit a closed-form solution, and the exhaustive search is NP-hard in the number of RSUs. To this end, we propose an approximate algorithm that applies a greedy interval-by-interval scheduling policy by selecting RSUs to transmit. We use coalition game formulation to maximize the overall added fairness by the selected RSUs in each transmission interval. Once, RSUs are selected, we employ a maximum uncertainty method to handpick data samples that contribute the most to the learning performance. Our method outperforms random selection, uniform selection, and pure network-based optimization methods (e.g., FedCS) in terms of the ultimate accuracy of the target learning application.

math.OC↗

arXiv2022

Nano-Resolution Visual Identifiers Enable Secure Monitoring in Next-Generation Cyber-Physical Systems

Today's supply chains heavily rely on cyber-physical systems such as intelligent transportation, online shopping, and E-commerce. It is advantageous to track goods in real-time by web-based registration and authentication of products after any substantial change or relocation. Despite recent advantages in technology-based tracking systems, most supply chains still rely on plainly printed tags such as barcodes and Quick Response (QR) codes for tracking purposes. Although affordable and efficient, these tags convey no security against counterfeit and cloning attacks, raising privacy concerns. It is a critical matter since a few security breaches in merchandise databases in recent years has caused crucial social and economic impacts such as identity loss, social panic, and loss of trust in the community. This paper considers an end-to-end system using dendrites as nano-resolution visual identifiers to secure supply chains. Dendrites are formed by generating fractal metallic patterns on transparent substrates through an electrochemical process, which can be used as secure identifiers due to their natural randomness, high entropy, and unclonable features. The proposed framework compromises the back-end program for identification and authentication, a web-based application for mobile devices, and a cloud database. We review architectural design, dendrite operational phases (personalization, registration, inspection), a lightweight identification method based on 2D graph-matching, and a deep 3D image authentication method based on Digital Holography (DH). A two-step search is proposed to make the system scalable by limiting the search space to samples with high similarity scores in a lower-dimensional space. We conclude by presenting our solution to make dendrites secure against adversarial attacks.

cs.CR↗

arXiv2022

Fast Key Points Detection and Matching for Tree-Structured Images

This paper offers a new authentication algorithm based on image matching of nano-resolution visual identifiers with tree-shaped patterns. The algorithm includes image-to-tree conversion by greedy extraction of the fractal pattern skeleton along with a custom-built graph matching algorithm that is robust against imaging artifacts such as scaling, rotation, scratch, and illumination change. The proposed algorithm is applicable to a variety of tree-structured image matching, but our focus is on dendrites, recently-developed visual identifiers. Dendrites are entropy rich and unclonable with existing 2D and 3D printers due to their natural randomness, nano-resolution granularity, and 3D facets, making them an appropriate choice for security applications such as supply chain trace and tracking. The proposed algorithm improves upon graph matching with standard image descriptors. For instance, image inconsistency due to the camera sensor noise may cause unexpected feature extraction leading to inaccurate tree conversion and authentication failure. Also, previous tree extraction algorithms are prohibitively slow hindering their scalability to large systems. In this paper, we fix the current issues of [1] and accelerate the key points extraction up to 10-times faster by implementing a new skeleton extraction method, a new key points searching algorithm, as well as an optimized key point matching algorithm. Using minimum enclosing circle and center points, make the algorithm robust to the choice of pattern shape. In contrast to [1] our algorithm handles general graphs with loop connections, therefore is applicable to a wider range of applications such as transportation map analysis, fingerprints, and retina vessel imaging.

cs.CV↗

arXiv2022

DH-GAN: A Physics-driven Untrained Generative Adversarial Network for 3D Microscopic Imaging using Digital Holography

Digital holography is a 3D imaging technique by emitting a laser beam with a plane wavefront to an object and measuring the intensity of the diffracted waveform, called holograms. The object's 3D shape can be obtained by numerical analysis of the captured holograms and recovering the incurred phase. Recently, deep learning (DL) methods have been used for more accurate holographic processing. However, most supervised methods require large datasets to train the model, which is rarely available in most DH applications due to the scarcity of samples or privacy concerns. A few one-shot DL-based recovery methods exist with no reliance on large datasets of paired images. Still, most of these methods often neglect the underlying physics law that governs wave propagation. These methods offer a black-box operation, which is not explainable, generalizable, and transferrable to other samples and applications. In this work, we propose a new DL architecture based on generative adversarial networks that uses a discriminative network for realizing a semantic measure for reconstruction quality while using a generative network as a function approximator to model the inverse of hologram formation. We impose smoothness on the background part of the recovered image using a progressive masking module powered by simulated annealing to enhance the reconstruction quality. The proposed method is one of its kind that exhibits high transferability to similar samples, which facilitates its fast deployment in time-sensitive applications without the need for retraining the network. The results show a considerable improvement to competitor methods in reconstruction quality (about 5 dB PSNR gain) and robustness to noise (about 50% reduction in PSNR vs noise increase rate).

cs.IR↗

arXiv2022

Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review

This paper explores Deep Learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasizing driving safety for both Autonomous Vehicles (AVs) and human-operated vehicles. We present a typical processing pipeline, which can be used to understand and interpret traffic videos by extracting operational safety metrics and providing general hints and guidelines to improve traffic safety. This processing framework includes several steps, including video enhancement, video stabilization, semantic and incident segmentation, object detection and classification, trajectory extraction, speed estimation, event analysis, modeling and anomaly detection. Our main goal is to guide traffic analysts to develop their own custom-built processing frameworks by selecting the best choices for each step and offering new designs for the lacking modules by providing a comparative analysis of the most successful conventional and DL-based algorithms proposed for each step. We also review existing open-source tools and public datasets that can help train DL models. To be more specific, we review exemplary traffic problems and mentioned requires steps for each problem. Besides, we investigate connections to the closely related research areas of drivers' cognition evaluation, Crowd-sourcing-based monitoring systems, Edge Computing in roadside infrastructures, Automated Driving Systems (ADS)-equipped vehicles, and highlight the missing gaps. Finally, we review commercial implementations of traffic monitoring systems, their future outlook, and open problems and remaining challenges for widespread use of such systems.

cs.CV↗

arXiv2022

Network-level Safety Metrics for Overall Traffic Safety Assessment: A Case Study

Driving safety analysis has recently experienced unprecedented improvements thanks to technological advances in precise positioning sensors, artificial intelligence (AI)-based safety features, autonomous driving systems, connected vehicles, high-throughput computing, and edge computing servers. Particularly, deep learning (DL) methods empowered volume video processing to extract safety-related features from massive videos captured by roadside units (RSU). Safety metrics are commonly used measures to investigate crashes and near-conflict events. However, these metrics provide limited insight into the overall network-level traffic management. On the other hand, some safety assessment efforts are devoted to processing crash reports and identifying spatial and temporal patterns of crashes that correlate with road geometry, traffic volume, and weather conditions. This approach relies merely on crash reports and ignores the rich information of traffic videos that can help identify the role of safety violations in crashes. To bridge these two perspectives, we define a new set of network-level safety metrics (NSM) to assess the overall safety profile of traffic flow by processing imagery taken by RSU cameras. Our analysis suggests that NSMs show significant statistical associations with crash rates. This approach is different than simply generalizing the results of individual crash analyses, since all vehicles contribute to calculating NSMs, not only the ones involved in crash incidents. This perspective considers the traffic flow as a complex dynamic system where actions of some nodes can propagate through the network and influence the crash risk for other nodes. We also provide a comprehensive review of surrogate safety metrics (SSM) in the Appendix A.

cs.CV↗

arXiv2021

A Review of AI-enabled Routing Protocols for UAV Networks: Trends, Challenges, and Future Outlook

Unmanned Aerial Vehicles (UAVs), as a recently emerging technology, enabled a new breed of unprecedented applications in different domains. This technology's ongoing trend is departing from large remotely-controlled drones to networks of small autonomous drones to collectively complete intricate tasks time and cost-effectively. An important challenge is developing efficient sensing, communication, and control algorithms that can accommodate the requirements of highly dynamic UAV networks with heterogeneous mobility levels. Recently, the use of Artificial Intelligence (AI) in learning-based networking has gained momentum to harness the learning power of cognizant nodes to make more intelligent networking decisions by integrating computational intelligence into UAV networks. An important example of this trend is developing learning-powered routing protocols, where machine learning methods are used to model and predict topology evolution, channel status, traffic mobility, and environmental factors for enhanced routing. This paper reviews AI-enabled routing protocols designed primarily for aerial networks, including topology-predictive and self-adaptive learning-based routing algorithms, with an emphasis on accommodating highly-dynamic network topology. To this end, we justify the importance and adaptation of AI into UAV network communications. We also address, with an AI emphasis, the closely related topics of mobility and networking models for UAV networks, simulation tools and public datasets, and relations to UAV swarming, which serve to choose the right algorithm for each scenario. We conclude by presenting future trends, and the remaining challenges in AI-based UAV networking, for different aspects of routing, connectivity, topology control, security and privacy, energy efficiency, and spectrum sharing.

cs.NI↗

arXiv2021

Fully-echoed Q-routing with Simulated Annealing Inference for Flying Adhoc Networks

Current networking protocols deem inefficient in accommodating the two key challenges of Unmanned Aerial Vehicle (UAV) networks, namely the network connectivity loss and energy limitations. One approach to solve these issues is using learning-based routing protocols to make close-to-optimal local decisions by the network nodes, and Q-routing is a bold example of such protocols. However, the performance of the current implementations of Q-routing algorithms is not yet satisfactory, mainly due to the lack of adaptability to continued topology changes. In this paper, we propose a full-echo Q-routing algorithm with a self-adaptive learning rate that utilizes Simulated Annealing (SA) optimization to control the exploration rate of the algorithm through the temperature decline rate, which in turn is regulated by the experienced variation rate of the Q-values. Our results show that our method adapts to the network dynamicity without the need for manual re-initialization at transition points (abrupt network topology changes). Our method exhibits a reduction in the energy consumption ranging from 7% up to 82%, as well as a 2.6 fold gain in successful packet delivery rate}, compared to the state of the art Q-routing protocols

cs.NI↗

arXiv2020

Aerial Imagery Pile burn detection using Deep Learning: the FLAME dataset

Wildfires are one of the costliest and deadliest natural disasters in the US, causing damage to millions of hectares of forest resources and threatening the lives of people and animals. Of particular importance are risks to firefighters and operational forces, which highlights the need for leveraging technology to minimize danger to people and property. FLAME (Fire Luminosity Airborne-based Machine learning Evaluation) offers a dataset of aerial images of fires along with methods for fire detection and segmentation which can help firefighters and researchers to develop optimal fire management strategies. This paper provides a fire image dataset collected by drones during a prescribed burning piled detritus in an Arizona pine forest. The dataset includes video recordings and thermal heatmaps captured by infrared cameras. The captured videos and images are annotated and labeled frame-wise to help researchers easily apply their fire detection and modeling algorithms. The paper also highlights solutions to two machine learning problems: (1) Binary classification of video frames based on the presence [and absence] of fire flames. An Artificial Neural Network (ANN) method is developed that achieved a 76% classification accuracy. (2) Fire detection using segmentation methods to precisely determine fire borders. A deep learning method is designed based on the U-Net up-sampling and down-sampling approach to extract a fire mask from the video frames. Our FLAME method approached a precision of 92% and a recall of 84%. Future research will expand the technique for free burning broadcast fire using thermal images.

cs.CV↗

arXiv2020

Towards Boosting the Channel Attention in Real Image Denoising : Sub-band Pyramid Attention

Convolutional layers in Artificial Neural Networks (ANN) treat the channel features equally without feature selection flexibility. While using ANNs for image denoising in real-world applications with unknown noise distributions, particularly structured noise with learnable patterns, modeling informative features can substantially boost the performance. Channel attention methods in real image denoising tasks exploit dependencies between the feature channels, hence being a frequency component filtering mechanism. Existing channel attention modules typically use global statics as descriptors to learn the inter-channel correlations. This method deems inefficient at learning representative coefficients for re-scaling the channels in frequency level. This paper proposes a novel Sub-band Pyramid Attention (SPA) based on wavelet sub-band pyramid to recalibrate the frequency components of the extracted features in a more fine-grained fashion. We equip the SPA blocks on a network designed for real image denoising. Experimental results show that the proposed method achieves a remarkable improvement than the benchmark naive channel attention block. Furthermore, our results show how the pyramid level affects the performance of the SPA blocks and exhibits favorable generalization capability for the SPA blocks.

eess.IV↗

arXiv2020

Deep DIH : Statistically Inferred Reconstruction of Digital In-Line Holography by Deep Learning

Digital in-line holography is commonly used to reconstruct 3D images from 2D holograms for microscopic objects. One of the technical challenges that arise in the signal processing stage is removing the twin image that is caused by the phase-conjugate wavefront from the recorded holograms. Twin image removal is typically formulated as a non-linear inverse problem due to the irreversible scattering process when generating the hologram. Recently, end-to-end deep learning-based methods have been utilized to reconstruct the object wavefront (as a surrogate for the 3D structure of the object) directly from a single-shot in-line digital hologram. However, massive data pairs are required to train deep learning models for acceptable reconstruction precision. In contrast to typical image processing problems, well-curated datasets for in-line digital holography does not exist. Also, the trained model highly influenced by the morphological properties of the object and hence can vary for different applications. Therefore, data collection can be prohibitively cumbersome in practice as a major hindrance to using deep learning for digital holography. In this paper, we proposed a novel implementation of autoencoder-based deep learning architecture for single-shot hologram reconstruction solely based on the current sample without the need for massive datasets to train the model. The simulations results demonstrate the superior performance of the proposed method compared to the state of the art single-shot compressive digital in-line hologram reconstruction method.

eess.IV↗

arXiv2019

An Autonomous Spectrum Management Scheme for Unmanned Aerial Vehicle Networks in Disaster Relief Operations

This paper studies the problem of spectrum shortage in an unmanned aerial vehicle (UAV) network during critical missions such as wildfire monitoring, search and rescue, and disaster monitoring. Such applications involve a high demand for high-throughput data transmissions such as real-time video-, image-, and voice- streaming where the assigned spectrum to the UAV network may not be adequate to provide the desired Quality of Service (QoS). In these scenarios, the aerial network can borrow an additional spectrum from the available terrestrial networks in the trade of a relaying service for them. We propose a spectrum sharing model in which the UAVs are grouped into two classes of relaying UAVs that service the spectrum owner and the sensing UAVs that perform the disaster relief mission using the obtained spectrum. The operation of the UAV network is managed by a hierarchical mechanism in which a central controller assigns the tasks of the UAVs based on their resources and determine their operation region based on the level of priority of impacted areas and then the UAVs autonomously fine-tune their position using a model-free reinforcement learning algorithm to maximize the individual throughput and prolong their lifetime. We analyze the performance and the convergence for the proposed method analytically and with extensive simulations in different scenarios.

cs.LG↗

arXiv2019

A Solution for Dynamic Spectrum Management in Mission-Critical UAV Networks

In this paper, we study the problem of spectrum scarcity in a network of unmanned aerial vehicles (UAVs) during mission-critical applications such as disaster monitoring and public safety missions, where the pre-allocated spectrum is not sufficient to offer a high data transmission rate for real-time video-streaming. In such scenarios, the UAV network can lease part of the spectrum of a terrestrial licensed network in exchange for providing relaying service. In order to optimize the performance of the UAV network and prolong its lifetime, some of the UAVs will function as a relay for the primary network while the rest of the UAVs carry out their sensing tasks. Here, we propose a team reinforcement learning algorithm performed by the UAV's controller unit to determine the optimum allocation of sensing and relaying tasks among the UAVs as well as their relocation strategy at each time. We analyze the convergence of our algorithm and present simulation results to evaluate the system throughput in different scenarios.

cs.NI↗

arXiv2019

Wildfire Monitoring in Remote Areas using Autonomous Unmanned Aerial Vehicles

In this paper, we propose a drone-based wildfire monitoring system for remote and hard-to-reach areas. This system utilizes autonomous unmanned aerial vehicles (UAVs) with the main advantage of providing on-demand monitoring service faster than the current approaches of using satellite images, manned aircraft and remotely controlled drones. Furthermore, using autonomous drones facilitates minimizing human intervention in risky wildfire zones. In particular, to develop a fully autonomous system, we propose a distributed leader-follower coalition formation model to cluster a set of drones into multiple coalitions that collectively cover the designated monitoring field. The coalition leader is a drone %with longer communication range that employs observer drones potentially with different sensing and imaging %actuation capabilities to hover in circular paths and collect imagery information from the impacted areas. The objectives of the proposed system include i) to cover the entire fire zone with a minimum number of drones, and ii) to minimize the energy consumption and latency of the available drones to fly to the fire zone. Simulation results confirm that the performance of the proposed system -- without the need for inter-coalition communications -- approaches that of a centrally-optimized system.

cs.CY↗

arXiv2019

ECGNET: Learning where to attend for detection of atrial fibrillation with deep visual attention

The complexity of the patterns associated with Atrial Fibrillation (AF) and the high level of noise affecting these patterns have significantly limited the current signal processing and shallow machine learning approaches to get accurate AF detection results. Deep neural networks have shown to be very powerful to learn the non-linear patterns in the data. While a deep learning approach attempts to learn complex pattern related to the presence of AF in the ECG, they can benefit from knowing which parts of the signal is more important to focus during learning. In this paper, we introduce a two-channel deep neural network to more accurately detect AF presented in the ECG signal. The first channel takes in a preprocessed ECG signal and automatically learns where to attend for detection of AF. The second channel simultaneously takes in the preprocessed ECG signal to consider all features of entire signals. The model shows via visualization that what parts of the given ECG signal are important to attend while trying to detect atrial fibrillation. In addition, this combination significantly improves the performance of the atrial fibrillation detection (achieved a sensitivity of 99.53%, specificity of 99.26% and accuracy of 99.40% on the MIT-BIH atrial fibrillation database with 5-s ECG segments.)

q-bio.QM↗