DroTrack: High-speed Drone-based Object Tracking Under Uncertainty

Hamdi, Ali; Salim, Flora D.; Kim, Du Yong

doi:10.1109/fuzz48607.2020.9177571

Cited by 15 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…New VOT tasks include object tracking with segmentation [69], tracking by reconstruction [121], graph convolutional tracking [72], deep multi-scale spatial-temporal tracking [330] and drone-based VOT [314]. In drone-based object tracking [87], a drone d is tracking a moving object in real-time o using a camera as illustrated in Figure 14. Unlike conventional object tracking using fixed cameras, a camera mounted on d is moving according to the motion of d. When d or o moves the distance between them is altered.…”

Section: Computer Vision Related Stdm Tasksmentioning

confidence: 99%

Spatiotemporal Data Mining: A Survey on Challenges and Open Problems

Hamdi¹,

Shaban²,

Erradi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Spatiotemporal data mining (STDM) discovers useful patterns from the dynamic interplay between space and time. Several available surveys capture STDM advances and report a wealth of important progress in this field. However, STDM challenges and problems are not thoroughly discussed and presented in articles of their own. We attempt to fill this gap by providing a comprehensive literature survey on state-of-the-art advances in STDM. We describe the challenging issues and their causes and open gaps of multiple STDM directions and aspects. Specifically, we investigate the challenging issues in regards to spatiotemporal relationships, interdisciplinarity, discretisation, and data characteristics. Moreover, we discuss the limitations in the literature and open research problems related to spatiotemporal data representations, modelling and visualisation, and comprehensiveness of approaches. We explain issues related to STDM tasks of classification, clustering, hotspot detection, association and pattern mining, outlier detection, visualisation, visual analytics, and computer vision tasks. We also highlight STDM issues related to multiple applications including crime and public safety, traffic and transportation, earth and environment monitoring, epidemiology, social media, and Internet of Things.

show abstract

Section: Computer Vision Related Stdm Tasksmentioning

confidence: 99%

Spatiotemporal Data Mining: A Survey on Challenges and Open Problems

Hamdi¹,

Shaban²,

Erradi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent research efforts have used CNNs visual representation learning to advance multiple applications [8]- [10]. CNNbased methods are widely utilised to produce visual feature vectors from CT-scan images for disease prediction [11].…”

Section: Related Workmentioning

confidence: 99%

MARL: Multimodal Attentional Representation Learning for Disease Prediction

Hamdi¹,

Aboeleneen²,

Shaban³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Existing learning models often utilise CT-scan images to predict lung diseases. These models are posed by high uncertainties that affect lung segmentation and visual feature learning. We introduce MARL, a novel Multimodal Attentional Representation Learning model architecture that learns useful features from multimodal data under uncertainty. We feed the proposed model with both the lung CT-scan images and their perspective historical patients' biological records collected over times. Such rich data offers to analyse both spatial and temporal aspects of the disease. MARL employs Fuzzy-based image spatial segmentation to overcome uncertainties in CT-scan images. We then utilise a pre-trained Convolutional Neural Network (CNN) to learn visual representation vectors from images. We augment patients' data with statistical features from the segmented images. We develop a Long Short-Term Memory (LSTM) network to represent the augmented data and learn sequential patterns of disease progressions. Finally, we inject both CNN and LSTM feature vectors to an attention layer to help focus on the best learning features. We evaluated MARL on regression of lung disease progression and status classification. MARL outperforms state-of-the-art CNN architectures, such as EfficientNet and DenseNet, and baseline prediction models. It achieves a 91% R 2 score, which is higher than the other models by a range of 8% to 27%. Also, MARL achieves 97% and 92% accuracy for binary and multi-class classification, respectively. MARL improves the accuracy of state-of-the-art CNN models with a range of 19% to 57%. The results show that combining spatial and sequential temporal features produces better discriminative feature.

show abstract

“…Specifically, we collect the weather measurements for the geo-location coordinates instead of general weather status. We define the thresholds mentioned above according to the aviation safety regulations 4 and experts recommendations from online portals 5 Most of the QoS attributes are used directly to select the best Skyway in the A* algorithm. However, the drone speed requires a prepossessing step to consider the relationship with wind speed and direction.…”

Section: Weather Qos Propertiesmentioning

confidence: 99%

“…Pervasive Internet-of-Things (IoT) embedded sensors provide new drones usages to improve human lifestyle and productivity. New research opportunities are opened in different computing fields such drone learning [2], IoT [3], computer vision [4], and smart environments [5]. This leads to a wide variety of new applications ranging from public security [6], disaster management [7], E-commerce [8], [9] , and delivery [8], [10].…”

Section: Introductionmentioning

confidence: 99%

Drone-as-a-Service Composition Under Uncertainty

Hamdi¹,

Salim²,

Kim³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We propose an uncertainty-aware service approach to provide drone-based delivery services called Drone-as-a-Service (DaaS) effectively. Specifically, we propose a service model of DaaS based on the dynamic spatiotemporal features of drones and their in-flight contexts. The proposed DaaS service approach consists of three components: scheduling, route-planning, and composition. First, we develop a DaaS scheduling model to generate DaaS itineraries through a Skyway network. Second, we propose an uncertaintyaware DaaS route-planning algorithm that selects the optimal Skyways under weather uncertainties. Third, we develop two DaaS composition techniques to select an optimal DaaS composition at each station of the planned route. A spatiotemporal DaaS composer first selects the optimal DaaSs based on their spatiotemporal availability and drone capabilities. A predictive DaaS composer then utilises the outcome of the first composer to enable fast and accurate DaaS composition using several Machine Learning classification methods. We train the classifiers using a new set of spatiotemporal features which are in addition to other DaaS QoS properties. Our experiments results show the effectiveness and efficiency of the proposed approach.

show abstract

DroTrack: High-speed Drone-based Object Tracking Under Uncertainty

Cited by 15 publications

References 17 publications

Spatiotemporal Data Mining: A Survey on Challenges and Open Problems

Spatiotemporal Data Mining: A Survey on Challenges and Open Problems

MARL: Multimodal Attentional Representation Learning for Disease Prediction

Drone-as-a-Service Composition Under Uncertainty

Contact Info

Product

Resources

About