Harald Skinnemoen - Academia.edu (original) (raw)

Papers by Harald Skinnemoen

IEEE Conference Proceedings, 2018

In this paper we study and compare several approaches to detect floods and evidence for passabili... more In this paper we study and compare several approaches to detect floods and evidence for passability of roads by conventional means in Twitter. We focus on tweets containing both visual information (a picture shared by the user) and metadata, a combination of text and related extra information intrinsic to the Twitter API. This work has been done in the context of the MediaEval 2018 Multimedia Satellite Task. 2 RELATED WORKS Recent literature approaches leverage on satellite [8, 12, 15] or ground acquisitions [5] to identify flood events. Other works focus more on urban elements detection such as roads [6, 9]. To the best of our knowledge there are no existing works to determine road passability evidence during flood events. 3 DATA The dataset used in this work was distributed by MediaEval 2018 Multimedia Satellite Task [1, 4]. It consists of 5820 Twitter images with its related metadata, from which ∼36% of the images present flooded regions with evidence of roads. Only the images belonging to the earlier class are considered for the second task evaluation: among them, the ∼45% present passable roads. Furthermore, for Copyright held by the owner/author(s).

2018 International Symposium on Networks, Computers and Communications (ISNCC), 2018

In this paper, we present the functional design and experimental validation of network coding tec... more In this paper, we present the functional design and experimental validation of network coding technology over hybrid networks including satellite links. We first describe our design framework based on a holistic modelling of (overlay) heterogeneous networking satellite scenarios. We then define different types of logical nodes depending on their encoding, re-encoding and decoding functionalities and whether or not the satellite (overlay) application designer has control over them. Nodes are assumed strategically chosen to recode, which may result in a small number of re-encoding nodes that suffice to optimize selected performance metrics. Our main contribution is a system-oriented functional design of network coding that enables flexible instantiation of different types of network codes via configurable network coding (C-NC) functions. Random or structured NC coefficients can be remotely or locally generated and a packet scheduler can forward packets according to different policies. The choice of coefficients and overall NC scheme depend on the SATCOM-specific performance target, namely delay or bandwidth constraints. Here, we present a preliminary design and experimental testebed validation for the case of delay constrained transmission. Our results show the practical benefits of re-encoding and performance tradeoffs of different network coding schemes. In particular, our results show the good structural properties and delay-reliability tradeoffs of our novel proposal of structured network codes using Pascal matrices due to the regenerative properties of the coding coefficients.

Today, Unmanned Aerial Vehicles (UAVs) are widely used in many different scenarios including sear... more Today, Unmanned Aerial Vehicles (UAVs) are widely used in many different scenarios including search, monitoring, inspection, and surveillance. To be able to transmit the sensor data from the UAVs to the destination reliably within tangible response times to the relevant content is crucial, especially for tactical use cases. In this paper, we propose network coded torrents (NECTOR) to leverage multiple network interfaces for resilient hybrid satellite communications (SatCom) and terrestrial networking for UAVs. NECTOR is significantly different from the state-of-the-art multipath protocols such as multipath TCP (MPTCP) as it does not require any additional packet scheduler, rate-adaptation or forward error correction. We present the design and implementation of NECTOR, and evaluate its performance compared to MPTCP. Our experimental results show that NECTOR provides goodput (up to 70%) higher than MPTCP with 5.49 times less signaling overhead.

We present A Quality of Experience (QoE) video adaptive solution formulated such that it takes in... more We present A Quality of Experience (QoE) video adaptive solution formulated such that it takes into account the limitations of the target mobile satellite network and the particular use-case scenario and end-user requirements for situational awareness. A novel crossapplication/transport layer design take this into account, and secures both user control over priorities as well as an adaptive mode with feedback on transfer network capacity status, so the video capacity can be adapted accordingly.. Performance evaluation of the solution is carried out using an experimental platform such that the cross layer design together with several kinds of videos and network behavior can be tested. The numerical results show the benefit of the QoE optimization approach, compared to a best case non-adaptive solution, with both Quality of Service QoS and QoE metrics. The solution tracks abrupt drops in the network with as low 15% adaptation rate as well as variations over time. In particular, videos with more movement show more improvement in QoE, and quality improves 10% compared to a best case non-adaptive solution guessing the initial status of the network. I. Introduction he motivation for this work is formed by situations where available bandwidth is a priori unknown and potentially varying during use, such as in mobile satellite systems when using Best Effort Quality of Service, and where video serves the purpose of carrying information for situational awareness. Best Effort is of interest as costs are substantially less than for guaranteed services, it is easier to vary video quality and rates depending on relevance at a given moment and often, as in BGAN, the maximum rates can often be higher for many common types of terminals. In this paper we present ASMIRA (Advanced System for Moving Image Reception with Adaptation) - an adaptive solution for video transmission designed to optimize Quality of Experience (QoE) in time varying networks and validate its benefits with an evaluation of performance for mobile satellite communications systems. The application is targeted for Situational Awareness, and situations like safety, security, disaster and emergency management. While this work is mostly analytical, validations of performance has been carried out also using realistic satellite traces. The primary strength of our work Iies in the fact that it has been formulated as an optimization mechanism that takes into account the limitations of the target network, the particular use-case scenario and the end user requirements. The optimization mechanism targets two issues: time-varying conditions of the network link and video quality. The optimization makes use of cross-layer signaling from the transport layer in order to update the optimal adaptation values of the video. Benefits of this mechanism are assessed through extensive testing over an experimental platform specifically implemented for our scenario. This platform provided a close-to-solution test bed with the flexibility of the lab1 PhD candidate, Dept. of Telecommunications and Systems Engineering. Researcher at AnsuR Technologies.

... for simplified installation, where one is based on a motor and the other on smart signaling. ... more ... for simplified installation, where one is based on a motor and the other on smart signaling. ... area 1/3 of Britain, with 46,000 km water pipes, 39,000 km sewer pipes, 1839 waste ... The FP6 Project SatNEx has been a valuable contributor to the satellite research community the last ...

Applied sciences, Dec 8, 2020

During natural disasters, situational awareness is needed to understand the situation and respond... more During natural disasters, situational awareness is needed to understand the situation and respond accordingly. A key need is assessing open roads for transporting emergency support to victims. This can be done via analysis of photos from affected areas with known location. This paper studies the problem of detecting blocked/open roads from photos during floods by applying a two-step approach based on classifiers: does the image have evidence of road? If it does, is the road passable or not? We propose a single double-ended neural network (NN) architecture which addresses both tasks simultaneously. Both problems are treated as a single class classification problem with the use of a compactness loss. The study was performed on a set of tweets, posted during flooding events, that contain (i) metadata and (ii) visual information. We studied the usefulness of each data source and the combination of both. Finally, we conducted a study of the performance gain from ensembling different networks. Through the experimental results, we prove that the proposed double-ended NN makes the model almost two times faster and the load on memory lighter while improving the results with respect to training two separate networks to solve each problem independently.

Floods are major natural disasters which cause deaths and material damages every year. Monitoring... more Floods are major natural disasters which cause deaths and material damages every year. Monitoring these events is crucial in order to reduce both the affected people and the economic losses. In this work we train and test three different Deep Learning segmentation algorithms to estimate the water area from river images, and compare their performances. We discuss the implementation of a novel data chain aimed to monitor river water levels by automatically process data collected from surveillance cameras, and to give alerts in case of high increases of the water level or flooding. We also create and openly publish the first image dataset for river water segmentation.

IEEE Wireless Communications, Oct 1, 2005

DVB-RCS was the first interactive DVB system to provide an interactive broadband connection as an... more DVB-RCS was the first interactive DVB system to provide an interactive broadband connection as an extension of the DVB systems. The standard defines the physical and media access control layer protocols between the satellite operator and interactive user terminals. Following a response to a commercial requirement, DVB-RCS has been enhanced with a new set of extensions called DVB-RCS+M, that support broadband communications via mobile satellite services to mobile and typically collective terminals. By ensuring interoperability through an open standard approach with multiple vendors, DVB-RCS+M represents a key enabler for market growth in the mobile satellite communications sector. Successful trials and implementations of DVB-RCS+M have been carried out and the future looks promising

International Journal of Satellite Communications and Networking, 2010

ABSTRACT This paper presents the detailed architecture of the WISECOM system, which can quickly r... more ABSTRACT This paper presents the detailed architecture of the WISECOM system, which can quickly re-establish and provide telecommunication services after a disaster by integrating terrestrial mobile radio networks, such as GSM, WiFi, WiMAX and TETRA, with satellite technologies. The system aims to be a useful tool to be deployed in the early hours after a disaster event, for both the victims and the rescue services who will be able to communicate in a reliable and robust way, improving the coordination of the different teams and reducing the time needed to provide victims with the proper treatment. The paper presents in detail the different services provided by the system taking into account its two different versions, based on two different satellite technologies, Inmarsat BGAN and DVB-RCS. Together with the presentation of the system capabilities, a business model is also proposed. Thereafter, the architecture of the general system and the demonstrators that have been developed are detailed, according to the two versions of the system. The work also presents the outcomes of the tests conducted with a prototype of the system, and of the final project demonstration, which was held in Germany in May 2008 with the involvement of real end-users (fire brigades and civil protection authorities).

This paper proposes a consolidated approach for Voice over IP (VoIP) with Bandwidth on Demand ove... more This paper proposes a consolidated approach for Voice over IP (VoIP) with Bandwidth on Demand over satellite networks based on the ETSI DVB-RCS standard. A real-time service like voice communication needs priority over other services in IP environments with limited bandwidth. In satellite networks bandwidth utilization should be optimized in order to save service costs, which requires dynamic bandwidth allocation schemes, and we study trade-off between voice quality and bandwidth efficiency under different DVB-RCS-specific capacity request and allocation strategies. It is demonstrated that DVB-RCS provides an efficient platform for integrated support for a variety of VoIP applications over satellite. The main contribution of this paper consists in the identification of the mechanisms capable of responding to the key challenges raised by the VoIP application in satellite environment.

Noisy channels causing transmission errors can severly limit reproduced coded speech if the mappi... more Noisy channels causing transmission errors can severly limit reproduced coded speech if the mapping between the source and channel spaces is not robust. In particular, precise representation of the short term spectral information (LPC) has been shown to be crucial for speech coder performance in LPC based coders 1]. The speciic problem considered here is transmission of coded speech over bandlimited AWGN channels where multi-level modulation schemes (QAM) are applicable.

In this paper we propose a multi-modal deep learning approach to detect floods in social media po... more In this paper we propose a multi-modal deep learning approach to detect floods in social media posts. Social media posts normally contain somemetadata and/or visual information, therefore in order to detect the floods we use this information. The model is based on a Convolutional Neural Network which extracts the visual features and a bidirectional Long Short-Term Memory network to extract the semantic features from the textual metadata. We validate the method on images extracted from Flickr which contain both visual information and metadata and compare the results when using both, visual information only or metadata only. This work has been done in the context of the MediaEval Multimedia Satellite Task.

In this paper we study the problem of flood detection and quantification using online media and s... more In this paper we study the problem of flood detection and quantification using online media and satellite data. We present a three approaches, two of them based on neural networks and a third one based on the combination of different bands of satellite images. This work aims to detect floods and also give relevant information about the flood situation such as the water level and the extension of the flooded regions, as specified in the three subtasks, for which of them we propose a specific solution.

Multimedia Tools and Applications

In emergency situations, actions that save lives and limit the impact of hazards are crucial. In ... more In emergency situations, actions that save lives and limit the impact of hazards are crucial. In order to act, situational awareness is needed to decide what to do. Geolocalized photos and video of the situations as they evolve can be crucial in better understanding them and making decisions faster. Cameras are almost everywhere these days, either in terms of smartphones, installed CCTV cameras, UAVs or others. However, this poses challenges in big data and information overflow. Moreover, most of the time there are no disasters at any given location, so humans aiming to detect sudden situations may not be as alert as needed at any point in time. Consequently, computer vision tools can be

2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Mar 1, 2017

This paper proposes a novel method to optimize bandwidth usage for object detection in critical c... more This paper proposes a novel method to optimize bandwidth usage for object detection in critical communication scenarios. We develop two operating models of active information seeking. The first model identifies promising regions in low resolution imagery and progressively requests higher resolution regions on which to perform recognition of higher semantic quality. The second model identifies promising regions in low resolution imagery while simultaneously predicting the approximate location of the object of higher semantic quality. From this general framework, we develop a car recognition system via identification of its license plate and evaluate the performance of both models on a car dataset that we introduce. Results are compared with traditional JPEG compression and demonstrate that our system saves up to one order of magnitude of bandwidth while sacrificing little in terms of recognition performance.

2017 IEEE International Conference on Big Data (Big Data)