We offer a position as an

Early Stage Researcher (M/F/D)

in the Marie Skłodowska-Curie Innovative Training Network Project MENELAOS^NT in the field

Mobile mapping applications of CS techniques (ESR12)

Intelligent Infrastructure based on digitalization and Big Data solutions for smart mobility. The key factor for smart infrastructures is the predictive maintenance based on connected and digitalized infrastructures. This project will focus its goals to the use of low-cost mobile devices for the continuous monitoring and digitalizing for different transport infrastructures, inside and outside urban areas. The mobile devices will integrate sensors of different natures for the acquisition of georeferenced data. Several sensors will be used, such as image and LiDAR sensors, and sensors with compressed sensing strategies, among others. So, the specific objective of this project will be the automatic and real-time data processing for the extraction of relevant information existing in the transport infrastructure.The challenge of the project is focused on real-time processing applying compressive sensing and synchronization of multi sensor data for Mobile Mapping applications based on devices mounted on non-dedicated vehicles. The goal of this real-time processing consists of detecting relevant assets and components of the transport infrastructure and will allow for change detection, through the automatic comparison of the current state with the previous ground truth registered.

The successful candidate will be employed for a maximum period of three years full-time equivalent and receives a generous financial package plus an additional mobility and family allowance according to the rules for Early Stage Researchers (ESRs) in an EU Marie Sklodowska-Curie Actions Innovative Training Networks (ITN). A career development plan will be prepared for each fellow in accordance with his/her supervisor and will include training, planned secondments and outreach activities in partner institutions of the network. The ESR fellows are supposed to complete their PhD thesis by the end of the 3rd year of their employment. For more information please visit the Marie Sklodowska-Curie Actions Innovative Training Networks website.

Whilst Photogrammetry provides high-quality, high-definition images and measurements of the surveyed areas, Light-detection-and-ranging (LIDAR) technology provides accurate and precise Point Clouds real time. The project aim will be to process acquired data based on Compressive Sensing and Big Data techniques and compare the outputs to ground truth model, which results in real-time warnings regarding to any detected change.

This challenge will allow to develop applications for SmartMobility, SmartLogistics, SmartAsset y SmartAdmin of linear structures and cities. The data will be acquired from different types of low-cost sensors (LiDAR, RGB, thermographic and multispectral images), with and without compressed sensing strategies, integrated in Mobile Mapping systems with complementary positioning sensors (GNSS, inertial units) to allow for the positioning of the assets for security purposes. These systems will be mounted on non-dedicated mobile vehicles, that circulate regularly through the areas under study, such as buses, taxis or dust carts, in such way that continuous information about the scenarios will be acquired. Additionally, the versatility of the systems will reinforce its performance and utility in real-life scenarios.

The development addressed to the transport infrastructures (railway, road and urban space) is looking for developments based on novel hardware techniques of Compressive Sensing, to limit multimodal data acquisition from sensor measurements to user only relevant information.

In these cases, CS measurements will be gathered from multiple sources, which will be related in terms of position and/or time. In this situation, Bayesian framework will help in reducing the number of measurements by a criterion to stop acquisition when the sufficient number of measurements have been taken. This also gives a way for robust data fusion from multiple sources. Another approach to test will be to use distributed coding algorithms, by exploring the joint sparsity in multiple signals. Applicability of other approaches can also be researched for this.

The research on sensor data processing, mainly LiDAR and images (RGB, thermographic, multispectral), should restrict the data acquisition to the Region of Interest, to reduce computer processing requirements and allow real-time processing. This real-time automatic process allows the launching of warnings regarding the state of the infrastructure, dangers for vehicle drivers or pedestrians, or commands for autonomous vehicles.

The data collected, together with the hardware, interfaces or platforms developed for sensor systems, should enhance the extraction of information through multi sensor data fusion, and reduce processing requirements, allowing real-time object detection. The work will address mainly to elements with such size that they can be detected based on the resolution of the sensors implemented, including both lineal and punctual assets.

At the end of the project, the results be checked by means of real-time test for inventory/detection of components/changes with the MMS-based processing framework.

Mobile platforms that will be used to carry out tests and validation:

Car or Van with a navigation system
Railway dresin
UAV platform
Portable system based on simultaneous localization and mapping (SLAM)

YOUR TASKS

Select the sensors and study the appropriateness of the CS approach for each platform
Investigate and implement solutions for integration and fusion of sensor data and information, including geometric calibration and radiometric characterization to obtain a CS signature
Study and develop applications for CS validation in operating environments and particularly for urban asset modelling, indoor mapping and SLAM and forestry management
Validate implemented solutions using the present technologies at INSITU as a ground truth.

PROFILE

A Master of Science in Computer Science Science is required. It could comprise to the full range of mathematical, physical, engineering and technology disciplines related to sensor data acquisition and programming.
ESRs must demonstrate that their English proficiency is in both written and spoken English sufficiently high for them to derive the full benefit from the network training. Spanish recommendable.
Previous experience with LiDAR and RGB image processing, sensor fusion, Compressive Sensing or real time processing will be valued.
Knowledge of C++, Python, Machine/Deep Learning developments, deep background of Neuronal Networks such as KERAS, or Tensorflow libraries, specific Object Detection Systems like YOLO, SSD and Faster R-CNN

PLANNED SECONDMENTS

CITIUS, Spain, Dr. P. López Martinez, 3 months, ToF sensor characterization and appropriate application assessment
Pmdtec, Siegen, Germany, Dr. M. Albrecht, 3 months, sensor characterization and appropriate application assessment
CEOSpaceTech, Bucharest, Romania, Dr. D. Coltuc, 3 months, sensor characterization and appropriate application assessment.

We are a technology-based engineering and architecture firm. We are specialist in Mobile Mapping Systems. We were founded in the year 2008 as a way to transfer the activities of the University of Vigo GEO-Applied Technologies research group to the market. We are present in Spain (Madrid, A Coruña, Lugo and Vigo) where we provide services throughout Europe, and in Brazil (Sao Paulo), through our subsidiary Metro Cúbico Engenharia (www.metrocubicoengenharia.com.br), to work on projects on the American continent.
We are a large, young, well-educated, serious, reliable and multi-disciplinary team meaning that we all contribute, think, plan and design the best option to adapt to each of our customer’s needs. We get excited about each and every one of our projects and give our best to each one. We do maintenance of our drones, travel thousands of kilometres with our Mobile Mapping equipment, document large infrastructures and buildings and integrate large volumes of georeferenced data obtained using these and other new technologies available to the company. We are in constant contact with our offices in Vigo, Coruña, Madrid and Brazil, as they are fundamental pillars for the company’s development.

The position will be located at

Ingenieria Insitu
Rúa Fonte das Abelleiras, s/n
36310, CITEXVI, Vigo, Spain

Supervisor: Prof. Dr. Pedro Arias Sanchez

Planned Recruitment date: 1st September 2020.
Eligibility Criteria and Mobility Rule

ESRs must, at the date of recruitment, be in the first four years (full-time equivalent research experience) of their research careers and have not been awarded a doctoral degree. Full-Time Equivalent Research Experience is measured from the date when the researcher obtained the first degree entitling him/her to embark on a doctorate (either in the country in which the degree was obtained or in the country in which the researcher is recruited), even if a doctorate was never started or envisaged. Researchers can be of any nationality.

ESRs must not have resided or carried out their main activity (work, studies, etc.) in the country of the recruiting beneficiary for more than 12 months in the 3 years immediately before the planned recruitment date. Compulsory national service, short stays such as holidays, and time spent as part of a procedure for obtaining refugee status under the Geneva Convention are not taken into account.