Periodic Reporting for period 3 - FITOPTIVIS (From the cloud to the edge - smart IntegraTion and OPtimization Technologies for highly efficient Image and VIdeo processing Systems) Reporting period: 2020-06-01 to 2021-11-30 Summary of the context and overall objectives of the project ObjectivesThe objectives of FitOptiVis are:FitOptiVis developments are driven by industrial use cases that serve as a basis for requirements, demonstration, and validation. Models and abstractions play a crucial role as a basis for an integrated reference architecture, design methods and run-time operation of CPS imaging and video pipelines. Devices and components expose their functional and performance set points, each with the corresponding resource requirements, through minimal interfaces. Model-driven design methods aim to design set points that trade-off functional and performance capabilities against resource usage, for maximal design-time and run-time flexibility. Resource virtualization and predictable, composable reconfiguration enable modular, scalable run-time multi-objective adaptation and optimization ensuring quality and real-time performance, even across reconfigurations. On-line monitoring and learning techniques enable the evolution of set points and their resource requirements in changing contexts, both operational environments and use patterns. A common reference architecture will capture the essential aspects of the envisioned approach in appropriate component abstractions, virtualization techniques and quality- and resource management protocols. The approach is grounded in the development of smart, high-performance, energy-efficient devices and components to validate the concepts and as a basis to exploit the FitOptiVis results.Use cases and demonstrators as driversThe FitOptiVis operational objectives are motivated by industrial use cases from diverse application domains. The use cases share demanding image and video processing, while they differ in other aspects like available processing power, energy budgets, safety requirements, configuration distribution, configuration dynamics, etc. The use cases dictate the requirements for the development of an integral approach for smart integration of image- and video-processing pipelines for CPS through a reference architecture, supported by low-power, high-performance, smart devices, and through methods and tools for combined design-time and run-time multi-objective optimisation within system and environment constraints. The use cases moreover form the basis for demonstrators. These demonstrators serve for validation and analysis of the project results, and as a basis for exploitation. Following an industry driven approach, guarantees that all the technical specifications for the FitOptiVis platform, components and tools are going to be derived from the use case needs and requirements, leveraging on appropriate requirements gathering and management techniques. Both cross-domain and domain-specific requirements will be taken into account and prioritized to cover all the necessary design set points.The use cases and demonstrators are chosen to have a diversity in image and video processing tasks. The different application domains will benefit from a common reference architecture, shared design methods, and generally usable devices and components. FitOptiVis CPS are highly evolvable systems. Today’s needs may rapidly change into something else. Therefore, the solutions for the problems of tomorrow can then be borrowed from other application fields. The generic and unified platform and design methods delivered by FitOptiVis enable the fast creation of image and video processing infrastructure in different domains, and simplified connections between systems across domains. This will become increasingly important in our rapidly evolving society where systems are without exception connected in the Internet of Things. FitOptiVis will deliver generic results that addresses this development and that are applicable in many domains (even outside of FitOptiVis) and across domains. Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far During this period, we ended the first iteration of the project developments and conducted the second iteration. although the technical achievements are still on track, the consequence of COVID-19 rules delayed the finishing of the partial demonstrations for the second iteration. There are still partial demonstrations, but these are not as advanced as planned originally. What is available is reported in the MS6 deliverables.Up to now, the COVID-19 pandemic mainly led to blocking entrance to laboratories and workshops to finish integration and testing the partial demonstrations. In several cases some parts were not delivered in time, but with months of delays. Presently access to laboratories and workshops is granted again, but only to a limited number of people. So work on demonstrators can proceed, but still not full-speed. In any case, all deliverables for milestone MS6 are ready. As the second end-user workshop is planned after the second-year review, MS6 will be reached by M28. The feedback of the first end-user workshop was used for the update of the project requirements, independent from the use-cases. The other work packages used this to revisit the work done during the first iteration, leading to the updated deliverables in M24. We had our first review, followed by several activities resulting from the reviewers’ feedback. These will lead to a clear and consistent picture to be presented during the review of 2020. Important aspects are the QRML (a DSL for resource and quality management) and the use of tools by the different partners. All these aspects were discussed during the project workshops. Due to the COVID-19 pandemic the June 2020 workshop was virtual.During previous period, we prepared a change request, mainly dealing with small shifts of effort, and a change of some people project roles.During the last period, we finished the technical work, and demonstrators. This was also the end of the 3rd iteration in the project. Evaluation was performed and the final end-user workshop was held. All planned deliverables were delivered, and all use cases gave good results. The gap analysis, in deliverable D6.3 showed that most technologies developed in FitOptiVis find their way into product development of the partners. Especially several developed tools and components are very useful in the use cases. Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far) The final results are the successful application of the methodology, tools and components developed in the project. An extensive description of the impact, gaps and market value of the project results on the use cases can be found in deliverable D6.3 chapter 6. All objectives are addressed in that chapter, including Objective 5, effective impact.The COVID19 pandemic lead to hampering evaluation of the demonstration, and some this could not be measured at all. However, most aspects of the demonstrators are evaluated, and in most case with a positive result. Therefore most involved companies will continue to use the results into future developments of their products.Most weaknesses identified deal with non-technical reasons like certification, standardisation, or cost. Technical weakness lie in AI techniques to improve the solutions. pic1.jpg pic2.jpg Updated picture of the whole group during a project workshop 20180611-132229.jpg 20180613-110529.jpg
