VISION TECHNOLOGIES ENABLED FOR INTEGRATED INTELLIGENT TRANSPORTATION

Operation co-funded by EU cohesion policy (European Regional Development Fund (ERDF)) under the programme Multi-regional Spain - ERDF (2014ES16RFOP002), managing authority: Subdirección General de Gestión del FEDER, de la Dirección General de Fondos Europeos del Ministerio de Hacienda.. The source names no beneficiary for this operation. Location: Seville Province (NUTS ES618); Spain. Budget: total eligible expenditure EUR 144,958; EU co-financing EUR 115,966.4 (co-financing rate 80%), as stated by the source. Runs 2019-01-01 to 2021-12-31. Source: Kohesio, EU cohesion policy projects managed by national and regional authorities (not CORDIS); selected because its summary names quantum technology. Summary from Kohesio (English machine translation by the source): THIS SUBPROJECT IS PART OF AN AMBITIOUS PLAN FOR THE EFFICIENT IMPLEMENTATION OF EMBEDDED VISION SYSTEMS IN THE FIELD OF INTELLIGENT TRANSPORT. IMAGE PROCESSING, OBJECT DETECTION AND RECOGNITION AND THE AUTOMATIC INTERPRETATION OF THE SCENE REPRESENT AN OVERWHELMING COMPUTATIONAL LOAD. FURTHERMORE, THE CHOSEN APPLICATION SCENARIO INTRODUCES HARD RESTRICTIONS ON THE PHYSICAL PROFILE OF THE SYSTEM AND ITS POWER CONSUMPTION. OUR CONTRIBUTION WILL FOCUS ON THE SENSOR PLANE AND THE PROCESSING ARCHITECTURE FOR DEEP LEARNING INFERENCE. ON THE ONE HAND WE ARE GOING TO EXTEND THE PERFORMANCE OF IMAGE SENSORS. IN THE AUTOMOTIVE FIELD, THERE IS A DEMAND FOR EXCEPTIONAL SENSOR CAPABILITIES IN TERMS OF DYNAMIC RANGE, LOW-LIGHT VISION AND ACCURACY IN THE ESTIMATION OF DISTANCES. TO RESPOND TO THIS DEMAND, WE WILL WORK ON THE DEVELOPMENT OF LOW-NOISE READOUT CHANNELS AND THE DESIGN OF ANALOG-DIGITAL CONVERTERS FOR IMAGE SENSORS. WE WILL ALSO DEVELOP A PROTOTYPE CMOS IMAGE SENSOR BASED ON SPADS. IN ADDITION TO THIS, AS WILL BE MENTIONED LATER IN THE COURSE OF THE SCIENTIFIC PROPOSAL, THE FINAL OBJECTIVE OF IMAGE DETECTION IS THE EXTRACTION OF THE RELEVANT INFORMATION FROM THE VISUAL STIMULUS. TAKING ADVANTAGE OF SPATIAL AND TEMPORAL CORRELATIONS, WE CAN DERIVE TECHNIQUES TO EXTRACT THIS INFORMATION, DISCARDING IRRELEVANT DATA IN THE FIRST STAGES OF VISION. THIS CAN HAVE AN IMPORTANT IMPACT ON THE ENERGY EFFICIENCY OF THE SYSTEM. IN THIS SENSE, WE WILL WORK ON COMPRESSIVE SAMPLING TECHNIQUES AND EVENT-DRIVEN REPRESENTATION BASED ON THE LOCAL COMPUTATION OF TEMPORAL AND SPATIAL CONTRASTS. WE WANT TO CONSIDER ALSO TECHNIQUES FOR EXTRACTING INFORMATION WITHOUT WAITING TO THE FORMATION OF THE IMAGE, WHAT IS NOW REFERRED AS QUANTUM IMAGING. ALL THESE ADVANCES WILL MATERIALIZE IN A PROTOTYPE CHIP AS PROOF OF CONCEPT. IN THE FIELD OF IMAGE PROCESSING, THE APPLICATION OF CONVOLUTIONAL NEURAL NETWORKS (CNNS) AND DEEP LEARNING (DL) IS A WORLDWIDE TREND. THESE ARE TECHNIQUES THAT OVERCOME, IN [shortened; the full text is on the Kohesio page]

Original source.

Source: Kohesio (EU cohesion policy projects), European Commission, Directorate-General for Regional and Urban Policy (DG REGIO). Retrieved 2026-10-21. Licence: CC0 1.0 (Cohesion Open Data Platform, dataset 2014-2020 Kohesio projects). Selected metadata, adapted presentation; the publisher's record is authoritative. No endorsement by the source is implied. Licence: public domain dedication (CC0 1.0).

AI-assisted summary: The operation, co-funded by the EU's ERDF, focuses on implementing embedded vision systems for intelligent transportation in Seville Province, Spain, with a budget of EUR 144,958. It runs from January 1, 2019, to December 31, 2021. Suggested technology pillar: enabling. Generated by AI from the public source text; it may contain errors and the original source is authoritative.