Periodic Reporting for period 1 - UDE (Artificial Intelligence and Computer Vision for real-time diagnosis of public spaces )
Reporting period: 2019-06-01 to 2019-11-30
Urban Data Eye brings to the market UDE, a real time solution for diagnosis of large semi-confined (public and private) spaces that leverages data captured from existing live CCTV cameras by providing actionable data and knowledge to solve the main needs that impact: Smart Cities, Retail and Manufacturing. Our main objectives are: analysing the platform scalability (data storage, GPU processing and server optimization), specifying the technical requirements to enhance the predictive models and the cloud analytics module and the validation requirements to perform the pilot demonstrations, performing a viability analysis of introducing our own-developed cameras and other sensors (radar, infrared and ultrasonic) and identifying the technical risks and the corresponding mitigation strategies.
Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far
From the feedback gained through the trials performed, we have specified the technical requirements to enhance the predictive models and the cloud analytics module in order to improve the computational efficiency of the different Artificial Vision algorithms and the data analytics and visualization functionality. We have also defined the validation requirements to perform the pilot demonstrations for the Retail and Manufacturing scenarios. In particular, we worked on the identification of initial metrics and performance enhancements in the algorithms. We also performed a technical risk analysis and prepared a contingency plan based on the initial risks identified. Additionally, we extended our market analysis and updated the financial forecast accordingly. The overall result shows that the current technology is still immature and not patentable. The economic and commercial unfeasibility of the project and the uncertain path of the upcoming pure research make the company unsustainable, so we have decided its dissolution and therefore, we are not continuing with the project.
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)
UDE would disrupt the urban diagnosis market by enabling: 1) Smart Cities enhance the energy efficiency of public spaces and the detection of mobility problems by gender (i.e. uncover dangerous areas for women); 2) Retail could discover the behaviour of customers inside malls to optimize pricing and marketing providers can establish valorisation methods to increase benefits through shop windows; 3) Factories could benefit from keeping track of human operators’ movements in order to better organize the spatial distribution of facilities, and therefore optimize the use of warehouses and industrial/production means in assembly lines.