Polytechnic University of Milan

About: Polytechnic University of Milan is a education organization based out in Milan, Italy. It is known for research contribution in the topics: Computer science & Finite element method. The organization has 18231 authors who have published 58416 publications receiving 1229711 citations. The organization is also known as: PoliMi & L-NESS.

Deep Convolutional Neural Networks for pedestrian detection

Abstract: Pedestrian detection is a popular research topic due to its paramount importance for a number of applications, especially in the fields of automotive, surveillance and robotics. Despite the significant improvements, pedestrian detection is still an open challenge that calls for more and more accurate algorithms. In the last few years, deep learning and in particular Convolutional Neural Networks emerged as the state of the art in terms of accuracy for a number of computer vision tasks such as image classification, object detection and segmentation, often outperforming the previous gold standards by a large margin. In this paper, we propose a pedestrian detection system based on deep learning, adapting a general-purpose convolutional network to the task at hand. By thoroughly analyzing and optimizing each step of the detection pipeline we propose an architecture that outperforms traditional methods, achieving a task accuracy close to that of state-of-the-art approaches, while requiring a low computational time. Finally, we tested the system on an NVIDIA Jetson TK1, a 192-core platform that is envisioned to be a forerunner computational brain of future self-driving cars. HighlightsA deep convolutional neural network for pedestrian detection is proposed.The proposed method improves the accuracy performance with respect to handcrafted features.Our method detects pedestrians with a good accuracy and has a reasonable computational complexity.

Improving software process improvement

Abstract: Two dichotomies characterize software process improvement efforts and approaches: disciplined versus creative work and procurer risks versus user satisfaction. Based on these perspectives, the authors introduce six theses to illuminate the problems of pursuing SPI.

Knowledge management in non‐profit organizations

Abstract: The non‐profit sector is at present involved in a deep renewal process. Non‐profit organizations are required to deliver tailored and high‐quality services in order to overcome environmental complexity and scarcity of resources. In this context, non‐profit organizations are being called to reengineer their core processes and organizational paradigms. To achieve excellence, all available resources should be managed with increased effectiveness and efficiency, the most important of these being knowledge. This paper contributes to the literature about the role which knowledge management plays in achieving excellence in the non‐profit sector. In particular, the main results from an explorative survey of Italian non‐profit organizations are formalized and discussed.

Towards Open-World Software: Issue and Challenges

Abstract: Traditional software development is based on the closed-world assumption that the boundary between system and environment is known and unchanging. However, this assumption no longer works within today's unpredictable open-world settings, especially in ubiquitous and pervasive computing settings, which demand techniques that let software react to changes by self-organizing its structure and self-adapting its behavior. The more we move toward dynamic and heterogeneous systems, and the more we stress their self-healing and self-adapting capabilities, the more we need new approaches to develop these applications and new ways to structure and program them. Programming open systems requires new programming language features. Two features that bear investigation are introspection mechanisms to get runtime information about newly encountered services and reflective mechanisms to adapt client applications dynamically. Some existing standards, industrial products, and research prototypes that support, to a certain extent, the open-world assumptions are service-oriented technologies, publish/subscribe middleware systems, grid infrastructures, autonomic frameworks