Università degli studi di Modena e Reggio Emilia

Exposing city information to dynamic, distributed, powerful, scalable, and user-friendly big data systems is expected to enable the implementation of a wide range of new opportunities; however, the size, heterogeneity and geographical dispersion of data often makes it difficult to combine, analyze and consume them in a single system. In the context of the H2020 CLASS project, we describe an innovative framework aiming to facilitate the design of advanced big-data analytics workflows. The proposal covers the whole compute continuum, from edge to cloud, and relies on a well-organized distributed infrastructure exploiting: a) edge solutions with advanced computer vision technologies enabling the real-time generation of “rich” data from a vast array of sensor types; b) cloud data management techniques offering efficient storage, real-time querying and updating of the high-frequency incoming data at different granularity levels. We specifically focus on obstacle detection and tracking for edge processing, and consider a traffic density monitoring application, with hierarchical data aggregation features for cloud processing; the discussed techniques will constitute the groundwork enabling many further services. The tests are performed on the real use-case of the Modena Automotive Smart Area (MASA).

It is well known that biomedical imaging analysis plays a crucial role in the healthcare sector and produces a huge quantity of data. These data can be exploited to study diseases and their evolution in a deeper way or to predict their onsets. In particular, image classification represents one of the main problems in the biomedical imaging context. Due to the data complexity, biomedical image classification can be carried out by trainable mathematical models, such as artificial neural networks. When employing a neural network, one of the main challenges is to determine the optimal duration of the training phase to achieve the best performance. This paper introduces a new adaptive early stopping technique to set the optimal training time based on dynamic selection strategies to fix the learning rate and the mini-batch size of the stochastic gradient method exploited as the optimizer. The numerical experiments, carried out on different artificial neural networks for image classification, show that the developed adaptive early stopping procedure leads to the same literature performance while finalizing the training in fewer epochs. The numerical examples have been performed on the CIFAR100 dataset and on two distinct MedMNIST2D datasets which are the large-scale lightweight benchmark for biomedical image classification.

Combining Natural Language with Vision represents a unique and interesting challenge in the domain of Artificial Intelligence. The AI City Challenge Track 5 for Natural Language-Based Vehicle Retrieval focuses on the problem of combining visual and textual information, applied to a smart-city use case. In this paper, we present All You Can Embed (AYCE), a modular solution to correlate single-vehicle tracking sequences with natural language. The main building blocks of the proposed architecture are (i) BERT to provide an embedding of the textual descriptions, (ii) a convolutional backbone along with a Transformer model to embed the visual information. For the training of the retrieval model, a variation of the Triplet Margin Loss is proposed to learn a distance measure between the visual and language embeddings. The code is publicly available at https://github.com/cscribano/AYCE_2021.

Object detection is arguably one of the most important and complex tasks to enable the advent of next-generation autonomous systems. Recent advancements in deep learning techniques allowed a significant improvement in detection accuracy and latency of modern neural networks, allowing their adoption in automotive, avionics and industrial embedded systems, where performances are required to meet size, weight and power constraints.Multiple benchmarks and surveys exist to compare state-of-the-art detection networks, profiling important metrics, like precision, latency and power efficiency on Commercial-off-the-Shelf (COTS) embedded platforms. However, we observed a fundamental lack of fairness in the existing comparisons, with a number of implicit assumptions that may significantly bias the metrics of interest. This includes using heterogeneous settings for the input size, training dataset, threshold confidences, and, most importantly, platform-specific optimizations, that are especially important when assessing latency and energy-related values. The lack of uniform comparisons is mainly due to the significant effort required to re-implement network models, whenever openly available, on the specific platforms, to properly configure the available acceleration engines for optimizing performance, and to re-train the model using a homogeneous dataset.This paper aims at filling this gap, providing a comprehensive and fair comparison of the best-in-class Convolution Neural Networks (CNNs) for real-time embedded systems, detailing the effort made to achieve an unbiased characterization on cutting-edge system-on-chips. Multi-dimensional trade-offs are explored for achieving a proper configuration of the available programmable accelerators for neural inference, adopting the best available software libraries. To stimulate the adoption of fair benchmarking assessments, the framework is released to the public in an open source repository.

Modern automotive and avionics embedded systems integrate several functionalities that are subject to complex timing requirements. A typical application in these fields is composed of sensing, computation, and actuation. The ever increasing complexity of heterogeneous sensors implies the adoption of multi-rate task models scheduled onto parallel platforms. Aspects like freshness of data or first reaction to an event are crucial for the performance of the system. The Directed Acyclic Graph (DAG) is a suitable model to express the complexity and the parallelism of these tasks. However, deriving age and reaction timing bounds is not trivial when DAG tasks have multiple rates. In this paper, a method is proposed to convert a multi-rate DAG task-set with timing constraints into a single-rate DAG that optimizes schedulability, age and reaction latency, by inserting suitable synchronization constructs. An experimental evaluation is presented for an autonomous driving benchmark, validating the proposed approach against state-of-the-art solutions.

3D object detection and classification are crucial tasks for perception in Autonomous Driving (AD). To promptly and correctly react to environment changes and avoid hazards, it is of paramount importance to perform those operations with high accuracy and in real-time. One of the most widely adopted strategies to improve the detection precision is to fuse information from different sensors, like e.g. cameras and LiDAR. However, sensor fusion is a computationally intensive task, that may be difficult to execute in real-time on an embedded platforms. In this paper, we present a new approach for LiDAR and camera fusion, that can be suitable to execute within the tight timing requirements of an autonomous driving system. The proposed method is based on a new clustering algorithm developed for the LiDAR point cloud, a new technique for the alignment of the sensors, and an optimization of the Yolo-v3 neural network. The efficiency of the proposed method is validated comparing it against state-of-the-art solutions on commercial embedded platforms.