No abstract

Convolutional neural networks have pushed forward image analysis research and computer vision over the last decade, constituting a state-of-the-art approach in object detection today. The design of increasingly deeper and wider architectures has made it possible to achieve unprecedented levels of detection accuracy, albeit at the cost of both a dramatic computational burden and a large memory footprint. In such a context, cloud systems have become a mainstream technological solution due to their tremendous scalability, providing researchers and practitioners with virtually unlimited resources. However, these resources are typically made available as remote services, requiring communication over the network to be accessed, thus compromising the speed of response, availability, and security of the implemented solution. In view of these limitations, the on-device paradigm has emerged as a recent yet widely explored alternative, pursuing more compact and efficient networks to ultimately enable the execution of the derived models directly on resource-constrained client devices. This study provides an up-to-date review of the more relevant scientific research carried out in this vein, circumscribed to the object detection problem. In particular, the paper contributes to the field with a comprehensive architectural overview of both the existing lightweight object detection frameworks targeted to mobile and embedded devices, and the underlying convolutional neural networks that make up their internal structure. More specifically, it addresses the main structural-level strategies used for conceiving the various components of a detection pipeline (i.e., backbone, neck, and head), as well as the most salient techniques proposed for adapting such structures and the resulting architectures to more austere deployment environments. Finally, the study concludes with a discussion of the specific challenges and next steps to be taken to move toward a more convenient accuracy–speed trade-off.

No abstract

Abstract. Modeling and rendering of synthetic plants and trees has always received a lot of attention from computer graphics practitioners. Recent advances in plant and tree modeling have made it possible to generate and render very complex scenes. Models developed so far allow low quality and photorealistic rendering as well as a fine control on the amount of geometry sent to the graphics pipeline. Recently, non-photorealistic rendering techniques have been proposed as an alternative to traditional rendering. In this paper we present a method for interactive rendering of vegetation silhouettes. Our goal is to expressively render plant and tree models. Previous methods are either too slow for real-time rendering or they do not maintain the general appearance of a given vegetable species. We solve these two problems in our work.

Ambient Intelligence (AmI) encompasses technological infrastructures capable of sensing data from environments and extracting high-level knowledge to detect or recognize users’ features and actions, as well as entities or events in their surroundings. Visual perception, particularly object detection, has become one of the most relevant enabling factors for this context-aware user-centered intelligence, being the cornerstone of relevant but complex tasks, such as object tracking or human action recognition. In this context, convolutional neural networks have proven to achieve state-of-the-art accuracy levels. However, they typically result in large and highly complex models that typically demand computation offloading onto remote cloud platforms. Such an approach has security- and latency-related limitations and may not be appropriate for some AmI use cases where the system response time must be as short as possible, and data privacy must be guaranteed. In the last few years, the on-device paradigm has emerged in response to those limitations, yielding more compact and efficient neural networks able to address inference directly on client machines, thus providing users with a smoother and better-tailored experience, with no need of sharing their data with an outsourced service. Framed in that novel paradigm, this work presents a review of the recent advances made along those lines in object detection, providing a comprehensive study of the most relevant lightweight CNN-based detection frameworks, discussing the most paradigmatic AmI domains where such an approach has been successfully applied, the different challenges arisen, the key strategies and techniques adopted to create visual solutions for image-based object classification and localization, as well as the most relevant factors to bear in mind when assessing or comparing those techniques, such as the evaluation metrics or the hardware setups used.

Abstract. We present several techniques to generate clouds and smoke with cartoon style and sketching obtaining interactive speed for the graphical results. The proposed method allows abstracting the visual and geometric complexity of the gaseous phenomena using a particle system. The abstraction process is made using implicit surfaces, which are used later to calculate the silhouette and obtain the result image. Additionally, we add detail layers that allow improvement of the appearance and provide the sensation of greater volume for the gaseous effect. Finally, we also include in our application a simulator that generates smoke animations.

Seeking a more flexible and efficient production, additive manufacturing (AM) has emerged as a major player in the industrial field, streamlining the fabrication of custom tangible assets by directly 3D printing them. However, production still takes too long due to printing, but also due to the product design stage, in which the customer works together with an expert to create a 3D model of the targeted product by means of computer-aided design (CAD) software. Skipping intermediate agents and making customers responsible for the design process will reduce waiting times and speed up the manufacturing process. This work is conceived as a first step towards that optimized AM model, being aimed at bringing CAD tools closer to clients through an enhanced user experience, and consequently at simplifying pre-manufacturing design tasks. Specifically, as an alternative to the traditional user interface operated with the keyboard and mouse duo, standard in CAD and AM, the paper presents a comprehensive multi-touch interaction system conceived as a customer-centric human-machine interface. To depict the proposed solutions, we adopt furniture manufacturing as a case study and, supported by a CAD-like software prototype for 3D modeling of custom cabinets introduced in a previous work of the authors, we assess our approach’s validity in terms of usability by conducting in-lab and remote user studies. The comparison between the designed multi-touch interaction and its desktop alternative yields promising results, showing improved performance and higher satisfaction of the end-user for the touch-based approach, that lay the groundwork for a smarter factory vision based on remotely-operated AM.

Motivated by the pervasiveness of artificial intelligence (AI) and the Internet of Things (IoT) in the current “smart everything” scenario, this article provides a comprehensive overview of the most recent research at the intersection of both domains, focusing on the design and development of specific mechanisms for enabling a collaborative inference across edge devices towards the in situ execution of highly complex state-of-the-art deep neural networks (DNNs), despite the resource-constrained nature of such infrastructures. In particular, the review discusses the most salient approaches conceived along those lines, elaborating on the specificities of the partitioning schemes and the parallelism paradigms explored, providing an organized and schematic discussion of the underlying workflows and associated communication patterns, as well as the architectural aspects of the DNNs that have driven the design of such techniques, while also highlighting both the primary challenges encountered at the design and operational levels and the specific adjustments or enhancements explored in response to them.