A historical perspective of algorithmic lateral inhibition and accumulative computation in computer vision

计算机视觉算法侧抑制与累积计算之历史展望

Neurocomputing, Volume 74, Issue 8, 15 March 2011, Pages 1175-1181

Abstract: Certainly, one of the prominent ideas of Professor José Mira was that it is absolutely mandatory to specify the mechanisms and/or processes underlying each task and inference mentioned in an architecture in order to make operational that architecture. The conjecture of the last fifteen years of joint research has been that any bottom-up organization may be made operational using two biologically inspired methods called “algorithmic lateral inhibition”, a generalization of lateral inhibition anatomical circuits, and “accumulative computation”, a working memory related to the temporal evolution of the membrane potential. This paper is dedicated to the computational formulation of both methods. Finally, all of the works of our group related to this methodological approximation are mentioned and summarized, showing that all of them support the validity of this approximation.

Computer vision techniques for construction safety and health monitoring

计算机视觉技术在施工安全与健康监测中的应用

Advanced Engineering Informatics, Volume 29, Issue 2, April 2015, Pages 239-251

Abstract: For construction safety and health, continuous monitoring of unsafe conditions and action is essential in order to eliminate potential hazards in a timely manner. As a robust and automated means of field observation, computer vision techniques have been applied for the extraction of safety related information from site images and videos, and regarded as effective solutions complementary to current time-consuming and unreliable manual observational practices. Although some research efforts have been directed toward computer vision-based safety and health monitoring, its application in real practice remains premature due to a number of technical issues and research challenges in terms of reliability, accuracy, and applicability. This paper thus reviews previous attempts in construction applications from both technical and practical perspectives in order to understand the current status of computer vision techniques, which in turn suggests the direction of future research in the field of computer vision-based safety and health monitoring. Specifically, this paper categorizes previous studies into three groups—object detection, object tracking, and action recognition—based on types of information required to evaluate unsafe conditions and acts. The results demonstrate that major research challenges include comprehensive scene understanding, varying tracking accuracy by camera position, and action recognition of multiple equipment and workers. In addition, we identified several practical issues including a lack of task-specific and quantifiable metrics to evaluate the extracted information in safety context, technical obstacles due to dynamic conditions at construction sites and privacy issues. These challenges indicate a need for further research in these areas. Accordingly, this paper provides researchers insights into advancing knowledge and techniques for computer vision-based safety and health monitoring, and offers fresh opportunities and considerations to practitioners in understanding and adopting the techniques.

Target-lesscomputer visionfor traffic signal structure vibration studies

无目标计算机视觉技术在交通信号结构震动研究中的应用

Mechanical Systems and Signal Processing, Volumes 60–61, August 2015, Pages 571-582

Abstract: The presented computer vision method allows for non-contact, target-less determination of traffic signal structure displacement and modal parameters, including mode shapes. By using an analytical model to relate structural displacement to stress, it is shown possible to utilize a rapid set-up and take-down computer vision-based system to infer structural stresses to a high degree of precision. Using this computer vision method, natural frequencies of the structure are determined with accuracy similar to strain gage and string potentiometer instrumentation. Even with structural displacements measured at less than 0.5 pixel, excellent mode shape results are obtained. Finally, one-minute equivalent stress ranges from ambient wind excitation are found to have excellent agreement between the inferred stress from strain gage data and stresses calculated from computer vision tied to an analytical stress model. This demonstrates the ability of this method and implemented system to develop fatigue life estimates using wind velocity data and modest technical means.

Context-AwareComputation Offloading for Mobile Cloud Computing: Requirements Analysis, Survey and Design Guideline

移动云计算情景感知计算卸载：需求分析、研究与设计指导原则

Procedia Computer Science, Volume 56, 2015, Pages 10-17

Abstract: Along with the rise of mobile handheld devices the resource demands of respective applications grow as well. However, mobile devices are still and will always be limited related to performance (e.g., computation, storage and battery life), context adaptation (e.g., intermittent connectivity, scalability and heterogeneity) and security aspects. A prominent solution to overcome these limita- tions is the so-called computation offloading, which is the focus of mobile cloud computing (MCC). However, current approaches fail to address the complexity that results from quickly and constantly changing context conditions in mobile user scenarios and hence developing effective and efficient MCC applications is still challenging. Therefore, this paper first presents a list of re- quirements for MCC applications together with a survey and classification of current solutions. Furthermore, it provides a design guideline for the selection of suitable concepts for different classes of common cloud-augmented mobile applications. Finally, it presents open issues that developers and researchers should be aware of when designing their MCC-approach.

Integration of Cloud computing and Internet of Things: A survey

云计算与物联网之整合研究

Future Generation Computer Systems, Available online 3 October 2015

Abstract: Cloud computing and Internet of Things (IoT) are two very different technologies that are both already part of our life. Their adoption and use are expected to be more and more pervasive, making them important components of the Future Internet. A novel paradigm where Cloud and IoT are merged together is foreseen as disruptive and as an enabler of a large number of application scenarios. In this paper, we focus our attention on the integration of Cloud and IoT, which is what we call the CloudIoT paradigm. Many works in literature have surveyed Cloud and IoT separately and, more precisely, their main properties, features, underlying technologies, and open issues. However, to the best of our knowledge, these works lack a detailed analysis of the new CloudIoT paradigm, which involves completely new applications, challenges, and research issues. To bridge this gap, in this paper we provide a literature survey on the integration of Cloud and IoT. Starting by analyzing the basics of both IoT and Cloud Computing, we discuss their complementarity, detailing what is currently driving to their integration. Thanks to the adoption of the CloudIoT paradigm a number of applications are gaining momentum: we provide an up-to-date picture of CloudIoT applications in literature, with a focus on their specific research challenges. These challenges are then analyzed in details to show where the main body of research is currently heading. We also discuss what is already available in terms of platforms–both proprietary and open source–and projects implementing the CloudIoT paradigm. Finally, we identify open issues and future directions in this field, which we expect to play a leading role in the landscape of the Future Internet.