CMOS Vision Sensors: Embedding Computer Vision at Imaging Front-Ends

Rodríguez-Vázquez, Á.; Fernández-Berni, Jorge; Leñero‐Bardallo, Juan A.; Vornicu, Ion; Carmona-Galán, Ricardo

doi:10.1109/mcas.2018.2821772

Cited by 27 publications

(19 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of material wear detection, three-dimensional (3D) sensors are also used, which represent new technical means for obtaining information. Three-dimensional data provides more information and at the same time, reduces the deviation of the measured data [ 130 ]. A large group of sensors consists of chemical character sensors.…”

Section: Resultsmentioning

confidence: 99%

Predictive Maintenance and Intelligent Sensors in Smart Factory: Review

Pech

Vrchota

Bednář

2021

Sensors

232

View full text Add to dashboard Cite

With the arrival of new technologies in modern smart factories, automated predictive maintenance is also related to production robotisation. Intelligent sensors make it possible to obtain an ever-increasing amount of data, which must be analysed efficiently and effectively to support increasingly complex systems’ decision-making and management. The paper aims to review the current literature concerning predictive maintenance and intelligent sensors in smart factories. We focused on contemporary trends to provide an overview of future research challenges and classification. The paper used burst analysis, systematic review methodology, co-occurrence analysis of keywords, and cluster analysis. The results show the increasing number of papers related to key researched concepts. The importance of predictive maintenance is growing over time in relation to Industry 4.0 technologies. We proposed Smart and Intelligent Predictive Maintenance (SIPM) based on the full-text analysis of relevant papers. The paper’s main contribution is the summary and overview of current trends in intelligent sensors used for predictive maintenance in smart factories.

show abstract

Section: Resultsmentioning

confidence: 99%

Predictive Maintenance and Intelligent Sensors in Smart Factory: Review

Pech

Vrchota

Bednář

2021

Sensors

232

View full text Add to dashboard Cite

show abstract

“…. , N}, but is part of the 3 × 3 neighborhood of a cell, which belongs to the cellular network, being listed in the set 5 It is important to note that only CNN hardware realizations with such a basic coupling configuration have been developed so far (Vázquez et al, 2018). v xi,j across a capacitor with capacitance C xi,j R > 0 , expressing the state, and the output voltage v yi,j .…”

Section: Theory Of Cellular Nonlinear Networkmentioning

confidence: 99%

“…Besides constitutive the ideal framework for modeling biological systems (Chua, 1998;Chua and Roska, 2002), Cellular Nonlinear Networks (CNNs) (Chua and Yang, 1988a;Chua and Yang, 1988b) represent a powerful multi-variate signal processing paradigm, which, featuring a bio-inspired architecture, operates in a massively parallel fashion, allowing to process data at very high rates, as necessary in time-critical Internet-of-Things (IoT) applications, nowadays. Purely CMOS analogue hardware implementations of the CNN signal processing paradigm are typically co-integrated with highly selective equal-sized sensor arrays to allow the solution of complex computing tasks directly where the acquisition of specific data takes place (Vázquez et al, 2018). A technological issue, which limits the applicability scope of these sensor-processor arrays, is related to the huge difference between the typically small minimum size of an element of the sensor matrix, and the relatively large minimum integrated circuit (IC) area, which a processing element of the CNN hardware realization usually occupies, due to the fact that it needs to accommodate memory units, which endow the resulting computing machine with local stored programmability on board, allowing to harness thoroughly the advantages associated with the massive parallelism of the CNN signal processing paradigm.…”

Section: Introductionmentioning

confidence: 99%

“…However, as is the case here, converting traditional nonlinear circuits to memristive equivalents may require the extension of classical nonlinear system-theoretic techniques. The Memristor Cellular Nonlinear Network (M-CNN), proposed in Tetzlaff et al (2020), differs from a standard time-and space-invariant two-dimensional CNN (Chua and Yang, 1988a;Chua and Yang, 1988b), characterized by first-order cells, and typically implemented in hardware (Vázquez et al, 2018), for the inclusion of a single nonvolatile memristor in parallel to the capacitor in the circuit implementation of each processing element. One of the most powerful tools for the analysis of nonlinear dynamical systems with one degree of freedom is the Dynamic Route Map (DRM) (Chua, 2018a), which represents the system-theoretic technique of reference for the investigation of CNNs with first-order processing elements.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

System-Theoretic Methods for Designing Bio-Inspired Mem-Computing Memristor Cellular Nonlinear Networks

Ascoli

Tetzlaff

Kang

et al. 2021

Front. Nanotechnol.

View full text Add to dashboard Cite

The introduction of nano-memristors in electronics may allow to boost the performance of integrated circuits beyond the Moore era, especially in view of their extraordinary capability to process and store data in the very same physical volume. However, recurring to nonlinear system theory is absolutely necessary for the development of a systematic approach to memristive circuit design. In fact, the application of linear system-theoretic techniques is not suitable to explore thoroughly the rich dynamics of resistance switching memories, and designing circuits without a comprehensive picture of the nonlinear behaviour of these devices may lead to the realization of technical systems failing to operate as desired. Converting traditional circuits to memristive equivalents may require the adaptation of classical methods from nonlinear system theory. This paper extends the theory of time- and space-invariant standard cellular nonlinear networks with first-order processing elements for the case where a single non-volatile memristor is inserted in parallel to the capacitor in each cell. A novel nonlinear system-theoretic method allows to draw a comprehensive picture of the dynamical phenomena emerging in the memristive mem-computing array, beautifully illustrated in the so-called Primary Mosaic for the class of uncoupled memristor cellular nonlinear networks. Employing this new analysis tool it is possible to elucidate, with the support of illustrative examples, how to design variability-tolerant bio-inspired cellular nonlinear networks with second-order memristive cells for the execution of computing tasks or of memory operations. The capability of the class of memristor cellular nonlinear networks under focus to store and process information locally, without the need to insert additional memory units in each cell, may allow to increase considerably the spatial resolution of state-of-the-art purely CMOS sensor-processor arrays. This is of great appeal for edge computing applications, especially since the Internet-of-Things industry is currently calling for the realization of miniaturized, lightweight, low-power, and high-speed mem-computers with sensing capability on board.

show abstract

“…Early machine vision, on the other hand primarily relied on developing better photodetectors and in some instances integrating CMOS-based preprocessing modules for image filtering, feature extraction, light-level adaptation, noise elimination etc. bridging the gap between "sensing" and "compute" [24][25][26][27][28]. More recent developments in the area of brain-inspired machine vision also attempts to combine "sensing" with "memory" [13,23,29].…”

mentioning

confidence: 99%

A Bio-inspired and Low-power 2D Machine Vision with Adaptive Machine Learning and Forgetting

Dodda¹,

Jayachandran²,

Radhakrishnan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Natural intelligence has many dimensions, and in animals, learning about the environment and making behavioral changes are some of its manifestations. In primates vision plays a critical role in learning. The underlying biological neural networks contain specialized neurons and synapses which not only sense and process the visual stimuli but also learns and adapts, with remarkable energy efficiency. Forgetting also plays an active role in learning. Mimicking the adaptive neurobiological mechanisms for seeing, learning, and forgetting can, therefore, accelerate the development of artificial intelligence (AI) and bridge the massive energy gap that exists between AI and biological intelligence. Here we demonstrate a bio-inspired machine vision based on large area grown monolayer 2D phototransistor array integrated with analog, non-volatile, and programmable memory gate-stack that not only enables direct learning, and unsupervised relearning from the visual stimuli but also offers learning adaptability under photopic (bright-light), scotopic (low-light), as well as noisy illumination conditions at miniscule energy expenditure. In short, our “all-in-one” hardware vision platform combines “sensing”, “computing” and “storage” not only to overcome the von Neumann bottleneck of conventional complementary metal oxide semiconductor (CMOS) technology but also to eliminate the need for peripheral circuits and sensors.

show abstract

CMOS Vision Sensors: Embedding Computer Vision at Imaging Front-Ends

Cited by 27 publications

References 40 publications

Predictive Maintenance and Intelligent Sensors in Smart Factory: Review

Predictive Maintenance and Intelligent Sensors in Smart Factory: Review

System-Theoretic Methods for Designing Bio-Inspired Mem-Computing Memristor Cellular Nonlinear Networks

A Bio-inspired and Low-power 2D Machine Vision with Adaptive Machine Learning and Forgetting

Contact Info

Product

Resources

About