Real-Time Underwater Image Recognition with FPGA Embedded System for Convolutional Neural Network

Zhao, Minghao; Chen, Hu; Wei, Fenglin; Wang, Kai; Wang, Chong; Jiang, Yu

doi:10.3390/s19020350

Cited by 44 publications

(20 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…FPGA is wildly utilized in various tasks including deep learning [199,247,[331][332][333][334]. Inference accelerators are commonly implemented utilizing FPGA.…”

Section: Fpga-based Approachmentioning

confidence: 99%

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

et al. 2021

View full text Add to dashboard Cite

In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.

show abstract

“…FPGA is wildly utilized in various tasks including deep learning [199,247,[331][332][333][334]. Inference accelerators are commonly implemented utilizing FPGA.…”

Section: Fpga-based Approachmentioning

confidence: 99%

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Moreover, the compression techniques allowed the memory size to be reduced to 0.5 MB [31] compared to 240 MB for AlexNet. For low power consumption and strong computing capability, the use of Field-Programmable Gate Array (FPGA) for an image recognition system on the Convolution Neural Network [39] can also be considered. A sufficiently small model could be stored directly on the FPGAs, which have often less than 10MB of on-chip memory.…”

Section: State-of-the-artmentioning

confidence: 99%

The Effectiveness of Using a Pretrained Deep Learning Neural Networks for Object Classification in Underwater Video

2020

View full text Add to dashboard Cite

Video image processing and object classification using a Deep Learning Neural Network (DLNN) can significantly increase the autonomy of underwater vehicles. This paper describes the results of a project focused on using DLNN for Object Classification in Underwater Video (OCUV) implemented in a Biomimetic Underwater Vehicle (BUV). The BUV is intended to be used to detect underwater mines, explore shipwrecks or observe the process of corrosion of munitions abandoned on the seabed after World War II. Here, the pretrained DLNNs were used for classification of the following type of objects: fishes, underwater vehicles, divers and obstacles. The results of our research enabled us to estimate the effectiveness of using pretrained DLNNs for classification of different objects under the complex Baltic Sea environment. The Genetic Algorithm (GA) was used to establish tuning parameters of the DLNNs. Three different training methods were compared for AlexNet, then one training method was chosen for fifteen networks and the tests were provided with the description of the final results. The DLNNs were trained on servers with six medium class Graphics Processing Units (GPUs). Finally, the trained DLNN was implemented in the Nvidia JetsonTX2 platform installed on board of the BUV, and one of the network was verified in a real environment.

show abstract

“…32,33 They also utilized the parallel FP-growth algorithm to mine the data and briefly analyzed the results of the frequent itemsets and association rules. [34][35][36][37]…”

Section: Research Of Thermoclinementioning

confidence: 99%

Spatio-temporal dependence-based tensor fusion for thermocline analysis in Argo data

Jiang

Lin

Ruan

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part I:

Self Cite

View full text Add to dashboard Cite

As the ocean data acquired by the Argo project is increasingly huge, how to use artificial intelligence to analyze it so as to discover the distribution and variation of ocean temperature with space and time becomes an important research topic in the world. In this article, a spatio-temporal dependence-based tensor fusion method is proposed, which can be used to determine and analyze the thermocline. In the time dimension, long short-term memory is used to predict the temperature of seawater; in the spatial dimension, the thermocline is found incrementally by using tensor analysis. Experiments on BOA Argo data from 2004 to 2016 show that the proposed method can accurately determine the boundary of the thermocline and predict the future trend of the thermocline.

show abstract

Real-Time Underwater Image Recognition with FPGA Embedded System for Convolutional Neural Network

Cited by 44 publications

References 27 publications

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

The Effectiveness of Using a Pretrained Deep Learning Neural Networks for Object Classification in Underwater Video

Spatio-temporal dependence-based tensor fusion for thermocline analysis in Argo data

Contact Info

Product

Resources

About