Combined weightless neural network FPGA architecture for deforestation surveillance and visual navigation of UAVs

Torres, Vitor Alvarenga; Jaimes, Brayan René Acevedo; Ribeiro, Eduardo S.; Braga, Mateus T.; Shiguemori, Elcio Hideiti; Velho, Haroldo Fraga de Campos; Torres, Luiz C. B.; Braga, Antônio de Pádua

doi:10.1016/j.engappai.2019.08.021

Cited by 22 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9 The proposed pattern recognition systems are based on the implementation of Field Programmable Gate Arrays for visual navigation of the UAV. 10 Pingel et al 11 made a great contribution to the research by dealing with the problem of classifying spatial data according to the type of terrain. Profound research methods for visual applications for UAVs are also presented in the works of Ham et al 12 However, despite significant advances in this field, the need for simple and effective visual recognition systems remains.…”

Section: Introductionmentioning

confidence: 99%

“…Some scholars employed a machine learning classifier to detect repeated dynamic patterns and improve UAV navigation 9 . The proposed pattern recognition systems are based on the implementation of Field Programmable Gate Arrays for visual navigation of the UAV 10 . Pingel et al 11 made a great contribution to the research by dealing with the problem of classifying spatial data according to the type of terrain.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Retracted: An unmanned aerial vehicles navigation system on the basis of pattern recognition applications—Review of implementation options and prospects for development

2021

View full text Add to dashboard Cite

The popularity of unmanned aerial vehicles (UAVs) kept growing over the past few decades. UAVs are widely used in various fields for monitoring, mapping, aerial photography, rescue operations, and so forth. However, the UAV navigation may be difficult in areas where global positioning systems is not available. This article presents an analytical review of the promising methods of creating a navigation system based on a pattern recognition algorithm. Linear algebra and mathematical morphology to describe the operation of pattern recognition applications in UAV's navigation systems, classification of images through profound research of intelligent navigation systems, analysis and digital image processing to identify options for the implementation of artificial intelligent systems of visual navigation were used to identify existing pattern recognition applications in the process of constructive systematization. It was shown that the UAV navigation requires objects in the image to be recognized and the distance to a possible obstacle to be estimated using deep learning method for image segmentation and depth map estimation. An obligatory initial point in the image recognition algorithm is the image preprocessing procedures based on machine vision techniques. The results of this study may be useful in developing efficient UAV applications for military and civil purposes.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Retracted: An unmanned aerial vehicles navigation system on the basis of pattern recognition applications—Review of implementation options and prospects for development

2021

View full text Add to dashboard Cite

show abstract

“…However, they could not use the model to predict the amount or total area of deforestation and risk factors and could only determine whether deforestation risk exists. In addition, the weightless neural network architecture created by the field-programmable gate array in conjunction with an unmanned aerial vehicle for deforestation monitoring and visual navigation assessment in green rural regions is shown to provide a greater level of processing of visuals (Torres et al 2020). Tien Bui et al (2017) modeled forest fires by particle swarm optimization neurofuzzy, which can determine the optimal values of parameters and reasonably predict the causes of forest fires generated in Vietnam, random forest, and support vector machine.…”

Section: Artificial Intelligence For Natural Resource Management: Red...mentioning

confidence: 99%

Artificial intelligence-based solutions for climate change: a review

Chen

Zhang

et al. 2023

Environ Chem Lett

View full text Add to dashboard Cite

Climate change is a major threat already causing system damage to urban and natural systems, and inducing global economic losses of over $500 billion. These issues may be partly solved by artificial intelligence because artificial intelligence integrates internet resources to make prompt suggestions based on accurate climate change predictions. Here we review recent research and applications of artificial intelligence in mitigating the adverse effects of climate change, with a focus on energy efficiency, carbon sequestration and storage, weather and renewable energy forecasting, grid management, building design, transportation, precision agriculture, industrial processes, reducing deforestation, and resilient cities. We found that enhancing energy efficiency can significantly contribute to reducing the impact of climate change. Smart manufacturing can reduce energy consumption, waste, and carbon emissions by 30–50% and, in particular, can reduce energy consumption in buildings by 30–50%. About 70% of the global natural gas industry utilizes artificial intelligence technologies to enhance the accuracy and reliability of weather forecasts. Combining smart grids with artificial intelligence can optimize the efficiency of power systems, thereby reducing electricity bills by 10–20%. Intelligent transportation systems can reduce carbon dioxide emissions by approximately 60%. Moreover, the management of natural resources and the design of resilient cities through the application of artificial intelligence can further promote sustainability.

show abstract

“…Most algorithms that operate online using data from a single image detect defective pixels by computing statistical variations within a neighborhood centered around each pixel. Although these algorithms frequently run on programmable architectures such as traditional computers and embedded processors, custom hardware architectures can provide higher performance with lower resources and power consumption, which are required for applications such as assisted-driving automobiles [ 20 , 21 , 22 ], surveillance systems [ 23 , 24 , 25 ], and biometric recognition [ 26 , 27 , 28 ], among many others. Numerous researchers have proposed custom hardware devices to perform image processing in real time, which reduces power consumption and increases hardware integration.…”

Section: Introductionmentioning

confidence: 99%

A CMOS Image Readout Circuit with On-Chip Defective Pixel Detection and Correction

López-Portilla

Valenzuela

Zarkesh-Ha

et al. 2023

Sensors

View full text Add to dashboard Cite

Images produced by CMOS sensors may contain defective pixels due to noise, manufacturing errors, or device malfunction, which must be detected and corrected at early processing stages in order to produce images that are useful to human users and image-processing or machine-vision algorithms. This paper proposes a defective pixel detection and correction algorithm and its implementation using CMOS analog circuits, which are integrated with the image sensor at the pixel and column levels. During photocurrent integration, the circuit detects defective values in parallel at each pixel using simple arithmetic operations within a neighborhood. At the image-column level, the circuit replaces the defective pixels with the median value of their neighborhood. To validate our approach, we designed a 128×128-pixel imager in a 0.35μm CMOS process, which integrates our defective-pixel detection/correction circuits and processes images at 694 frames per second, according to post-layout simulations. Operating at that frame rate, our proposed algorithm and its CMOS implementation produce better results than current state-of-the-art algorithms: it achieves a Peak Signal to Noise Ratio (PSNR) and Image Enhancement Factor (IEF) of 45 dB and 198.4, respectively, in images with 0.5% random defective pixels, and a PSNR of 44.4 dB and IEF of 194.2, respectively, in images with 1.0% random defective pixels.

show abstract

Combined weightless neural network FPGA architecture for deforestation surveillance and visual navigation of UAVs

Cited by 22 publications

References 19 publications

Retracted: An unmanned aerial vehicles navigation system on the basis of pattern recognition applications—Review of implementation options and prospects for development

Retracted: An unmanned aerial vehicles navigation system on the basis of pattern recognition applications—Review of implementation options and prospects for development

Artificial intelligence-based solutions for climate change: a review

A CMOS Image Readout Circuit with On-Chip Defective Pixel Detection and Correction

Contact Info

Product

Resources

About