Spatial–Spectral Image Classification with Edge Preserving Method

Merugu, Suresh; Tiwari, Anuj; Sharma, Surendra Kumar

doi:10.1007/s12524-020-01265-7

Cited by 28 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model constructs a knowledge graph to encode contextual relationships and utilizes prior contextual relationships to influence the object detection process. Merugu et al [30] integrated image classification with spatial context information by combining colorimetric edge preservation with spatial-spectral modeling.…”

Section: Context Informationmentioning

confidence: 99%

Composite Backbone Small Object Detection Based on Context and Multi-Scale Information with Attention Mechanism

Jing,

Liu,

Liu

2024

Mathematics

View full text Add to dashboard Cite

Object detection has gained widespread application across various domains; nevertheless, small object detection still presents numerous challenges due to the inherent limitations of small objects, such as their limited resolution and susceptibility to interference from neighboring elements. To improve detection accuracy of small objects, this study presents a novel method that integrates context information, attention mechanism, and multi-scale information. First, to realize feature augmentation, a composite backbone network is employed which can jointly extract object features. On this basis, to efficiently incorporate context information and focus on key features, the composite dilated convolution and attention module (CDAM) is designed, consisting of a composite dilated convolution module (CDM) and convolutional block attention module (CBAM). Then, a feature elimination module (FEM) is introduced to reduce the feature proportion of medium and large objects on feature layers; the impact of neighboring objects on small object detection can thereby be mitigated. Experiments conducted on MS COCO validate the superior performance of the method compared with baseline detectors, while it yields an average enhancement of 0.8% in overall detection accuracy, with a notable enhancement of 2.7% in small object detection.

show abstract

Section: Context Informationmentioning

confidence: 99%

Composite Backbone Small Object Detection Based on Context and Multi-Scale Information with Attention Mechanism

Jing,

Liu,

Liu

2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…In opposition to a huge variety of device fuctuations found in the MG, the massive bandwidth, reminiscence impact, along with fat phase contribution in the frequency reaction of FOPID were formulated to craft the controller and were executed nicely. From a hybrid algorithm, the amalgamation of a dynamic genetic with a bacteria foraging approach, initially, and the T2FFOPID's parameter tuning trouble were changed [21]. Via nonlinear time domain simulations along with performance indices underneath variant disturbances along with working criteria, the controller's functionality in the lower-frequency oscillations within the device having numerous MG penetration ratios was examined.…”

Section: Related Workmentioning

confidence: 99%

An FRLQG Controller-Based Small-Signal Stability Enhancement of Hybrid Microgrid Using the BCSSO Algorithm

Ensermu

Santhi

Merugu

et al. 2023

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

The development of a network termed microgrid (MG) has been motivated owing to augmentation in renewable energy source (RES) infiltration along with the utilization of enhanced power electronic technologies. Recently, more popularity has been gained by the hybrid MG (HMG). Maintaining the power system’s (PS) small-signal stability (SSS) is highly complicated during the energy enhancement of RES. The enhancement of the SSS has been focused on by numerous existing methodologies; however, the optimal solution was not obtained by those methodologies. A new controller with the assistance of bell-curved squirrel search optimization (BCSSO) is proposed to address the aforementioned issue. Initially, for PSs such as photovoltaic (PV), wind turbines, along with fuel cells, a mathematical model is ascertained. Then, in this, the converter design has been developed. The PV’s maximum power flow is recognized by maximum power point tracking (MPPT) in the bidirectional switched buck-boost converter (BSBBC), which is utilized in this research, and by utilizing the fuzzy ruled linear quadratic Gaussian (FRLQG), the converters are controlled to assure safe operation along with soft dynamics. By employing the BCSSO, the parameters are modified in this controller which in turn ameliorates the SSS. The experiential evaluation of the proposed system’s performance is analogized with the existing methodologies. Consequently, the outcomes confirmed that a better performance was attained by the proposed methodology than the prevailing works.

show abstract

“…Assistive devices worn on the tongue: Tongue Display Unit(TDU) [17] converts the images captured by camera into electro tactile stimuli and are sent to dorsum of the tongue through a flexible electrode array which is placed on the tongue.…”

Section: Wearable Assistive Toolsmentioning

confidence: 99%

A Review of Some Assistive Tools and their Limitations for Visually Impaired

Merugu¹,

Ghinea²,

Shaik³

et al. 2022

helix

Self Cite

View full text Add to dashboard Cite

World report on Vision by World Health Organization reported that there are at least 2.2 Billion people are Visually Impaired. "The National Blindness & Visual Impairment Survey India 2015-2019" survey report by Government of India reported that the overall estimated prevalence of the Blindness in age 50 or more is 1.99% and the overall estimated prevalence of Visually Impaired in age 50 or more is 13.76%. The above numbers urge researchers to develop advanced assistive tools for Blind and Visually Impaired. There have been several assistive tools already designed to assist and enhance the quality of life to Blind and Visually Impaired. But most of them are limited and confined to specific problems. In this paper, a systematic review of some of the assistive tools for Blind and Visually Impaired is done. The detailed review of existing assistive tools reveals that the factors like user-friendly, ensuring safety, independent mobility, multiple features and user-centric design need priority consideration while designing such tools.

show abstract

Spatial–Spectral Image Classification with Edge Preserving Method

Cited by 28 publications

References 20 publications

Composite Backbone Small Object Detection Based on Context and Multi-Scale Information with Attention Mechanism

Composite Backbone Small Object Detection Based on Context and Multi-Scale Information with Attention Mechanism

An FRLQG Controller-Based Small-Signal Stability Enhancement of Hybrid Microgrid Using the BCSSO Algorithm

A Review of Some Assistive Tools and their Limitations for Visually Impaired

Contact Info

Product

Resources

About