A Loosely Coupled Extended Kalman Filter Algorithm for Agricultural Scene-Based Multi-Sensor Fusion

Lv, Meibo; Wei, Hai‐Rui; Fu, Xinyu; Wang, Wuwei; Zhou, Daming

doi:10.3389/fpls.2022.849260

Cited by 13 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ML technique serves as a correction factor to estimate model error. The findings indicate that, compared to traditional and alternative Kalman filter models [25], our hybrid models have a goodness of fit of more than 0.95 and much lower root mean square and absolute mean errors. The method's applicability to various settings was shown further in two different ways.…”

Section: Related Workmentioning

confidence: 86%

Hybrid CNN-SVM Classifier Approaches to Process Semi-Structured Data in Sugarcane Yield Forecasting Production

et al. 2023

View full text Add to dashboard Cite

Information communication technology (ICT) breakthroughs have boosted global social and economic progress. Most rural Indians rely on agriculture for income. The growing population requires modern agricultural practices. ICT is crucial for educating farmers on how to be environmentally friendly. It helps them create more food by solving a variety of challenges. India’s sugarcane crop is popular and lucrative. Long-term crops that require water do not need specific soil. They need water; the ground should always have adequate water due to the link between cane growth and evaporation. This research focuses on forecasting soil moisture and classifying sugarcane output; sugarcane has so many applications that it must be categorized. This research examines these claims: The first phase model predicts soil moisture using two-level ensemble classifiers. Secondly, to boost performance, the proposed ensemble model integrates the Gaussian probabilistic method (GPM), the convolutional neural network (CNN), and support vector machines (SVM). The suggested approach aims to correctly anticipate future soil moisture measurements affecting crop growth and cultivation. The proposed model is 89.53% more accurate than conventional neural network classifiers. The recommended models’ outcomes will assist farmers and agricultural authorities in boosting production.

show abstract

Section: Related Workmentioning

confidence: 86%

Hybrid CNN-SVM Classifier Approaches to Process Semi-Structured Data in Sugarcane Yield Forecasting Production

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The Kalman filter (KFA) algorithm is a predictor algorithm in the form of mathematical equations to estimate a process by minimizing the value of SME (Square Mean Error), and a feedback process occurs from the sensor as an output [40,[42][43][44]. The sensor output still contains noise that interferes with the expected output results.…”

Section: 2 Implementation Of Kalman Filter Algorithm To Reduce Noisementioning

confidence: 99%

Implementation of Kalman filter algorithm to optimize the calculation of ultrasonic sensor distance value in Hooke law props system

Pratiwi,

Fadli,

Cahyanto

et al. 2024

EEJET

View full text Add to dashboard Cite

The Kalman filter algorithm is very important as a recursive algorithm method to optimize sensor output from physical parameter measurement systems, especially physics practicum demonstration systems. One of the distance parameter measurement demonstration systems used in Hooke’s law demonstration system is applied in physics practicum, the system has problems related to fluctuating or unstable sensor output. This research implements the Kalman filter algorithm on the Arduino IDE sketch to reduce noise that appears at the ultrasonic sensor output. The methodology used in this study includes the application of the Kalman filter algorithm to the Arduino IDE sketch with the variable value of the Kalman filter algorithm equation modified with a value of R=10, H=1, and Q=1, and returns the filtered Kalman out value. The Arduino output results are exported to Ms. Excel for further analysis and generate a filtered ultrasonic sensor output signal graph compared without using the Kalman filter. The ultrasonic sensor output noise filtration effectively reduces noise by showing a decrease in the mean squared error (MSE) value and obtaining the best performance of up to 89.23 %. The accuracy of Kalman filter filtration results can be seen from the calculation that the spring constant of filtered metal materials is smaller than the conventional measurement spring constant. Accurate and effective results with the implementation of the Kalman filter algorithm can be developed for the variation values of distance parameters and Kalman filter algorithm variables (R, Q, and H) with other value variations, especially variables that produce filtering curves close to straight lines. It was concluded that the Kalman filter algorithm was able to improve the performance of Hooke’s law prop system

show abstract

“…We highlight the methodology that inspires our study in blue-dashed rectangles in Figure 2 . Where the loosely coupled fusion strategy [ 32 ] is adopted to keep constant computational complexity for real-time performance, along with adding a reset mode for the framework, as discussed in [ 33 ] as well as an online IMU-camera extrinsic calibration paradigm [ 4 ]. Integrating the IMU/GPS readings with the global shutter visual sensor monocular frames raises our localization solution’s accuracy level, leveraging the MAV’s inertial and global localization information.…”

Section: Related Workmentioning

confidence: 99%

MAV Localization in Large-Scale Environments: A Decoupled Optimization/Filtering Approach

Soliman

Hadj-Abdelkader

Bonardi

et al. 2023

Sensors

View full text Add to dashboard Cite

Developing new sensor fusion algorithms has become indispensable to tackle the daunting problem of GPS-aided micro aerial vehicle (MAV) localization in large-scale landscapes. Sensor fusion should guarantee high-accuracy estimation with the least amount of system delay. Towards this goal, we propose a linear optimal state estimation approach for the MAV to avoid complicated and high-latency calculations and an immediate metric-scale recovery paradigm that uses low-rate noisy GPS measurements when available. Our proposed strategy shows how the vision sensor can quickly bootstrap a pose that has been arbitrarily scaled and recovered from various drifts that affect vision-based algorithms. We can consider the camera as a “black-box” pose estimator thanks to our proposed optimization/filtering-based methodology. This maintains the sensor fusion algorithm’s computational complexity and makes it suitable for MAV’s long-term operations in expansive areas. Due to the limited global tracking and localization data from the GPS sensors, our proposal on MAV’s localization solution considers the sensor measurement uncertainty constraints under such circumstances. Extensive quantitative and qualitative analyses utilizing real-world and large-scale MAV sequences demonstrate the higher performance of our technique in comparison to most recent state-of-the-art algorithms in terms of trajectory estimation accuracy and system latency.

show abstract

A Loosely Coupled Extended Kalman Filter Algorithm for Agricultural Scene-Based Multi-Sensor Fusion

Cited by 13 publications

References 30 publications

Hybrid CNN-SVM Classifier Approaches to Process Semi-Structured Data in Sugarcane Yield Forecasting Production

Hybrid CNN-SVM Classifier Approaches to Process Semi-Structured Data in Sugarcane Yield Forecasting Production

Implementation of Kalman filter algorithm to optimize the calculation of ultrasonic sensor distance value in Hooke law props system

MAV Localization in Large-Scale Environments: A Decoupled Optimization/Filtering Approach

Contact Info

Product

Resources

About