FeatFlow: Learning geometric features for 3D motion estimation

Li, Qing; Wang, Cheng; Li, Xin; Wen, Chenglu

doi:10.1016/j.patcog.2020.107574

Cited by 3 publications

(2 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method involves preprocessing, segmentation, feature extraction, and other steps on the image, followed by the use of classification algorithms for judgment and counting [3]. For example, image processing techniques can be used to perform binarization, filtering, edge detection, and other operations on potato sprout images, and then morphological operations and feature extraction algorithms can be used to detect sprouts [4]. Finally, machine learning based classifiers such as support vector machines, decision trees, etc.…”

Section: Morphological Characteristics Of Potato Eyes and Traditional...mentioning

confidence: 99%

Research Progress in Potato Bud Recognition

2023

acss

View full text Add to dashboard Cite

In recent years, with the continuous development of agricultural technology, potato bud recognition technology has attracted more and more attention. Potato bud recognition is the key to the automatic cutting of potato seed tubers, which has a significant impact on the quality and yield of potatoes. Therefore, bud recognition technology is of great significance for the management and decision-making of agricultural production. At present, research on potato bud recognition mainly focuses on morphological methods, computer vision, and deep learning. Among them, morphological methods are mainly based on the theory of mathematical morphology, through the extraction and processing of morphological features of the bud eye to achieve recognition; Computer vision methods mainly use techniques such as image processing and feature extraction to achieve eye bud recognition; The deep learning method is mainly based on neural network models and achieves automatic recognition of eye buds through training with a large amount of data. In recent years, with the development of deep learning technology, potato bud recognition methods based on convolutional neural networks have become a research hotspot. By constructing a convolutional neural network model and using data enhancement, transfer learning and other methods, researchers have achieved a relatively significant recognition effect, but for potato bud eyes with attachments or mechanical damage on the surface, the recognition effect is general. Therefore, this article aims to review the current research progress of potato bud recognition, and seek a more efficient, accurate, and robust bud recognition technology that can provide better decision support for agricultural production, thereby improving the yield and quality of potatoes, reducing manual operation time and cost, and improving production efficiency and economic benefits.

show abstract

Section: Morphological Characteristics Of Potato Eyes and Traditional...mentioning

confidence: 99%

Research Progress in Potato Bud Recognition

2023

acss

View full text Add to dashboard Cite

show abstract

“…As a result, naked eye visibility still plays a key role in making decisions, especially at close range. Going further, projects have been carried out on the creation of autonomous vessels [1,2], in which autonomous navigation makes use of motion flow techniques, such as FeatFlow [3], as auxiliary sources of information.…”

Section: Introductionmentioning

confidence: 99%

Using Conventional Cameras as Sensors for Estimating Confidence Intervals for the Speed of Vessels from Single Images

Huillca

Fernandes

2022

Sensors

View full text Add to dashboard Cite

In this paper, we describe an image-based approach for estimating the speed of a moving vessel using the wakes that remain on the surface of water after the vessel has passed. The proposed method calculates the speed of the vessel using only one RGB image. In this study, we used the vanishing line of the mean water plane, the camera height concerning the level of the tide, and the intrinsic parameters of the camera to perform geometric rectification on the surface plane of the water. We detected the location of troughs on one of the wake arms and computed the distance between them in the rectified image to estimate the speed of the vessel as a so-called inverse ship wake problem. We used a radar that was designed to monitor ships to validate the proposed method. We used statistical studies to determine the reliability and error propagation of the estimated values throughout the calculation process. The experiments showed that the proposed method produced precise and accurate results that agreed with the actual radar data when using a simple capture device, such as a conventional camera.

show abstract

LiDAR-based localization using universal encoding and memory-aware regression

Wang

Wen

et al. 2022

Pattern Recognition

View full text Add to dashboard Cite

FeatFlow: Learning geometric features for 3D motion estimation

Cited by 3 publications

References 62 publications

Research Progress in Potato Bud Recognition

Research Progress in Potato Bud Recognition

Using Conventional Cameras as Sensors for Estimating Confidence Intervals for the Speed of Vessels from Single Images

LiDAR-based localization using universal encoding and memory-aware regression

Contact Info

Product

Resources

About