Real-Time Detection of Hogweed: UAV Platform Empowered by Deep Learning

Menshchikov, Alexander; Shadrin, Dmitrii; Prutyanov, Viktor; Lopatkin, Daniil; Sosnin, Sergey; Tsykunov, Evgeny; Iakovlev, Evgeny; Somov, Andrey

doi:10.1109/tc.2021.3059819

Cited by 43 publications

(25 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The analysis of the distribution of both species showed that the regions most affected by the compact invaded areas of Caucasian hogweeds have been located mainly in Eastern Europe, where poorer countries did not have funds to remove the invasion, especially around 30-40 years ago when together with the mentioned fall of communism and modification of the agricultural system, former crops were abandoned. Sometimes the invasion patches became so large that satellite imagery and other spatial analysis tools were used to select where the problem with invasion should be resolved as a priority [54][55][56][57][58][59]. In connection with the massive spread of H. sosnowskyi in Russia, even questions were raised about the need to create a special federal target program to control it.…”

Section: Dispersal Of the Caucasian Hogweedsmentioning

confidence: 99%

Invasion of the Giant Hogweed and the Sosnowsky’s Hogweed as a Multidisciplinary Problem with Unknown Future—A Review

Grzędzicka

2022

Earth

View full text Add to dashboard Cite

Caucasian hogweeds are plants introduced to Europe from the Caucasus area. This review concerns the two most common ones—the giant hogweed Heracleum mantegazzianum and the Sosnowsky’s hogweed Heracleum sosnowskyi. The first of them was imported as garden decorations from the 19th century, mainly to Western Europe, while the second one was introduced from the mid–20th century to agricultural areas in Eastern Europe. Nowadays, these two species create one of the most problematic invasions in the world. This review aimed to synthesize research on those invaders based on 277 articles selected from the “Scopus” database. Most of the articles concerned their extensive distribution, at least on a continental scale and the rapid dispersal. The reviewed research showed that the complex physicochemical properties of hogweeds tissues and secretions significantly affected insects, aphids, ants, nematodes, fungi, soil microorganisms, plant communities, birds, and many other components of the ecosystems. This knowledge turned out to be disproportionately small to the scale of the problem. The review also showed what ecological traits of hogweeds were responsible for their wide and various role in the environment. Thus far, no effective method to eradicate Caucasian hogweeds has been found. This could be a growing mistake, given that they are probably during the rapid evolutionary changes within the range of their invasion.

show abstract

Section: Dispersal Of the Caucasian Hogweedsmentioning

confidence: 99%

Invasion of the Giant Hogweed and the Sosnowsky’s Hogweed as a Multidisciplinary Problem with Unknown Future—A Review

Grzędzicka

2022

Earth

View full text Add to dashboard Cite

show abstract

“…It was shown, that this setup outperforms previous state-of-the-art approaches and improves the accuracy of crop-weed classification without requiring a retraining of the model. In [8] the authors reported on a comparison between other segmentation CNNs which showed that U-Net performance is slightly lower than the competing SegNet and RefineNet with ResNet backbone. However, the computational complexity of the latter two models does not allow for deploying them to an embedded unit and perform the inference in real-time during the mission.…”

Section: B Image Analysis In Precision Agriculturementioning

confidence: 99%

“…In our previous work [8] we focused on the optimization of the most relevant FCNN architectures for inference on board the Single Board Computer (SBC). The point of this work was the feasibility of the application of such a drone with AI on board in Precision Agriculture (PA).…”

Section: B Image Analysis In Precision Agriculturementioning

confidence: 99%

Drone-Aided Detection of Weeds: Transfer Learning for Embedded Image Processing

Koshelev

Savinov

Menshchikov

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

“…Our toolkit was mentioned in works [18,19] as a tool that is able to run FCNNs in real-time on embedded systems. It was also used in [20] when it was a part of the navigation stack for the vision-based exploration of an unknown environment.…”

Section: Impactmentioning

confidence: 99%