Applications of UAS in Crop Biomass Monitoring: A Review

Wang, Tianhai; Liu, Yadong; Wang, Minghui; Qing, Fan; Tian, Hongkun; Qiao, Xi; Li, Yanzhou

doi:10.3389/fpls.2021.616689

Cited by 36 publications

(35 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The trajectories of multi-and hyperspectral measurements on the basis of copters can be constructed in wide ranges (the scanning of specific areas or point-by-point scanning of interesting parts can be used; the height of measurements can be controlled; the copter can hang over the area of interest and makes dependable observations; etc.) [53]. The resolutions of these systems vary from a few cm to tens of cm [33]; this property is interesting for the research of different spatial scales.…”

Section: Some Platforms For the Plant Remote Sensingmentioning

confidence: 99%

“…However, drones are more expensive than copters and cannot be used for the accurate scanning of interesting areas (there are minimal speeds and The prospective group is UAS platforms, which includes copters and drones [23]. The automatization of plant remote sensing on the basis of UAS is very high for both drones and copters because a program of flight can be automatically formed in accordance with a program of measurements [33,53]. The trajectories of multi-and hyperspectral measurements on the basis of copters can be constructed in wide ranges (the scanning of specific areas or point-by-point scanning of interesting parts can be used; the height of measurements can be controlled; the copter can hang over the area of interest and makes dependable observations; etc.)…”

Section: Some Platforms For the Plant Remote Sensingmentioning

confidence: 99%

“…However, drones are more expensive than copters and cannot be used for the accurate scanning of interesting areas (there are minimal speeds and heights of the flight of drones [27,33]); as a result, increasing the total area of investigation and duration of the flight by using drones is accompanied with a decrease in the resolution of the measurements [33]. Using airplanes for plant remote sensing is similar to using drones, but their loading capacity and speed are even greater; the last point increases the spatial and temporal scale of the measurement and decreases the spatial resolution [53]. Additionally, airplanes are very expensive, and their application requires the participation of pilots (i.e., automatization is lower) [53].…”

Section: Some Platforms For the Plant Remote Sensingmentioning

confidence: 99%

“…Using airplanes for plant remote sensing is similar to using drones, but their loading capacity and speed are even greater; the last point increases the spatial and temporal scale of the measurement and decreases the spatial resolution [53]. Additionally, airplanes are very expensive, and their application requires the participation of pilots (i.e., automatization is lower) [53].…”

Section: Some Platforms For the Plant Remote Sensingmentioning

confidence: 99%

See 3 more Smart Citations

Application of Reflectance Indices for Remote Sensing of Plants and Revealing Actions of Stressors

2021

View full text Add to dashboard Cite

Environmental conditions are very changeable; fluctuations in temperature, precipitation, illumination intensity, and other factors can decrease a plant productivity and crop. The remote sensing of plants under these conditions is the basis for the protection of plants and increases their survivability. This problem can be solved through measurements of plant reflectance and calculation of reflectance indices. Reflectance indices are related to the vegetation biomass, specific physiological processes, and biochemical compositions in plants; the indices can be used for both short-term and long-term plant monitoring. In our review, we considered the applications of reflectance indices in plant remote sensing. In Optical Methods and Platforms of Remote Sensing of Plants, we briefly discussed multi- and hyperspectral imaging, including descriptions of multispectral and hyperspectral cameras with different principles and their efficiency for the remote sensing of plants. In Main Reflectance Indices, we described the main reflectance indices, including vegetation, water, and pigment reflectance indices, as well as the photochemical reflectance index and its modifications. We focused on the relationships of leaf reflectance and reflectance indices to plant biomass, development, and physiological and biochemical characteristics. In Problems of Measurement and Analysis of Reflectance Indices, we discussed the methods of the correction of the reflectance indices that can be used for decreasing the influence of environmental conditions (mainly illumination, air, and soil) and plant characteristics (orientation of leaves, their thickness, and others) on their measurements and the analysis of the plant remote sensing. Additionally, the variability of plants was also considered as an important factor that influences the results of measurement and analysis.

show abstract

Section: Some Platforms For the Plant Remote Sensingmentioning

confidence: 99%

Section: Some Platforms For the Plant Remote Sensingmentioning

confidence: 99%

Section: Some Platforms For the Plant Remote Sensingmentioning

confidence: 99%

Section: Some Platforms For the Plant Remote Sensingmentioning

confidence: 99%

See 2 more Smart Citations

Application of Reflectance Indices for Remote Sensing of Plants and Revealing Actions of Stressors

2021

View full text Add to dashboard Cite

show abstract

“…A recently published detailed review of 126 literature sources not older than 2017 related to UAS (unmanned aerial systems) indicates the relevance of research in this field [6]. UAS is a low cost, fast and non-destructive method for remote sensing testing of crop biomass development that enables non-contact monitoring by collecting data on spectral, textural and structural characteristics of fields on very wide temporal and spatial scales, and we focus on those related to farms.…”

Section: Biomass Development Monitoringmentioning

confidence: 99%

Smart Sensor Monitoring in Energy Crop Biomass Production

Drazic¹

2021

Proceedings of the International Scientific Conference - Sinteza 2021

View full text Add to dashboard Cite

Sustainable biomass production is recognized as a key moment in the development of the European bioeconomy. In order for the production to be truly sustainable, a holistic approach is needed for research of new technologies and methods that are at the same time economically viable, environmentally friendly and socially acceptable. The approach of smart agriculture is based on the collection and processing of large databases that serve to understand crop reactions to the current environment and enable rational production planning. This paper gives a brief overview of IT used in agriculture with a focus on monitoring the biomass of energy crops in order to indicate the current level of development and potential application in the region. Biomass development monitoring is presented through the application of Data Acquisition Sensors, Biomass indexes and Data Processing And Analysis Methods. The current level of development of these technologies enables monitoring of biomass development (primarily through the vegetation index and crop height) in real time and in the selected area. The data collected in this way are used to predict and take adequate agro-technical measures at the right time, which leads to high stable yields.

show abstract

Zero‐shot obstacle detection using panoramic vision in farmland

Wang,

Chen,

Wang

et al. 2023

Journal of Field Robotics

View full text Add to dashboard Cite

Reliable obstacle detection is of great significance to the navigation technology of unmanned agricultural machinery. Currently, most of the previous works have achieved significant performance with the help of visual prior information of obstacles, where visual prior information refers to the visual features learned by models in the training stage. However, collecting enough annotated images for the training stage can be challenging. In the absence of annotated images, the current methods cannot perform optimally. To address the above problem, this paper presents a zero‐shot obstacle detection model based on the You Only Look Once X backbone, introducing the concept of zero‐shot learning into real‐time obstacle detection systems. Specifically, the cascade of encoder and decoder modules is appended to the presented model, and the integration of semantic space‐based classification and anchor‐free localization modules is used for zero‐shot obstacle detection. The feasibility of the proposed method was verified on the actual farmland test data set. The experimental results show that the F1 scores of the seen obstacle (e.g., people) and the unseen obstacle (e.g., agricultural machinery) are 96.22% and 94.66%, respectively. The average detection time for each panoramic image is 52.52 ms (equivalent to 19.04 FPS). The proposed obstacle detection method exhibits superior performance in the situation where training samples of the target category are not available. Notably, the proposed model not only performs the correct classification of unseen obstacles, but also improves the detection performance of both seen and unseen obstacles. The proposed method achieves a balance between accuracy and detection speed.

show abstract

Applications of UAS in Crop Biomass Monitoring: A Review

Cited by 36 publications

References 124 publications

Application of Reflectance Indices for Remote Sensing of Plants and Revealing Actions of Stressors

Application of Reflectance Indices for Remote Sensing of Plants and Revealing Actions of Stressors

Smart Sensor Monitoring in Energy Crop Biomass Production

Zero‐shot obstacle detection using panoramic vision in farmland

Contact Info

Product

Resources

About