- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
In-field high throughput grapevine phenotyping with a consumer-grade depth camera
摘要： Plant phenotyping, that is, the quantitative assessment of plant traits including growth, morphology, physiology, and yield, is a critical aspect towards efficient and effective crop management. Currently, plant phenotyping is a manually intensive and time consuming process, which involves human operators making measurements in the field, based on visual estimates or using hand-held devices. In this work, methods for automated grapevine phenotyping are developed, aiming to canopy volume estimation and bunch detection and counting. It is demonstrated that both measurements can be effectively performed in the field using a consumer-grade depth camera mounted on-board an agricultural vehicle. First, a dense 3D map of the grapevine row, augmented with its color appearance, is generated, based on infrared stereo reconstruction. Then, different computational geometry methods are applied and evaluated for plant per plant volume estimation. The proposed methods are validated through field tests performed in a commercial vineyard in Switzerland. It is shown that different automatic methods lead to different canopy volume estimates meaning that new standard methods and procedures need to be defined and established. Four deep learning frameworks, namely the AlexNet, the VGG16, the VGG19 and the GoogLeNet, are also implemented and compared to segment visual images acquired by the RGB-D sensor into multiple classes and recognize grape bunches. Field tests are presented showing that, despite the poor quality of the input images, the proposed methods are able to correctly detect fruits, with a maximum accuracy of 91.52%, obtained by the VGG19 deep neural network.
关键词： Grapevine canopy volume estimation,RGB-D sensing,Agricultural robotics,In-field phenotyping,Deep learning-based grape bunch detection
更新于2025-09-10 09:29:36
-
Leaf Area Estimation of Reconstructed Maize Plants Using a Time-of-Flight Camera Based on Different Scan Directions
摘要： The leaf area is an important plant parameter for plant status and crop yield. In this paper, a low-cost time-of-flight camera, the Kinect v2, was mounted on a robotic platform to acquire 3-D data of maize plants in a greenhouse. The robotic platform drove through the maize rows and acquired 3-D images that were later registered and stitched. Three different maize row reconstruction approaches were compared: reconstruct a crop row by merging point clouds generated from both sides of the row in both directions, merging point clouds scanned just from one side, and merging point clouds scanned from opposite directions of the row. The resulted point cloud was subsampled and rasterized, the normals were computed and re-oriented with a Fast Marching algorithm. The Poisson surface reconstruction was applied to the point cloud, and new vertices and faces generated by the algorithm were removed. The results showed that the approach of aligning and merging four point clouds per row and two point clouds scanned from the same side generated very similar average mean absolute percentage error of 8.8% and 7.8%, respectively. The worst error resulted from the two point clouds scanned from both sides in opposite directions with 32.3%.
关键词： crop characterization,precision farming,3-D sensors,agricultural robotics,plant phenotyping
更新于2025-09-09 09:28:46
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Implementation of UAV-Based Lidar for High Throughput Phenotyping
摘要： High throughput phenotyping is rapidly gaining widespread popularity due to its ability to non-destructively extract plant traits, such as plant height, canopy density, leaf and plant structure, and so on. In this study, we focus on developing a UAV-based LiDAR system to acquire accurate time-series 3D point clouds for monitoring two specific plant traits – plant height and canopy cover – which are integral for enhancing crop genetic improvement to meet the needs of future generations. Furthermore, the obtained estimates are validated by comparing the results with those obtained from wheel-based LiDAR data.
关键词： High throughput phenotyping,UAV,plant height,canopy cover,LiDAR system
更新于2025-09-09 09:28:46
-
On-the-go hyperspectral imaging for the in-field estimation of grape berry soluble solids and anthocyanin concentration
摘要： Background and Aims: Hyperspectral imaging (HSI) is used to assess fruit composition mostly indoor under controlled conditions. This work evaluates a HSI technique to measure TSS and anthocyanin concentration in wine grapes non-destructively, in real time and in the vineyard. Methods and Results: Hyperspectral images were acquired under natural illumination with a VIS–NIR hyperspectral camera (400–1000 nm) mounted on an all-terrain vehicle moving at 5 km/h in a commercial Tempranillo vineyard in La Rioja, Spain. Measurements were taken on four dates during grape ripening in 2017. Grape composition was analysed on the grapes imaged, which was then used to develop spectral models, trained with support vector machines, to predict TSS and anthocyanin concentration. Regression models of TSS had determination coefficients (R2) of 0.91 for a fivefold cross validation [root mean squared error (RMSE) of 1.358°Brix] and 0.92 for the prediction of external samples (RMSE of 1.274°Brix). For anthocyanin concentration, R2 of 0.72 for cross validation (RMSE of 0.282 mg/g berry) and 0.83 for prediction (RMSE of 0.211 mg/g berry) was achieved. Spatial–temporal variation maps were developed for the four image acquisition dates during ripening. Conclusions: These results suggest that potential for on-the-go HSI to automate the assessment of important grape compositional parameters in vineyard is promising. Significance of the Study: The on-the-go HSI method described in this study could be automated and provide valuable information to improve winery and vineyard decisions and vineyard management.
关键词： sensors,plant phenotyping,support vector machines,proximal sensing regression
更新于2025-09-09 09:28:46