Display options
Cite
Andújar D, Dorado J, Fernández-Quintanilla C, et al. An Approach to the Use of Depth Cameras for Weed Volume Estimation. Sensors (Basel). 2016;16(7)doi: 10.3390/s16070972.
Andújar, D., Dorado, J., Fernández-Quintanilla, C., & Ribeiro, A. (2016). An Approach to the Use of Depth Cameras for Weed Volume Estimation. Sensors (Basel, Switzerland), 16(7), . https://doi.org/10.3390/s16070972
Andújar, Dionisio, et al. "An Approach to the Use of Depth Cameras for Weed Volume Estimation." Sensors (Basel, Switzerland) vol. 16,7 (2016). doi: https://doi.org/10.3390/s16070972
Andújar D, Dorado J, Fernández-Quintanilla C, Ribeiro A. An Approach to the Use of Depth Cameras for Weed Volume Estimation. Sensors (Basel). 2016 Jun 25;16(7). doi: 10.3390/s16070972. PMID: 27347972; PMCID: PMC4970024.
Copy Download .nbib Format: NLM
Share it on

Sensors (Basel). 2016 Jun 25;16(7). doi: 10.3390/s16070972.

An Approach to the Use of Depth Cameras for Weed Volume Estimation.

Sensors (Basel, Switzerland)

Dionisio Andújar, José Dorado, César Fernández-Quintanilla, Angela Ribeiro

Affiliations

  1. Center for Automation and Robotics, Spanish National Research Council, CSIC-UPM, Arganda del Rey, Madrid 28500, Spain. [email protected].
  2. Institute of Agricultural Sciences, Spanish National Research Council, CSIC, Madrid 28006, Spain. [email protected].
  3. Institute of Agricultural Sciences, Spanish National Research Council, CSIC, Madrid 28006, Spain. [email protected].
  4. Center for Automation and Robotics, Spanish National Research Council, CSIC-UPM, Arganda del Rey, Madrid 28500, Spain. [email protected].

PMID: 27347972 PMCID: PMC4970024 DOI: 10.3390/s16070972

Abstract

The use of depth cameras in precision agriculture is increasing day by day. This type of sensor has been used for the plant structure characterization of several crops. However, the discrimination of small plants, such as weeds, is still a challenge within agricultural fields. Improvements in the new Microsoft Kinect v2 sensor can capture the details of plants. The use of a dual methodology using height selection and RGB (Red, Green, Blue) segmentation can separate crops, weeds, and soil. This paper explores the possibilities of this sensor by using Kinect Fusion algorithms to reconstruct 3D point clouds of weed-infested maize crops under real field conditions. The processed models showed good consistency among the 3D depth images and soil measurements obtained from the actual structural parameters. Maize plants were identified in the samples by height selection of the connected faces and showed a correlation of 0.77 with maize biomass. The lower height of the weeds made RGB recognition necessary to separate them from the soil microrelief of the samples, achieving a good correlation of 0.83 with weed biomass. In addition, weed density showed good correlation with volumetric measurements. The canonical discriminant analysis showed promising results for classification into monocots and dictos. These results suggest that estimating volume using the Kinect methodology can be a highly accurate method for crop status determination and weed detection. It offers several possibilities for the automation of agricultural processes by the construction of a new system integrating these sensors and the development of algorithms to properly process the information provided by them.

Keywords: Kinect v2; maize; plant volume estimation; weed detection; weed/crop structure characterization

References

  1. Sensors (Basel). 2015 Jun 04;15(6):12999-3011 - PubMed
  2. Sensors (Basel). 2011;11(3):2304-18 - PubMed
  3. Trends Plant Sci. 2013 Aug;18(8):428-39 - PubMed
  4. Sensors (Basel). 2014 Feb 14;14(2):3001-18 - PubMed
  5. Sensors (Basel). 2013 Feb 27;13(3):2830-47 - PubMed
  6. Sensors (Basel). 2013 Nov 27;13(12):16216-33 - PubMed
  7. Sensors (Basel). 2013 Oct 29;13(11):14662-75 - PubMed
  8. Sensors (Basel). 2014 Oct 24;14(11):20078-111 - PubMed
  9. Sensors (Basel). 2013 Feb 11;13(2):2384-98 - PubMed

Publication Types