The complex interaction between a genotype and its environment determines the observable phenotypic characteristics of a plant that ultimately influences yield and resource acquisition. Image-based plant phenotyping is to the proximal sensing and quantification of plant traits based on analyzing their images captured at regular intervals with precision. It facilitates the analysis of a large number of plants in a relatively short period of time with no or little manual intervention to compute diverse phenotypes. The process is generally non-destructive, allowing the same traits to be quantified repeatedly at multiple times during a plant’s life cycle. Plants are living organisms that constantly change in shape and appearance with increased architectural complexity with time. In addition, self-occlusions, illumination variations, view variations, differences in resolutions among different imaging modalities are critical bottlenecks to extracting meaningful phenotypes based on image analysis in the effort to link intricate plant phenotypes to genetic expression for global food security. Image-based plant phenotyping analysis is an interdisciplinary research field that combines computer vision, plant science, data science, and genomics. Although recent research has introduced phenotypic taxonomy to compute 2D and 3D phenotypes based on image analysis, these have not been exhaustive and further exploration is required.
This Research Topic will bring together research on the latest advances in computer vision and artificial intelligence techniques to identify and compute new phenotypes in plant science. Different phenotypes (e.g., morphological characteristics, physiological processes, and timing of important events) are manifested at different wavelengths of electromagnetic spectra at different timestamps of a plant’s life cycle. Hence, images for phenomic study are usually captured using cameras in multiple modalities at regular time intervals from multiple view angles. While advanced computer vision algorithms need to be explored for processing multimodal, multi-view, and time-series imagery, artificial intelligence techniques are indispensable for data modeling and analytics. 3D plant model reconstruction plays a crucial role in addressing challenges due to occlusions and phyllotaxy to achieve better phenotypic accuracy.
We welcome contributions on themes that include, but are not limited to, the following:
- 3D plant model reconstruction to compute 3D phenotypes;
- Advances in 2D and 3D phenotypic taxonomy and the computer vision algorithms to compute them;
- Multimodal and multi-view plant phenotyping analysis;
- Timing detection of important events in a plant’s life cycle based on computer vision and artificial intelligence techniques;
- Time-series modeling for phenotypic prediction and phenotype-genotype mapping.
The complex interaction between a genotype and its environment determines the observable phenotypic characteristics of a plant that ultimately influences yield and resource acquisition. Image-based plant phenotyping is to the proximal sensing and quantification of plant traits based on analyzing their images captured at regular intervals with precision. It facilitates the analysis of a large number of plants in a relatively short period of time with no or little manual intervention to compute diverse phenotypes. The process is generally non-destructive, allowing the same traits to be quantified repeatedly at multiple times during a plant’s life cycle. Plants are living organisms that constantly change in shape and appearance with increased architectural complexity with time. In addition, self-occlusions, illumination variations, view variations, differences in resolutions among different imaging modalities are critical bottlenecks to extracting meaningful phenotypes based on image analysis in the effort to link intricate plant phenotypes to genetic expression for global food security. Image-based plant phenotyping analysis is an interdisciplinary research field that combines computer vision, plant science, data science, and genomics. Although recent research has introduced phenotypic taxonomy to compute 2D and 3D phenotypes based on image analysis, these have not been exhaustive and further exploration is required.
This Research Topic will bring together research on the latest advances in computer vision and artificial intelligence techniques to identify and compute new phenotypes in plant science. Different phenotypes (e.g., morphological characteristics, physiological processes, and timing of important events) are manifested at different wavelengths of electromagnetic spectra at different timestamps of a plant’s life cycle. Hence, images for phenomic study are usually captured using cameras in multiple modalities at regular time intervals from multiple view angles. While advanced computer vision algorithms need to be explored for processing multimodal, multi-view, and time-series imagery, artificial intelligence techniques are indispensable for data modeling and analytics. 3D plant model reconstruction plays a crucial role in addressing challenges due to occlusions and phyllotaxy to achieve better phenotypic accuracy.
We welcome contributions on themes that include, but are not limited to, the following:
- 3D plant model reconstruction to compute 3D phenotypes;
- Advances in 2D and 3D phenotypic taxonomy and the computer vision algorithms to compute them;
- Multimodal and multi-view plant phenotyping analysis;
- Timing detection of important events in a plant’s life cycle based on computer vision and artificial intelligence techniques;
- Time-series modeling for phenotypic prediction and phenotype-genotype mapping.
