Journal: Frontiers in bioinformatics

Article Title: A Brave New World: Virtual Reality and Augmented Reality in Systems Biology

doi: 10.3389/fbinf.2022.873478

Figure Lengend Snippet: Input tracking and output display technologies in consumer-level VR/AR systems.

Article Snippet: e.g., Microsoft Azure Kinect DK (Redmond, WA), Sony PlayStation Camera (San Mateo, CA), OptiTrack (Corvallis, OR), Intel RealSense Depth Cameras (Santa Clara, CA), OpenCV OAK (Palo Alto, CA), HTC Vive Tracker (Taiwan).

Techniques: Transmission Assay, Software

Journal: Plant Phenomics

Article Title: Generating 3D Multispectral Point Clouds of Plants with Fusion of Snapshot Spectral and RGB-D Images

doi: 10.34133/plantphenomics.0040

Figure Lengend Snippet: Principle and flow chart of plant multispectral reflectance correction. (A) The flow chart of generating plant multispectral point cloud. Raw images such as depth image and multispectral image were registered, and multispectral image was reshaped as a multichannel image at the beginning of the procedure. Then, follow the point cloud generation that relies on the transformation from depth image coordinate system to the world coordinate system under the constrains of the camera intrinsic parameters. Finally, with the fusion of multiview point clouds and the mapping of corrected multispectral textures, the 3D multispectral point cloud model was constructed. (B) The flow chart of calculating the spatial distribution of the DN values of the references and correcting the plant spectral reflectance using ANN. In the stage of model training, the 3D light field features of references were extracted from depth image as independent variables and the spectral DN values as dependent variables. In the stage of model application, the 3D light field features of plant were set as input to obtain the predictions of the corresponding DN values of the reference. Finally, the reflectance image is corrected pixel by pixel based on this method to generate a mappable texture.

Article Snippet: The RGB-D sensor (Azure Kinect DK, Microsoft, Redmond, WA, USA) and the multispectral camera (MQ022MG-CM, XIMEA, Munster, Germany) were fixed together using a self-designed adapter and then mounted on a tripod.

Techniques: Transformation Assay, Construct

Journal: Plant Phenomics

Article Title: Generating 3D Multispectral Point Clouds of Plants with Fusion of Snapshot Spectral and RGB-D Images

doi: 10.34133/plantphenomics.0040

Figure Lengend Snippet: Visualization of multispectral images and point clouds of plants (wavelength of 740.7 nm). Original multispectral images, corrected multispectral images, and multispectral point clouds from 3 different viewpoints are presented in this figure. Spectral textures are displayed in pseudo-color to facilitate comparison. From the difference of the pseudo-color images before and after reflectance correction, the illumination effects were greatly reduced.

Article Snippet: The RGB-D sensor (Azure Kinect DK, Microsoft, Redmond, WA, USA) and the multispectral camera (MQ022MG-CM, XIMEA, Munster, Germany) were fixed together using a self-designed adapter and then mounted on a tripod.

Techniques: Comparison

Journal: Plant Phenomics

Article Title: Generating 3D Multispectral Point Clouds of Plants with Fusion of Snapshot Spectral and RGB-D Images

doi: 10.34133/plantphenomics.0040

Figure Lengend Snippet: Comparison of multispectral reflectance curves before and after reflectance correction. To facilitate obtaining the reflectance of the hemisphere reference, a flat plate of the same material was selected, and its reflectance was measured using the snapshot multispectral camera and ASD spectrometer. The results are displayed in the first row. Four measured leaf positions were selected as examples to be presented, labeled a, b, c, and d in turn.

Article Snippet: The RGB-D sensor (Azure Kinect DK, Microsoft, Redmond, WA, USA) and the multispectral camera (MQ022MG-CM, XIMEA, Munster, Germany) were fixed together using a self-designed adapter and then mounted on a tripod.

Techniques: Comparison, Labeling

Journal: Plant Phenomics

Article Title: Generating 3D Multispectral Point Clouds of Plants with Fusion of Snapshot Spectral and RGB-D Images

doi: 10.34133/plantphenomics.0040

Figure Lengend Snippet: Comparison of RMSE and distance range of multispectral reflectance curves before and after reflectance correction at all measured leaf positions.

Article Snippet: The RGB-D sensor (Azure Kinect DK, Microsoft, Redmond, WA, USA) and the multispectral camera (MQ022MG-CM, XIMEA, Munster, Germany) were fixed together using a self-designed adapter and then mounted on a tripod.

Techniques: Comparison

Journal: Plant Phenomics

Article Title: Generating 3D Multispectral Point Clouds of Plants with Fusion of Snapshot Spectral and RGB-D Images

doi: 10.34133/plantphenomics.0040

Figure Lengend Snippet: Comparison of average RMSE and distance range of multispectral reflectance curves among using model-based method such as ANN and search-based method with various distance metrics after reflectance correction at the measured positions of all leaves. Euclidean, weighted Euclidean, Cosine, Mahalanobis, Chebychev, Cosine after principal components analysis (PCA), and weighted Mahalanobis are included in the selected metrics. The suffix v1 and v2 stand for both descending and ascending weighting, respectively.

Article Snippet: The RGB-D sensor (Azure Kinect DK, Microsoft, Redmond, WA, USA) and the multispectral camera (MQ022MG-CM, XIMEA, Munster, Germany) were fixed together using a self-designed adapter and then mounted on a tripod.

Techniques: Comparison

Journal: Plant Phenomics

Article Title: Generating 3D Multispectral Point Clouds of Plants with Fusion of Snapshot Spectral and RGB-D Images

doi: 10.34133/plantphenomics.0040

Figure Lengend Snippet: Visualization of the 3D multispectral point clouds of perilla and tomato plants (wavelength of 740.7 nm) before and after correction for different periods. The left side of each subplot shows the 3D multispectral point cloud before correction, and the right side shows the 3D multispectral point cloud after correction.

Article Snippet: The RGB-D sensor (Azure Kinect DK, Microsoft, Redmond, WA, USA) and the multispectral camera (MQ022MG-CM, XIMEA, Munster, Germany) were fixed together using a self-designed adapter and then mounted on a tripod.

Techniques:

Journal: Plant Phenomics

Article Title: Generating 3D Multispectral Point Clouds of Plants with Fusion of Snapshot Spectral and RGB-D Images

doi: 10.34133/plantphenomics.0040

Figure Lengend Snippet: Comparison of RMSE and distance range of multispectral reflectance curves before correction (BC) and after correction (AC) at all measured leaf positions of perilla and tomato plants at different periods.

Article Snippet: The RGB-D sensor (Azure Kinect DK, Microsoft, Redmond, WA, USA) and the multispectral camera (MQ022MG-CM, XIMEA, Munster, Germany) were fixed together using a self-designed adapter and then mounted on a tripod.

Techniques: Comparison