Non - destructive Automatic Leaf Area Measurements by Combining Stereo and 1 Time - of - Flight

Leaf area measurements are commonly obtained by destructive and laborious practice. This paper 5 shows how stereo and Time-of-Flight (ToF) images can be combined for non-destructive automatic leaf area 6 measurements. We focus on some challenging plant images captured in a greenhouse environment, and show that 7 even the state-of-the-art stereo methods produce unsatisfactory results. By transforming depth information in a 8 ToF image to a localised search range for dense stereo, a global optimisation strategy is adopted for producing 9 smooth results that preserve discontinuity. We also use edges of colour and disparity images for automatic leaf 10 detection and develop a smoothing method necessary for accurately estimating surface area. In addition to 11 show that combining stereo and ToF images gives superior qualitative and quantitative results, 149 automatic 12 measurements on leaf area using our system in a validation trial have a correlation of 0.97 with true values 13 and the root-mean-square error is 10.97 cm, which is 9.3% of the average leaf area.. Our approach could 14 potentially be applied for combining other modalities of images with large difference in image resolutions and 15 camera positions. 16