An unsupervised automatic measurement of wheat spike dimensions in dense 3D point clouds for field application

An accurate measurement of field-grown wheat traits, including spike number, dimension and volume are essential for crop phenotyping yield analysis. A high-throughput method to image in three dimensions is presented with an accompanying unsupervised measuring obtain individual data. Images captured using four structured light scanners on a field mobile platform, creating dimensionally sub-millimetre resolution 3D point clouds 4.5 m 3 less than 10 s. The analyses each trial plot's cloud, containing hundreds spikes, calculating the average size total per plot. analysis utilises adaptive k -means algorithm dynamic perspectives, fit spike's shape measures random sample consensus algorithm. generates small cuboids all spikes estimate volume. Experimental results show that proposed reliable tool identifying from crops spikes. Compared manual measurement, according five scenes, error rate number spikes' height width tests were 16.27%, 5.24% 12.38% respectively. • Laser imaging technology automatic application. High-throughput capture platform was constructed. Unsupervised allows clouds. Automatic can size, Framework evaluated by comparing experiment measurement.