Department of Electrical and Computer Engineering – Aarhus University
In collaboration with North Carolina State University, Texas A&M and United States Department of Agriculture, our recent work on realtime weeds recognition and quantification was well received in the OpenCV Spatial AI Competition. You can read the details of our work here.
Our latest work in the Smartgrass project was recently published in the Sensors special issue Sensing Technologies for Agricultural Automation and Robotics. With an optimized model and extensive high quality images, new state of the art prediction results in grass clover mixtures was presented. Using a specially developed ATV-mounted camera, the method was applied on 29.848 in-field images to sparsely map 225 hectare for the local legume content.
We recently presented our preliminary results in large-scale mapping of grass-clover leys at “Græsland 2018”, the largest grass-clover event in northern Europe, hosted by DLF.
Using an ATV, numerous georeferenced images were collected a couple of days before the first harvest of the 2018 season. Using an automated segmentation of each image into grass (blue), clover (red), and soil (green), the spatial distribution of the three is qualitatively visualized across the field. The three sample images exemplify the corresponding distribution at the three points in space.
In the future, by mounting the camera directly on front of the harvester, the farmer can monitor his entire fields when harvesting, without the need for driving an ATV. This allows the farmer to optimize his fertilization strategy based on the condition and spatial clover/grass distributions of his fields.
For more information, contact Søren Skovsen.
Our previous work in pixel-wise classification of high-resolution RGB images of grass-clover leys into clover, grass, and weeds demonstrated state of the art accuracy.
Extending this work into a two-step classification scheme with corresponding hierarchical labels, we have demonstrated an extended segmentation of clovers into the present species in the dataset: red clover (Trifolium pratense) and white clover (Trifolium repens).
The quantitative results of the segmentations on the hand-annotated test set are stated in the paper from the ICPA proceedings.
Qualitative results of the hierarchical segmentation on two images are shown below.
For more information, contact Søren Skovsen.