Abstract
A vision-based weed control robot for agricultural field application requires robust vegetation segmentation. The output of vegetation segmentation is the fundamental element in the subsequent process of weed and crop discrimination as well as weed control. There are two challenging issues for robust vegetation segmentation under agricultural field conditions: (1) to overcome strongly varying natural illumination; (2) to avoid the influence of shadows under direct sunlight conditions. A way to resolve the issue of varying natural illumination is to use high dynamic range (HDR) camera technology. HDR cameras, however, do not resolve the shadow issue. In many cases, shadows tend to be classified during the segmentation as part of the foreground, i.e., vegetation regions. This study proposes an algorithm for ground shadow detection and removal, which is based on color space conversion and a multilevel threshold, and assesses the advantage of using this algorithm in vegetation segmentation under natural illumination conditions in an agricultural field. Applying shadow removal improved the performance of vegetation segmentation with an average improvement of 20, 4.4, and 13.5% in precision, specificity and modified accuracy, respectively. The average processing time for vegetation segmentation with shadow removal was 0.46 s, which is acceptable for real-time application (<1 s required). The proposed ground shadow detection and removal method enhances the performance of vegetation segmentation under natural illumination conditions in the field and is feasible for real-time field applications.
Highlights
This work was part of the EU-funded project SmartBot, a project with the research goal to develop a small-sized vision-based robot for control of volunteer potato in a sugar beet field
This study proposes an algorithm for ground shadow detection and removal, which is based on color space conversion and a multilevel threshold, and assesses the advantage of using this algorithm in vegetation segmentation under natural illumination conditions in an agricultural field
Applying shadow removal improved the performance of vegetation segmentation with an average improvement of 20, 4.4, and 13.5% in precision, specificity and modified accuracy, respectively
Summary
This work was part of the EU-funded project SmartBot, a project with the research goal to develop a small-sized vision-based robot for control of volunteer potato (weed) in a sugar beet field. Shadows often create extreme illumination contrast, causing substantial luminance differences within a single image scene These extreme intensity differences make vegetation segmentation a very challenging task. An alternative way to measure the performance would be balanced accuracy, i.e. the average of sensitivity and specificity This measure can provide a biased value if segmentation output has a large number of false-positives in case an image contains only a small amount of vegetation. The modified accuracy (MA) was defined in this study This performance indicator uses a harmonic mean of relative vegetation area error (RVAE) and balanced accuracy (BA). Both measures have values between 0 and 1, where 0 represents very poor segmentation, and 1 represents perfect segmentation. The equations are described below: Balanced accuracy (BA) 1⁄4 Recall þ Specificity ð15Þ
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
