Researchers at Wageningen University in the Netherlands have developed a machine-vision-based system to automatically recognize and combat weeds in the field. The result will be increased productivity, reduced costs, and less impact on the environment.

To recognize and attack wild potato plants without contaminating the entire field, an imaging system was developed to differentiate between plants in the field and spray only those to be destroyed. With the support of Dutch imaging specialist Data Vision--the sales partner of Allied Vision Technologies (Stadtroda, Germany) in the Benelux countries--researchers developed a mobile system that can be hauled by a tractor.

This giant scanner captures the ground surface and recognizes the wild potato plants, which are subsequently targeted and treated with a herbicide micro-sprayer. The entire system is mounted on a trailer that can be towed over the field.

During the first stage, the weed must be detected using two AVT Marlin F-201 digital cameras with 2-Mpixel sensors--one of the cameras is a color version, the other is an IR-sensitive monochrome version with a 780-nm IR pass filter. The cameras serve two functions: first, they localize the plants against the earth background; then, they identify the plants either as weed or agricultural crop.

Industrial companies have already shown an interest in marketing the system. However, more development is needed before the system can abate not just wild potatoes but other invasive plants as well, making it more attractive for farmers. Moreover, work is underway on another automatic weed recognition system using AVT cameras that will mechanically remove them, making it appropriate for organic farming.

You can read the full case study HERE.

Posted by Vision Systems Design