Taking the drudgery out of weed control

For automated, mechanical weed control to work, scientists must teach machines how to distinguish between unwanted vegetation and the crop being cultivated. A new, high-tech system using x-rays to detect tomato stems is under development by UC Davis Cooperative Extension agricultural engineer David Slaughter and USDA Agricultural Research Service researcher Ron Haff. The output from the x-ray detector is input to a microcontroller that controls a pair of pneumatically powered mechanical weed knife blades.

Slaughter and Haff's work was explained this week in an online newsletter produced by Vision Systems Design, an organization that provides automation solutions for engineers and integrators worldwide.

The mechanical weeding machine includes an x-ray mounted to the side of a shielded tunnel that is pulled behind a tractor over the row of tomato plants. As the x-rays radiate across the tunnel, they are detected by an array of 32 photodiodes whose output is tied to a single point at the input of a summing amplifier, the story says.

The system was used in field trials on a 15-meter row containing 39 standing tomato seedlings. At a speed of about 1 mile per hour, the detection system identified all 39 stems of standing plants with no false positives.

Tomato field infested with field bindweed.

Read more