Feral swine, wild hogs, wild pigs – whatever you want to call them – are walking nightmares for farmers. Their long list of destructive behavior includes destroying food crops, native habitats, endangered species, and spreading disease.
This prolific invasive species calls at least 39 states home. A 2014 study found there were 6.3 million wild hogs in the U.S. An estimated $1.9 billion, based on $300 per animal, is spent annually for control and damage costs.
Wild hog research is tough since the greater crop damage is done out of sight and the animals are foraging mainly at night. Mississippi State University researchers used drones (UAS) in an effort to find a cost-effective, reliable technique for discovery and measurement of wild hog damage.
In 2016, the researchers chose 5 Mississippi corn fields in Bolivar, Leflore and Sunflower counties. Wild hogs were known to frequent these fields on an ongoing basis.
Drones were chosen as a method to reliably automate wild hog detection and accurately estimate specific damaged areas. The traditional research method had been for farmers to fill out questionnaires and/or share anecdotal information.
The approach used in this study provided an objective technique to quantify wild pig damage to a crop field and removed the potential bias from self-reporting by landowners and human observers. The study allowed for whole-field sampling rather than subsampling of small areas within a field.
The MSU researchers found:
- A substantial portion of damage to corn fields occurs immediately after planting when wild pigs root up recently planted corn seed. Their consumption of these seeds prior to emergence resulted in a flush of weeds in these areas that were barren of corn plants.
- Later-season damage consisted of trampled corn stalks. Both instances resulted in image textures that differed from that of healthy corn.
- Healthy crop structure exhibited a uniform texture pattern which differed from that of damaged areas. This difference in image texture is the basis for computer-automated detection of wild pig damage.
- Overall classification accuracies for hog damage were between 65% and 78%. When the classifier was incorrect, it was more likely to label damaged areas as healthy rather than labeling healthy areas as damaged.
- The methods used in the study did automate detection, but underestimated the area of wild pig damage in the studied corn fields.
Night Flight Would Help
Drone technology certainly has a future in wild hog detection. It would be especially useful in an eradication program if used at night when wild hogs are most active. Currently under FAA regulations, night flight is only permissible with a waiver, which requires a valid remote pilot certificate and use of additional lights to increase nighttime visibility.