Detecting Bees in Cherry Flowers Using Timelapse Images and Foundational Models

Bees perform important pollination services in fruit crops such as sweet cherry (Prunus avium). Growers will often introduce managed bees to supplement natural pollinators. Monitoring pollinating insects is important to understand the impact augmenting pollinators has on fruit yield, particularly in relation to June drop which is a major cause of yield instability in the cherry industry. Timelapse cameras allow for continuous monitoring of flowers, but manual analysis of the generated footage is very time consuming. Timelapse imaging combined with automated image processing methods, is a valuable tool in studying the role bee pollination plays in fruit production. We have developed a novel method for detecting bees in time lapse images, called BeeSAM2. This exploits both the zero-shot detector Grounding DINO and the foundational model Segment Anything 2. Promising results are achieved with the method being capable of detecting the bumblebee Bombus terrestris in images with a recall of 0.959 and precision of 0.991. These results are sufficiently accurate to deploy our method to quantify bee activity in cherry plantations, advancing the ability of researchers to monitor flower-pollinator interaction, and saving a significant amount of time during video processing.