Tracking individual honeybees among wildflower clusters with computer vision-facilitated pollinator monitoring

Abstract

Monitoring animals in their natural habitat is essential for advancement of animal behavioural studies, especially in pollination studies. Non-invasive techniques are preferred for these purposes as they reduce opportunities for research apparatus to interfere with behaviour. One potentially valuable approach is image-based tracking. However, the complexity of tracking unmarked wild animals using video is challenging in uncontrolled outdoor environments. Out-of-the-box algorithms currently present several problems in this context that can compromise accuracy, especially in cases of occlusion in a 3D environment. To address the issue, we present a novel hybrid detection and tracking algorithm to monitor unmarked insects outdoors. Our software can detect an insect, identify when a tracked insect becomes occluded from view and when it re-emerges, determine when an insect exits the camera field of view, and our software assembles a series of insect locations into a coherent trajectory. The insect detecting component of the software uses background subtraction and deep learning-based detection together to accurately and efficiently locate the insect among a cluster of wildflowers.We applied our method to track honeybees foraging outdoors using a new dataset that includes complex background detail, wind-blown foliage, and insects moving into and out of occlusion beneath leaves and among three-dimensional plant structures. We evaluated our software against human observations and previous techniques. It tracked honeybees at a rate of 86.6% on our dataset, 43% higher than the computationally more expensive, standalone deep learning model YOLOv2. We illustrate the value of our approach to quantify fine-scale foraging of honeybees. The ability to track unmarked insect pollinators in this way will help researchers better understand pollination ecology. The increased efficiency of our hybrid approach paves the way for the application of deep learning-based techniques to animal tracking in real-time using low-powered devices suitable for continuous monitoring.

Habitat fragmentation and food security in crop pollination systems

“…tracking of ‘marked’ pollinator individuals with remote devices; e.g. Ratnakaye et al, 2021). Finally, experimental studies provide information to calibrate biodiversity estimates in fragmented landscapes (SFAR function; Appendix ), as well as the effect of pollinator diversity on animal‐dependent crop production (Liang et al, 2016; O'Connor et al, 2017).…”

Towards precision apiculture: Traditional and technological insect monitoring methods in strawberry and raspberry crop polytunnels tell different pollination stories

“…Movement tracks of honeybees were extracted from recorded videos ( Fig 3 ) using automated tracking software [ 38 ]. This software uses a Hybrid Detection and Tracking (HyDaT) algorithm, comprising of foreground-background segmentation and deep learning-based detection techniques to identify and track honeybees in complex dynamic environments.…”

“…Validation study. A study was conducted to validate foraging data collected with the automated software [38] on honeybees. For this, foraging time data (time spent on flowers) for 10 randomly selected honeybee tracks were compared against human observations of the video footage and percentage errors were recorded.…”

The role of food odor in invertebrate foraging

“…[135][136][137] While it is much easier to analyze laboratory data with simple backgrounds, good lighting and often multiple cameras that allow tracking even when parts of the animal are obstructed, these methods can also perform well on field data. 138,139 Recent work using deep learning with frame-to-frame predictive priors has made camera-based tracking more successful, in certain cases even following animals while completely obstructed to a human observer. 140 Video tracking and deep learning-based analyses have thus revolutionized the field of animal tracking.…”