Automatic detection of bumblebees using video analysis

Azarcoya-Cabiedes, Willy; Vera, Pablo; Torres-Ruíz, Alfonso; Salas, Joaquín

doi:10.15446/dyna.v81n187.40475

Cited by 6 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…; Azarcoya‐Cabiedes et al . ; Weinstein ). Many digital video recorders (DVR) now have in‐built video motion detection (VMD) sensors (Mueller et al .…”

Section: Introductionmentioning

confidence: 99%

“…Data collection has involved identifying species and their behaviour, such as the number of flowers visited, pollinator search patterns and the duration of visits (Heinrich 1979;Jones, Reithel & Irwin 1998;Ohashi & Yahara 1998;Dauber et al 2010), variables that have generally been linked to plant reproductive success (Zimmerman 1983; continuous video recordings have mostly been used, which require considerable effort in reviewing the material. Continuous video can be processed using computer programs that incorporate an automated video processing (VP) facility featuring functions such as detection of moving objects (Storbeck & Daan 2001;Spampinato et al 2008;Azarcoya-Cabiedes et al 2014;Weinstein 2015). Many digital video recorders (DVR) now have in-built video motion detection (VMD) sensors (Mueller et al 2006).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Diel activity, frequency and visit duration of pollinators in focal plants: in situ automatic camera monitoring and data processing

Steen

2016

Methods Ecol Evol

View full text Add to dashboard Cite

Summary Data collection on interactions between organisms and their environment has traditionally been conducted by on‐site human observations, a time‐consuming enterprise that could explain the shortage of around‐the‐clock observations of free‐ranging wild animals. In this paper, I outline a time‐efficient procedure to collect data on flower‐visiting animals. The objectives were, first, to model diel activity rhythms by using cosine‐based mixed‐effects regression models (cosinor method) on data from an established automatic video monitoring system and, secondly, to test the use of a cheap off‐the‐shelf digital camera modified for automated monitoring of flower visitors. Two different model systems were studied: foraging bumblebees visiting focal white clovers, monitored around‐the‐clock (193 h) to model diel activity; and honeybees visiting thistles, monitored over a shorter period (5 h) to test the applicability and reliability of a new method for monitoring pollinators. The data were automatically entered and processed using R‐scripts after manual filtering of the images, obviating the need for manual data entry prior to analysis. For diel activity in bumblebees, the model that gave the best fit included the 24‐h fundamental period and one harmonic, a 12‐h period to modulate the signal, together with temperature. The bumblebees were exclusive diurnal, with activity starting about 5 h after sunrise, peaking sharply in the afternoon and ending about 1 h before sunset. In addition to time of day, activity also increased with temperature. The off‐the‐shelf digital camera, Canon PowerShot®, with motion detection script, was triggered by every flower‐visiting honeybee. In addition to recorded visitor frequency and visitor duration, it enabled high‐resolution images, which could be important for species identification. Automatic camera recording is advantageous for close‐up monitoring, compared with continuous video recording, because the latter demands more time and effort in reviewing the material. It could be used to study a range of different species such as pollinators, on‐plant behaviour of herbivorous animals, cavity dwellers or cavity breeders. Moreover, the procedures for automatic data entry, data processing and statistical analysis for modelling diel activity rhythms could have great relevance for researchers using other types of camera monitoring systems operating 24 h per day.

show abstract

“…; Azarcoya‐Cabiedes et al . ; Weinstein ). Many digital video recorders (DVR) now have in‐built video motion detection (VMD) sensors (Mueller et al .…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Diel activity, frequency and visit duration of pollinators in focal plants: in situ automatic camera monitoring and data processing

Steen

2016

Methods Ecol Evol

View full text Add to dashboard Cite

show abstract

“…The choice of post‐processing the data, rather than in situ motion detection, allows for decreasing power consumption and processor temperature and for fine‐tuning the motion detection threshold of the algorithms based on the rate of omission. Motion detection techniques applied as a post‐process to filter video recordings have been proven effective in detecting pollinator activity (Azarcoya‐Cabiedes et al., 2014; Weinstein, 2015). In our study, motion detection post‐processing was found useful in the case of rare and brief visits but not when visits are frequent.…”

Section: Video Analysismentioning

confidence: 99%

PICT: A low‐cost, modular, open‐source camera trap system to study plant–insect interactions

et al. 2021

View full text Add to dashboard Cite

1. Commercial camera traps (CTs) commonly used in wildlife studies have several technical limitations that restrict their scope of application. They are not easily customizable, unit prices sharply increase with image quality and importantly, they are not designed to record the activity of ectotherms such as insects. Those developed for the study of plant-insect interactions are yet to be widely adopted as they rely on expensive and heavy equipment.2. We developed PICT (plant-insect interactions camera trap), an inexpensive (<100 USD) do-it-yourself CT system based on a Raspberry Pi Zero computer designed to continuously film animal activity. The system is particularly well suited for the study of pollination, insect behaviour and predator-prey interactions. The focus distance can be manually adjusted to under 5 cm. In low light conditions, a near-infrared light automatically illuminates the subject. Frame rate, resolution and video compression levels can be set by the user. The system can be remotely controlled using either a smartphone, tablet or laptop via the onboard Wi-Fi. PICT can record up to 72-hr day and night videos at >720p resolution with a 110-Wh power bank (30,000 mAh).Its ultra-portable (<1 kg) waterproof design and modular architecture is practical in diverse field settings. We provide an illustrated technical guide detailing the steps involved in building and operating a PICT and for video post-processing.3. We successfully field-tested PICT in a Central African rainforest in two contrasting research settings: an insect pollinator survey in the canopy of the African ebony Diospyros crassiflora and the observation of rare pollination events of an epiphytic orchid Cyrtorchis letouzeyi.4. PICT overcomes many of the limitations commonly associated with CT systems designed to monitor ectotherms. Increased portability and image quality at lower costs This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…By tracking individual movement and social interactions, object-tracking techniques have provided useful methodologies to study the dynamic structure of social networks in diverse social groups. In social insect colonies, the technique has been applied to European honeybees (Apis mellifera) [15], bumblebees (Bombus ignitus) [16], carpenter ants (Camponotus fellah) [17] and others. These tracking methodologies do not, by themselves, provide a reliable assessment of individual behavioural state during social interactions, nor do they assess the reliability of information exchange during encounters between individuals.…”

Section: Introductionmentioning

confidence: 99%

Decoding alarm signal propagation of seed-harvester ants using automated movement tracking and supervised machine learning

et al. 2022

View full text Add to dashboard Cite

Alarm signal propagation through ant colonies provides an empirically tractable context for analysing information flow through a natural system, with useful insights for network dynamics in other social animals. Here, we develop a methodological approach to track alarm spread within a group of harvester ants, Pogonomyrmex californicus . We initially alarmed three ants and tracked subsequent signal transmission through the colony. Because there was no actual standing threat, the false alarm allowed us to assess amplification and adaptive damping of the collective alarm response. We trained a random forest regression model to quantify alarm behaviour of individual workers from multiple movement features. Our approach translates subjective categorical alarm scores into a reliable, continuous variable. We combined these assessments with automatically tracked proximity data to construct an alarm propagation network. This method enables analyses of spatio-temporal patterns in alarm signal propagation in a group of ants and provides an opportunity to integrate individual and collective alarm response. Using this system, alarm propagation can be manipulated and assessed to ask and answer a wide range of questions related to information and misinformation flow in social networks.

show abstract

Automatic detection of bumblebees using video analysis

Cited by 6 publications

References 10 publications

Diel activity, frequency and visit duration of pollinators in focal plants: in situ automatic camera monitoring and data processing

Diel activity, frequency and visit duration of pollinators in focal plants: in situ automatic camera monitoring and data processing

PICT: A low‐cost, modular, open‐source camera trap system to study plant–insect interactions

Decoding alarm signal propagation of seed-harvester ants using automated movement tracking and supervised machine learning

Contact Info

Product

Resources

About