Spatial Monitoring and Insect Behavioural Analysis Using Computer Vision for Precision Pollination

Ratnayake, Malika Nisal; Amarathunga, Don Chathurika; Zaman, Asaduz; Dyer, Adrian G.; Dorin, Alan

doi:10.1007/s11263-022-01715-4

Cited by 18 publications

(7 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More sophisticated tracking methods are available in other systems, e.g. a video-based processing pipeline that is able to detect, track and classify insects in heterogeneous environments of natural vegetation and enables the automated analysis of pollination events [48].…”

Section: Insect Detection and Trackingmentioning

confidence: 99%

Insect Detect: An open-source DIY camera trap for automated insect monitoring

Sittinger,

Uhler,

Pink

et al. 2023

Preprint

View full text Add to dashboard Cite

Insect monitoring is essential to design effective conservation strategies, which are indispensable to mitigate worldwide declines and biodiversity loss. For this purpose, traditional monitoring methods are widely established and can provide data with a high taxonomic resolution. However, processing of captured insect samples is often time-consuming and expensive, which limits the number of potential replicates. Automated monitoring methods can facilitate data collection at a higher spatiotemporal resolution with a comparatively lower effort and cost. Here, we present the Insect Detect DIY (do-it-yourself) camera trap for non-invasive automated monitoring of flower-visiting insects, which is based on low-cost off-the-shelf hardware components combined with open-source software. Custom trained deep learning models detect and track insects landing on an artificial flower platform in real time on-device and subsequently classify the cropped detections on a local computer. Field deployment of the solar-powered camera trap confirmed its resistance to high temperatures and humidity, which enables autonomous deployment during a whole season. On-device detection and tracking reliably estimated insect activity/abundance after metadata post-processing. Our insect classification model achieved a high top-1 accuracy on the test dataset and generalized well on a real-world dataset with captured insect images. The camera trap design and open-source software are highly customizable and can be adapted to different use cases. With custom trained detection and classification models, as well as accessible software programming, many possible applications surpassing our proposed deployment method can be realized.

show abstract

Section: Insect Detection and Trackingmentioning

confidence: 99%

Insect Detect: An open-source DIY camera trap for automated insect monitoring

Sittinger,

Uhler,

Pink

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This computer program enables tracking pollination events of the same individual between different flowers, and different insect pollinators to an individual flower simultaneously (Ratnayake et al 2021b). The software has been operated using either single camera or an array of cameras (Ratnayake et al 2023) at a berry farm in Victoria, Australia, that relies on insect pollination to produce quality and costcompetitive fruit. Its installation and successful operation has demonstrated that it is possible to automatically capture and process pollination-related data across a large plastic-covered farm polytunnel (Figure 3).…”

Section: New Insights From Australia For Managing Sustainability In A...mentioning

confidence: 99%

A world without bees: new insights from Australia for managing sustainability in a changing climate

Dyer,

Shrestha,

Garcia

et al. 2023

Proc. R. Soc. Vic.

View full text Add to dashboard Cite

Insect pollination is essential for many flowering plants that underpin agriculture and food production, as well as the ecological management of terrestrial environments. Several studies report that insect pollination is responsible for over 33% of food production, worth more than 200 billion US$/year to the international economy. Traditionally, honeybees (<i>Apis mellifera</i>) and bumblebees ( Bombus terrestris</i>) are used as managed species for agricultural crop pollination. These insects are also an important model species for improving scientific understanding of bee sensory processing. With increased awareness of the value of pollination in a changing world, it is important to better understand alternative pollinators, especially how different species tolerate changing environmental conditions. This review encapsulates a decade of comparative research that was principally conducted in Australia, a uniquely placed island continent that facilitates insights into complex processes operating over evolutionary time. Using a combination of field biology, imaging and computer modelling, it has been possible to establish that changes in pollinators result in significant changes in flower colour signaling independent of plant phylogeny. This work proves that pollinator distributions act as a selective factor on the success of plants. We highlight the limitations of current knowledge about the distributions of pollinators caused by data collection constraints. We then present tangible solutions for how technological applications such as mining of information from social network sites, and the use of imaging data combined with artificial intelligence can enhance our understanding of pollinator networks to help manage sustainable food production in a changing world.

show abstract

“…In order to gain a comprehensive understanding of the use of AI in greenhouse cultivation, the review expanded beyond C. sativa to include a wider range of horticulture-specific AI technologies. Such examples include plant and environment data analysis to recognise patterns and correlations; prediction of optimal harvesting times to improve the quality and yield of crops; and task automation in areas such as monitoring and controlling the growth environment, detecting pests and diseases, and optimising labour resource usage [98], [99], [101], [103], [104], [105], [108], [109]. The applications of AI in greenhouse cultivation are diverse, spanning various use cases, system integrations, and stages of technological readiness.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The majority of the studies employ AI for leaf disease detection, leaf area size, and optimal harvesting time [102], [103], [105], [106], [107], while only a few focus on optimising the environment and crop management [99], [100], [103], [107].Additionally, the review of greenhouse AIoT technologies discovered various innovative applications. For instanceRatnayake et al explored AI-based computer vision to improve pollinator monitoring, enabling markerless data capture for insect counting, motion tracking, behaviour analysis, and pollination prediction across large agricultural areas using edge computing and offline automated multi-species counting, tracking and behavioural analysis [109]. The system was tested on a commercial berry farm and demonstrated its ability to track multiple insect varieties and calculate metrics to assess pollination impact.…”

Section: Literature Reviewmentioning

confidence: 99%

A Survey of Modern Greenhouse Technologies and Practices for Commercial Cannabis Cultivation

et al. 2023

View full text Add to dashboard Cite

The limited availability of peer-reviewed scientific evidence in the cannabis industry has led many companies to rely on techniques derived from non-peer-reviewed sources for their practices. This study begins by examining the literature on the cultivation of C. sativa, investigating optimal conditions and their effects on growth, and characterising the requirements for greenhouse monitoring and control. A systematic review of current technological approaches is then conducted. The review demonstrates that technology-based control of greenhouse environments has the potential to surpass manual or traditional rule-based management techniques by reducing costs and increasing yields. However, the adoption of these technologies is impeded by the lack of publicly available labelled data on growth, pest and disease, environmental, and yield data of multiple indoor cultivation cycles. Currently, much of the research in this field is conducted privately by companies in the cannabis industry. This study recognises substantial gaps in research surrounding C. sativa cultivation and emphasises the opportunity for new research to address the absence of available C. sativa datasets and peer-reviewed scientific studies outside of private endeavours.INDEX TERMS AIoT, artificial intelligence (AI), greenhouse cultivation, cannabis, pest and disease detection.

show abstract

Spatial Monitoring and Insect Behavioural Analysis Using Computer Vision for Precision Pollination

Cited by 18 publications

References 58 publications

Insect Detect: An open-source DIY camera trap for automated insect monitoring

Insect Detect: An open-source DIY camera trap for automated insect monitoring

A world without bees: new insights from Australia for managing sustainability in a changing climate

A Survey of Modern Greenhouse Technologies and Practices for Commercial Cannabis Cultivation

Contact Info

Product

Resources

About