Computer vision and deep learning in insects for food and feed production: A review

Nawoya, Sarah; Ssemakula, Frank; Akol, Roseline; Geissmann, Quentin; Karstoft, Henrik; Bjerge, Kim; Mwikirize, Cosmas; Katumba, Andrew; Gebreyesus, Grum

doi:10.1016/j.compag.2023.108503

Cited by 13 publications

(2 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image acquisition methods for insect detection can be several, and from the review of the research published in the last decade (Gao et al, 2024;Nawoya et al, 2024), they include various devices like handheld cameras (digital cameras, smartphones), and mobile or fixed smart trap systems, but also datasets such as IP102, as well as photographs downloaded from search engines like Bing and Google. Uncrewed Aerial Systems (UAS) can play an important role in getting on-site images, since they can move and navigate automatically, support various sensors, and provide safe access to difficult locations.…”

Section: Introductionmentioning

confidence: 99%

Monitoring the spread of a pathogenic insect on vineyards using UAS

Longhi,

Martino,

Lingua

et al. 2024

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Globalisation has contributed to rapid economic growth but has also exposed vulnerabilities such as the spread of pests in agriculture. An example is the Popillia Japonica Newman beetle, introduced to Italy in 2014, which has caused significant economic losses, mainly affecting vine cultures. Reliable identification of pests is essential for its management, but it is time-consuming and laborious. This has prompted growing interest in image-based methods, supported by computer vision (CV), which can significantly improve efficiency in insect detection. This study aims to evaluate a CV algorithm's effectiveness in identifying adult specimens of Popillia using Near-Infrared sensors on Uncrewed Aerial Systems (UAS). The project, conducted in two vineyards in northern Italy, intends to establish a replicable and standardised data acquisition protocol for future monitoring activities. Insects detected by the CV-based method are validated by manual counting performed by entomologists. In a GIS environment, prescription maps are generated in near real-time to identify where the vineyard is most affected and to guide the drone spraying treatment only on the areas in which the threshold is exceeded. The study demonstrates effective semi-automated monitoring, with a clear correlation between CV-based and manual insect measurements, as indicated by the Pearson correlation coefficients ranging from 0.89 to 0.96. Although the CV-based method may overestimate insect numbers, it provides valuable insights for targeted pest management interventions and damage assessment. The project outcomes offer a promising approach to safeguarding agriculture against invasive species, enhancing regional economic resilience while minimising the spread of insecticide, the required time, and human interaction with harmful substances.

show abstract

Section: Introductionmentioning

confidence: 99%

Monitoring the spread of a pathogenic insect on vineyards using UAS

Longhi,

Martino,

Lingua

et al. 2024

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Novel phenotypes based on machine-learning methods may be a solution, as these methods are typically cheap, easy, non-invasive, and fast. Examples are the assessment of larval growth and larval body size using computer vision (Laursen et al, 2021;Majewski et al, 2022;Nawoya et al, 2024), and the prediction of larval nutritional composition through infrared analysis (Cruz-Tirado et al, 2023a,b;Kröncke et al, 2023a,b,c).…”

Section: Introductionmentioning

confidence: 99%

A bio-economic model for estimating economic values of important production traits in the black soldier fly (Hermetia illucens)

Zaalberg,

Nielsen,

Noer

et al. 2024

J. Insects Food Feed

View full text Add to dashboard Cite

Black soldier fly (BSF) larvae are exceptionally efficient at converting otherwise unusable waste products, while having a minimal impact on the environment. To optimise the production of BSF larvae, selective breeding could be used. With selective breeding, the best individuals to breed the next generation are selected, for example, with a breeding goal. This study aimed to make the first step towards defining such a breeding goal, by estimating the economic values (EV) of traits that are important for the production of BSF larvae. EV were estimated for larval mass on day 15, feed intake, feed conversion ratio, growth rate, dry mass-, protein- and fat content, development time, eggs per fly, egg hatching rate, and larval mortality. A bio-economic model was used to estimate the profit of a BSF production system that produces 1000 kg of wet larvae at harvesting. The EV of a trait was estimated as the increase in profit when the trait value was increased by 10%, whilst the other traits remained unchanged. EV were expressed per 10% increase, and changes in revenues and costs were specified. The results showed traits with the highest EV were related to composition (dry mass-, and protein-content) and growth (larval mass, development time, growth rate). Traits related to reproduction and flies (development from pupa to fly, number of eggs) had the lowest EV. Due to the lack of information on genetic parameters, the EV are expressed per +10% of the mean value of a trait. In the future, when more information is available, the EV should be expressed per genetic standard deviation. In conclusion, this is the first study that estimated EV for an insect species. The results are a first step towards developing a more sophisticated breeding program for optimizing BSF production.

show abstract