Neural networks for Pest Detection in Precision Agriculture

Segalla, Andrea; Fiacco, Gianluca; Tramarin, Luca; Nardello, Matteo; Brunelli, Davide

doi:10.1109/metroagrifor50201.2020.9277657

Cited by 16 publications

(15 citation statements)

References 27 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2020, Segalla et al [24] also wrote about an automated trap which is very similar to the trap proposed by Brunelli et al [23]. The two articles show high similarity.…”

Section: Earlier Prototype Trapsmentioning

confidence: 87%

“…However, there are differences as well. Since the Intel Movidius Neural Compute Stick is rather power demanding, the authors of [24] measured the energy consumption of the Raspberry Pi 3 and 4 devices with and without the accelerator stick. They found that the Raspberry Pi 3 with the accelerator stick requires the least amount of energy to run the moth counter software.…”

Section: Earlier Prototype Trapsmentioning

confidence: 99%

See 1 more Smart Citation

Codling Moth Monitoring with Camera-Equipped Automated Traps: A Review

Sütő

2022

Agriculture

View full text Add to dashboard Cite

The codling moth (Cydia pomonella) is probably the most harmful pest in apple and pear orchards. The crop loss due to the high harmfulness of the insect can be extremely expensive; therefore, sophisticated pest management is necessary to protect the crop. The conventional monitoring approach for insect swarming has been based on traps that are periodically checked by human operators. However, this workflow can be automatized. To achieve this goal, a dedicated image capture device and an accurate insect counter algorithm are necessary which make online insect swarm prediction possible. From the hardware side, more camera-equipped embedded systems have been designed to remotely capture and upload pest trap images. From the software side, with the aid of machine vision and machine learning methods, traditional (manual) identification and counting can be solved by algorithm. With the appropriate combination of the hardware and software components, spraying can be accurately scheduled, and the crop-defending cost will be significantly reduced. Although automatic traps have been developed for more pest species and there are a large number of papers which investigate insect detection, a limited number of articles focus on the C. pomonella. The aim of this paper is to review the state of the art of C. pomonella monitoring with camera-equipped traps. The paper presents the advantages and disadvantages of automated traps’ hardware and software components and examines their practical applicability.

show abstract

“…In 2020, Segalla et al [24] also wrote about an automated trap which is very similar to the trap proposed by Brunelli et al [23]. The two articles show high similarity.…”

Section: Earlier Prototype Trapsmentioning

confidence: 87%

Section: Earlier Prototype Trapsmentioning

confidence: 99%

Codling Moth Monitoring with Camera-Equipped Automated Traps: A Review

Sütő

2022

Agriculture

View full text Add to dashboard Cite

show abstract

“…Brunelli et al [29] presented an ultra-low power smart camera capable of detecting and recognizing pests in an apple field using a neural networks approach. An evolution of this system used Raspberry Pi [30] and Intel Movidius Neural Compute Stick [31], both powered by a solar panel. Table 1 compares these works and IndoorPlant according to the type of sensor they use, which plant species were cultivated, data analysis and storage, prediction technique, and use of historical contexts.…”

Section: Related Workmentioning

confidence: 99%

“…With this, IndoorPlant tells the farmer to modify the cultivation parameter; however, the farmer needs to approve this change. Another aspect is that the previous studies had only one specific service, such as predicting the temperature and humidity of the greenhouse [19], intelligent irrigation [23] or monitoring environment data [26][27][28][29][30][31]. IndoorPlant, on the other hand, can provide several intelligent services for the user, such as predicting harvest time, recommending improvements in cultivation, and alarms for any problem found in cultivation.…”

Section: Related Workmentioning

confidence: 99%

IndoorPlant: A Model for Intelligent Services in Indoor Agriculture Based on Context Histories

Martini

Helfer

Barbosa

et al. 2021

Sensors

View full text Add to dashboard Cite

The application of ubiquitous computing has increased in recent years, especially due to the development of technologies such as mobile computing, more accurate sensors, and specific protocols for the Internet of Things (IoT). One of the trends in this area of research is the use of context awareness. In agriculture, the context involves the environment, for example, the conditions found inside a greenhouse. Recently, a series of studies have proposed the use of sensors to monitor production and/or the use of cameras to obtain information about cultivation, providing data, reminders, and alerts to farmers. This article proposes a computational model for indoor agriculture called IndoorPlant. The model uses the analysis of context histories to provide intelligent generic services, such as predicting productivity, indicating problems that cultivation may suffer, and giving suggestions for improvements in greenhouse parameters. IndoorPlant was tested in three scenarios of the daily life of farmers with hydroponic production data that were obtained during seven months of cultivation of radicchio, lettuce, and arugula. Finally, the article presents the results obtained through intelligent services that use context histories. The scenarios used services to recommend improvements in cultivation, profiles and, finally, prediction of the cultivation time of radicchio, lettuce, and arugula using the partial least squares (PLS) regression technique. The prediction results were relevant since the following values were obtained: 0.96 (R2, coefficient of determination), 1.06 (RMSEC, square root of the mean square error of calibration), and 1.94 (RMSECV, square root of the mean square error of cross validation) for radicchio; 0.95 (R2), 1.37 (RMSEC), and 3.31 (RMSECV) for lettuce; 0.93 (R2), 1.10 (RMSEC), and 1.89 (RMSECV) for arugula. Eight farmers with different functions on the farm filled out a survey based on the technology acceptance model (TAM). The results showed 92% acceptance regarding utility and 98% acceptance for ease of use.

show abstract

“…Deep learning techniques are recently used to overcome these limitations and achieve a completely automated, realtime pest monitoring system by removing the human from the loop [20]. [21] is one of the recent works that exploit ML techniques to classify insects.…”

Section: Related Workmentioning

confidence: 99%

Automated Pest Detection With DNN on the Edge for Precision Agriculture

Albanese

Nardello

Brunelli

2021

IEEE J. Emerg. Sel. Topics Circuits Syst.

Self Cite

View full text Add to dashboard Cite

Artificial intelligence has smoothly penetrated several economic activities, especially monitoring and control applications, including the agriculture sector. However, research efforts toward low-power sensing devices with fully functional machine learning (ML) on-board are still fragmented and limited in smart farming. Biotic stress is one of the primary causes of crop yield reduction. With the development of deep learning in computer vision technology, autonomous detection of pest infestation through images has become an important research direction for timely crop disease diagnosis. This paper presents an embedded system enhanced with ML functionalities, ensuring continuous detection of pest infestation inside fruit orchards. The embedded solution is based on a low-power embedded sensing system along with a Neural Accelerator able to capture and process images inside common pheromone-based traps. Three different ML algorithms have been trained and deployed, highlighting the capabilities of the platform. Moreover, the proposed approach guarantees an extended battery life thanks to the integration of energy harvesting functionalities. Results show how it is possible to automate the task of pest infestation for unlimited time without the farmer's intervention.

show abstract

Neural networks for Pest Detection in Precision Agriculture

Cited by 16 publications

References 27 publications

Codling Moth Monitoring with Camera-Equipped Automated Traps: A Review

Codling Moth Monitoring with Camera-Equipped Automated Traps: A Review

IndoorPlant: A Model for Intelligent Services in Indoor Agriculture Based on Context Histories

Automated Pest Detection With DNN on the Edge for Precision Agriculture

Contact Info

Product

Resources

About