Insect Pest Detection and Identification Method Based on Deep Learning for Realizing a Pest Control System

Kuzuhara, Hiroaki; Takimoto, Hironori; Sato, Yasuhiro; Kanagawa, Akihiro

doi:10.23919/sice48898.2020.9240458

Cited by 42 publications

(24 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our system is widely applicable as a means to capture images of plants and insects and to automatically generate monitoring data of insect species abundance (4,(22)(23)(24). Our method could also contribute to insect pest monitoring with camera-equipped traps in agriculture and forestry without killing rare insect species (25,26). Remarkably, our automated insect monitoring camera system can collect images with sufficient resolution to efficiently and accurately analyse individual insects with YOLOv5.…”

Section: Discussionmentioning

confidence: 99%

Accurate detection and identification of insects from camera trap images with deep learning

Bjerge¹,

Alison

Dyrmann³

et al. 2022

Preprint

View full text Add to dashboard Cite

Reported insect declines have dramatically increased the global demand for standardized insect monitoring data. Image-based monitoring can generate such data cost-efficiently and non-invasively. However, extracting ecological data from images is more challenging for insects than for vertebrates because of their small size and great diversity. Deep learning facilitates fast and accurate insect detection and identification, but the lack of training data for coveted deep learning models is a major obstacle for their application. We present a large annotated image dataset of functionally important insect taxa. The primary dataset consists of 29,960 annotated insects representing nine taxa including bees, hoverflies, butterflies and beetles across more than two million images recorded with ten time-lapse cameras mounted over flowers during the summer of 2019. The insect image dataset was extracted using an iterative approach: First, a preliminary detection model identified candidate insects. Second, candidate insects were manually screened by users of an online citizen science platform. Finally, all annotations were quality checked by experts. We used the dataset to train and compare the performance of selected You Only Look Once (YOLO) deep learning algorithms. We show that these models detect and classify small insects in complex scenes with unprecedented accuracy. The best performing YOLOv5 model consistently identifies nine dominant insect species that play important roles in pollination and pest control across Europe. The model reached an average precision of 92.7% and recall of 93.8 % in detection and classification across species. Importantly, when presented with uncommon or unclear insects not seen during training, our model detects 80% of individuals and usually interprets them as closely related species. This is a useful property to (1) detect rare insects for which training data are absent, and (2) generate new training data to correctly identify those insects in future. Our camera system, dataset and deep learning framework show promising results in non-destructive monitoring of insects. Furthermore, resulting data are useful to quantify phenology, abundance, and foraging behaviour of flower-visiting insects. Above all, this dataset represents a critical benchmark for future development and evaluation of deep learning models for insect detection and identification.

show abstract

Section: Discussionmentioning

confidence: 99%

Accurate detection and identification of insects from camera trap images with deep learning

Bjerge¹,

Alison

Dyrmann³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Rotation is used by Ding et al [19], whereas reflection is used by Khalifa et al [37]. Some articles use more than the first two, such as adding noise [8], scaling [10], and flipping and colour adjustments [18,34].…”

Section: Combination Of Existing Image Data Sets and Other Methodsmentioning

confidence: 99%

“…The most well-known collection methods involve the use of search engines like Google [11] and Bing [12] or the use of websites like Flickr [13] as the standard gathering techniques. While Butera et al [7] employ all three techniques, other authors [8], [9] use Google and Flickr, and some authors [10] do not mention the techniques employed.…”

Section: Web Sourcesmentioning

confidence: 99%

A Systematic Literature Review on Insect Detection in Images

Souifi¹,

Mdhaffar²,

Rodriguez³

et al. 2022

Signal, Image Processing and Embedded Systems Trends

View full text Add to dashboard Cite

Due to the advancements of deep learning (DL), particularly in the areas of visual object detection and convolutional neural networks (CNN), insect detecetion in images has received a lot of attention from the research community in the last few years. This paper presents a systematic review of the literature on the topic of insect detection as a case of object detection in images. It covers 50 research papers on the subject and responds to three research questions: i) type of dataset used; ii) detection technique used; iii) insect location. The paper also provides a summary of existing methods used for insect detection.

show abstract

“…With increasing computational power, more complex neural network architectures, i.e., deep learning (DL) approaches have recently helped in tackling more challenging tasks in the field of food and agricultural science (Lee et al, 2015;DeChant et al, 2017;Lu et al, 2017;Zhang et al, 2018). Although there have been relatively fewer DL studies to identify filth elements for food contamination (Reinholds et al, 2015;Bansal et al, 2017), variations of DL designs such as Region-based Fully Convolutional Network (R-FCN), convolutional block attention module (CBAM), convolutional neural network (CNN) and pre-trained models have shown promising performances for pest, stored-grain insect, and fly classification (Chen et al, 2020;Kuzuhara et al, 2020;Shi et al, 2020). The DL models have not only achieved high classification accuracies, but also offered a new way of feature extraction embedded in the process as an alternative to conventional features such as domain-dependent, global, local, and mid-level features (Martineau et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Accurate species identification of food-contaminating beetles with quality-improved elytral images and deep learning

Bişğin

Bera

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Food samples are routinely screened for food-contaminating beetles (i.e., pantry beetles) due to their adverse impact on the economy, environment, public health and safety. If found, their remains are subsequently analyzed to identify the species responsible for the contamination; each species poses different levels of risk, requiring different regulatory and management steps. At present, this identification is done through manual microscopic examination since each species of beetle has a unique pattern on its elytra (hardened forewing). Our study sought to automate the pattern recognition process through machine learning. Such automation will enable more efficient identification of pantry beetle species and could potentially be scaled up and implemented across various analysis centers in a consistent manner. In our earlier studies, we demonstrated that automated species identification of pantry beetles is feasible through elytral pattern recognition. Due to poor image quality, however, we failed to achieve prediction accuracies of more than 80%. Subsequently, we modified the traditional imaging technique, allowing us to acquire high-quality elytral images. In this study, we explored whether high-quality elytral images can truly achieve near-perfect prediction accuracies for 27 different species of pantry beetles. To test this hypothesis, we developed a convolutional neural network (CNN) model and compared performance between two different image sets for various pantry beetles. Our study indicates improved image quality indeed leads to better prediction accuracy; however, it was not the only requirement for achieving good accuracy. Also required are many high-quality images, especially for species with a high number of variations in their elytral patterns. The current study provided a direction toward achieving our ultimate goal of automated species identification through elytral pattern recognition.

show abstract

Insect Pest Detection and Identification Method Based on Deep Learning for Realizing a Pest Control System

Cited by 42 publications

References 19 publications

Accurate detection and identification of insects from camera trap images with deep learning

Accurate detection and identification of insects from camera trap images with deep learning

A Systematic Literature Review on Insect Detection in Images

Accurate species identification of food-contaminating beetles with quality-improved elytral images and deep learning

Contact Info

Product

Resources

About