article · Sensors
Detecting insect pests during their early larval stages offers notable advantages for agriculture, allowing for timely intervention before severe crop damage occurs. While existing machine vision tools generally target adult insects or post-infestation symptoms, this research evaluates a robotic approach dedicated to identifying pest larvae using deep learning. The system mounts an off-the-shelf front-pointing RGB stereo camera on a mobile robot, evaluating eight models pre-trained on ImageNet using a dedicated pest larvae dataset. To balance operational efficiency with precise localisation, the system pairs an insect classifier for broader peripheral visual scanning with a faster region-based convolutional neural network detector for close-up identification. Dynamics simulated through CoppeliaSim and MATLAB and SIMULINK tools confirmed the operational feasibility of the configuration. The deep-learning setup achieved 99 percent classification accuracy alongside a detector mean average precision score of 0.84.
Pest larvae cause extensive damage to crops but are typically harder to spot than mature insects. Developing robotic vision systems that spot these early developmental stages allows farmers to intervene before infestations spread widely. This precision approach supports earlier, more targeted pest management, reducing broad pesticide usage and safeguarding crop yields.
This technology could enable developers of autonomous agricultural machinery and smart spraying robots to integrate automated early-stage pest detection. Farmers and crop-protection operators would be the primary end users of such systems. Currently, the work stands as applied research tested primarily through algorithmic benchmarking and software simulations, indicating it requires field validation before commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
Accurately detecting early developmental stages of insect pests (larvae) from off-the-shelf stereo camera sensor data using deep learning holds several benefits for farmers, from simple robot configuration to early neutralization of this less agile but more disastrous stage. Machine vision technology has advanced from bulk spraying to precise dosage to directly rubbing on the infected crops. However, these solutions primarily focus on adult pests and post-infestation stages. This study suggested using a front-pointing red-green-blue (RGB) stereo camera mounted on a robot to identify pest larvae using deep learning. The camera feeds data into our deep-learning algorithms experimented on eight ImageNet pre-trained models. The combination of the insect classifier and the detector replicates the peripheral and foveal line-of-sight vision on our custom pest larvae dataset, respectively. This enables a trade-off between the robot's smooth operation and localization precision in the pest captured, as it first appeared in the farsighted section. Consequently, the nearsighted part utilizes our faster region-based convolutional neural network-based pest detector to localize precisely. Simulating the employed robot dynamics using CoppeliaSim and MATLAB/SIMULINK with the deep-learning toolbox demonstrated the excellent feasibility of the proposed system. Our deep-learning classifier and detector exhibited 99% and 0.84 accuracy and a mean average precision, respectively.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/s23063147
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
