Search

Because our civilization has relied on pesticides to fight weeds, insects, and diseases since antiquity, the use of these chemicals has become natural and exclusive. Unfortunately, the use of pesticides has progressively had alarming effects on water quality, biodiversity, and human health. This paper proposes to improve farming practices by replacing pesticides with a laser-based robotic approach. This study focused on the neutralization of aphids, as they are among the most harmful pests for crops and complex to control. With the help of deep learning, we developed a mobile robot that spans crop rows, locates aphids, and neutralizes them with laser beams. We have built a prototype with the sole purpose of validating the localization-neutralization loop on a single seedling row. The experiments performed in our laboratory demonstrate the feasibility of detecting different lines of aphids (50% detected at 3 cm/s) and of neutralizing them (90% mortality) without impacting the growth of their host plants. The results are encouraging since aphids are one of the most challenging crop pests to eradicate. However, enhancements in detection and mainly in targeting are necessary to be useful in a real farming context. Moreover, robustness regarding field conditions should be evaluated.

Because our civilization has relied on pesticides to fight weeds, insects, and diseases since antiquity, the use of these chemicals has become natural and exclusive. Unfortunately, the use of pesticides has progressively had alarming effects on water quality, biodiversity, and human health. This paper proposes to improve farming practices by replacing pesticides with a laser-based robotic approach. This study focused on the neutralization of aphids, as they are among the most harmful pests for crops and complex to control. With the help of deep learning, we developed a mobile robot that spans crop rows, locates aphids, and neutralizes them with laser beams. We have built a prototype with the sole purpose of validating the localization-neutralization loop on a single seedling row. The experiments performed in our laboratory demonstrate the feasibility of detecting different lines of aphids (50% detected at 3 cm/s) and of neutralizing them (90% mortality) without impacting the growth of their host plants. The results are encouraging since aphids are one of the most challenging crop pests to eradicate. However, enhancements in detection and mainly in targeting are necessary to be useful in a real farming context. Moreover, robustness regarding field conditions should be evaluated. [ABSTRACT FROM AUTHOR]

Simple Summary: Accurate recognition and detection of pests is the basis of integrated pest management (IPM). Manual pest detection is a time-consuming and laborious work. We use computer vision technology to design an automatic aphid detection network. Compared with other methods, our model can improve the performance and efficiency of aphid detection simultaneously. Experimental results prove the effectiveness of our method. It is well recognized that aphid infestation severely reduces crop yield and further leads to significant economic loss. Therefore, accurately and efficiently detecting aphids is of vital importance in pest management. However, most existing detection methods suffer from unsatisfactory performance without fully considering the aphid characteristics, including tiny size, dense distribution, and multi-viewpoint data quality. In addition, existing clustered tiny-sized pest detection methods improve performance at the cost of time and do not meet the real-time requirements. To address the aforementioned issues, we propose a robust aphid detection method with two customized core designs: a Transformer feature pyramid network (T-FPN) and a multi-resolution training method (MTM). To be specific, the T-FPN is employed to improve the feature extraction capability by a feature-wise Transformer module (FTM) and a channel-wise feature recalibration module (CFRM), while the MTM aims at purifying the performance and lifting the efficiency simultaneously with a coarse-to-fine training pattern. To fully demonstrate the validity of our methods, abundant experiments are conducted on a densely clustered tiny pest dataset. Our method can achieve an average recall of 46.1% and an average precision of 74.2%, which outperforms other state-of-the-art methods, including ATSS, Cascade R-CNN, FCOS, FoveaBox, and CRA-Net. The efficiency comparison shows that our method can achieve the fastest training speed and obtain 0.045 s per image testing time, meeting the real-time detection. In general, our TD-Det can accurately and efficiently detect in-field aphids and lays a solid foundation for automated aphid detection and ranking. [ABSTRACT FROM AUTHOR]

It is well recognized that aphid infestation severely reduces crop yield and further leads to significant economic loss. Therefore, accurately and efficiently detecting aphids is of vital importance in pest management. However, most existing detection methods suffer from unsatisfactory performance without fully considering the aphid characteristics, including tiny size, dense distribution, and multi-viewpoint data quality. In addition, existing clustered tiny-sized pest detection methods improve performance at the cost of time and do not meet the real-time requirements. To address the aforementioned issues, we propose a robust aphid detection method with two customized core designs: a Transformer feature pyramid network (T-FPN) and a multi-resolution training method (MTM). To be specific, the T-FPN is employed to improve the feature extraction capability by a feature-wise Transformer module (FTM) and a channel-wise feature recalibration module (CFRM), while the MTM aims at purifying the performance and lifting the efficiency simultaneously with a coarse-to-fine training pattern. To fully demonstrate the validity of our methods, abundant experiments are conducted on a densely clustered tiny pest dataset. Our method can achieve an average recall of 46.1% and an average precision of 74.2%, which outperforms other state-of-the-art methods, including ATSS, Cascade R-CNN, FCOS, FoveaBox, and CRA-Net. The efficiency comparison shows that our method can achieve the fastest training speed and obtain 0.045 s per image testing time, meeting the real-time detection. In general, our TD-Det can accurately and efficiently detect in-field aphids and lays a solid foundation for automated aphid detection and ranking.

In agriculture, aphids are one of the most destructive pests, responsible for major reductions in wheat, corn and rape production leading to significant economic losses. However, manual pest recognition approaches are often time-consuming and laborious for Integrated Pest Management (IPM). In addition, the existing pest detection methods based on Convolutional Neural Network (CNN) are not satisfactory for small aphid recognition and detection in the field because aphids are tiny and often in dense distributions. In this work, a two-stage aphid detector named Coarse-to-Fine Network (CFN) is proposed to address these problems. The key idea of our method is to develop a Coarse Convolutional Neural Network (CCNN) for aphid clique searching as well as a Fine Convolutional Neural Network (FCNN) for refining the regions of aphids in the clique. Specifically, The CCNN detects approximately all the object regions from natural aphid images with various aphid distributions including dense aphid cliques and sparse aphid objects, in which an Improved Non-Maximum Suppression (INMS) strategy is proposed to eliminate overlapping regions. Then, the FCNN further refines the detected aphid regions from the CCNN. The final recognition and detection result would be obtained by combining the outputs from CCNN and FCNN together. Experiments on our dataset show that our CFN achieves an aphid detection performance of 76.8% Average Precision (AP), which improves 20.9%, 18%,13.7% and 12.5% compared to four state-of-the-art approaches. • Domain specific dataset for aphid recognition and detection in the field. • This dataset may have high application value in practical aphid monitoring. • Coarse-to-fine network proposed for aphid detection in dense distribution regions. • Improved non-maximum suppression can eliminate overlapping bounding boxes. [ABSTRACT FROM AUTHOR]

• Inception of a new task of deep learning based pest colony detection from images. • First agricultural aphid colony dataset: 376 Brassica images and 1967 colony labels. • A bounding box merging based aphid colony annotation technique is proposed. • Evaluation of several deep learning detectors for performance analysis. Plant pathogenic colony-forming aphids are serious pests of agricultural crops. Most aphid species develop colonies, which are several to many aphids that are functionally organized to extract food from plants. Early and efficient detection of aphid colonies enables the implementation of control measures to reduce crop damage. Aphid colonies exhibit different shapes, sizes, and numbers of individuals, and their distribution makes it hard to detect them correctly. This paper investigates machine learning-based aphid colony detection from imagery. To the best of our knowledge, it is the first study that uses artificial intelligence-based computing algorithms to detect aphid colonies from images. As such, no aphid colony image dataset is currently available publicly. To mitigate this, we have relabelled an existing insect and pest dataset and repurposed it as an aphid colony dataset (AphColDat). For labelling, first, we automatically identify the regions of interest for colonies based on the locations and distributions of aphids. A novel bounding box merging technique is proposed to generate regions potential colony boxes. These colony boxes are a collection of single or overlapping aphid boxes that co-locate together in a colony. Once the dataset is constructed, a convolutional neural network (CNN)-based binary classification algorithm is applied to the images to create AphColDat. This paper evaluates several object detecting deep learning models on the newly developed dataset. The results demonstrate mean average precisions (mAP) of 56.9%, 53.4%, 53.1%, and 48.7% respectively by Faster R-CNN, SSD, YOLOv3, and EfficientNet. In terms of average detection speed (computational time), SSD and EfficientNet are faster than Faster R-CNN and YOLOv3. [ABSTRACT FROM AUTHOR]