Automatic in-trap pest detection using deep learning for pheromone-based Dendroctonus valens monitoring

Dendroctonus valens LeConte, the red turpentine beetle (RTB) is an invasive pest which is severely threatening pine species in China. Traditional pheromone-based RTB monitoring depends on a manual count, which is not only time consuming but also error-prone. This study proposes a deep learning detection method for counting adult RTBs directly in the pheromone trap. The images of bark beetles were captured by a digital camera embedded in the collection cup of the pheromone trap. The state-of-the-art one-stage deep learning detector RetinaNet was further downsized by the depthwise separable convolution and feature pyramid tailoring, which was feasible to run on embedded devices. To enable the fine-grained identification of bark beetles, the downsized detector was enhanced by k-means anchor optimisation and residual classification subnet. The models were trained end-to-end on a GPU workstation with data augmentation and then deployed on embedded devices with minimal preprocessing. Experiments demonstrated that the object level average precision (AP) was 0.746 and the average runtime on the Jetson TX2 and Raspberry Pi 3b were 0.448s and 23.44s, respectively. The in-trap detector was capable of distinguishing the most aggressive RTBs from other five species of bark beetles attracted by pheromone with unconstrained size, pose, orientation, integrity, and position. The proposed method showed promising performance both qualitatively and quantitatively within limited computational budgets, which has introduced a practical and applicable solution for early warning of RTB outbreaks.

[1]  Thomas G. Dietterich,et al.  Segmentation of touching insects based on optical flow and NCuts , 2013 .

[2]  José García,et al.  A Distributed K-Means Segmentation Algorithm Applied to Lobesia botrana Recognition , 2017, Complex..

[3]  Tae-Soo Chon,et al.  Automatic identification and counting of small size pests in greenhouse conditions with low computational cost , 2015, Ecol. Informatics.

[4]  Graham W. Taylor,et al.  Automatic moth detection from trap images for pest management , 2016, Comput. Electron. Agric..

[5]  Zhongzhi Han,et al.  Research on insect pest image detection and recognition based on bio-inspired methods , 2018 .

[6]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[7]  Sang Cheol Kim,et al.  A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition , 2017, Sensors.

[8]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Saeid Minaei,et al.  Vision-based pest detection based on SVM classification method , 2017, Comput. Electron. Agric..

[10]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[11]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[12]  Sreekala G. Bajwa,et al.  Detection of soybean aphids in a greenhouse using an image processing technique , 2017, Comput. Electron. Agric..

[13]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[14]  Philipp Kirsch,et al.  Sex Pheromones and Their Impact on Pest Management , 2010, Journal of Chemical Ecology.

[15]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Alejandro López,et al.  Combination of image processing and artificial neural networks as a novel approach for the identification of Bemisia tabaci and Frankliniella occidentalis on sticky traps in greenhouse agriculture , 2016, Comput. Electron. Agric..

[17]  Jang-myung Lee,et al.  Detection of small-sized insect pest in greenhouses based on multifractal analysis , 2015 .

[18]  Ring T. Cardé,et al.  CONTROL OF MOTH PESTS BY MATING DISRUPTION: Successes and Constraints , 1995 .

[19]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.