Abstract
The detection of grain pests is of great significance to grain storage. However, in practice, because the size of grain insects is too small to identify. In this paper, the feature fusion SSD(single shot multi-box detector) algorithm based on the Top-Down strategy was proposed. Firstly, the Top-Down module is used to fuse the output characteristics of conv4 and conv5, and the block 11 which is not conducive to small object detection is deleted. Secondly, K-means clustering algorithm is used to cluster prior bounding boxes and made them more suitable for grain pests, which improves the performance on small object detection of grain pests. Five methods were used to enhance the self-made dataset of grain pests, and the enhanced dataset reached 9990 images. Experiments on the enhanced dataset show that the optimized model achieves a mAP (mean Average Precision) 96.89% with detection speed of 0.040s per image. Compared with 95.45% of the mAP achieved by the original SSD algorithm, the proposed model has a great improvement on detection performance. Compared with two-stages Faster R-CNN (mAP is 90.53% and speed is 0.115s per image), YOLOv3, TDFSSD and EfficentDet (D2, D1), the speed and accuracy of the optimized SSD algorithm have obvious advantages. The experimental results show that the proposed SSD model has a good performance on small object detection of grain pests and has a certain guiding significance for subsequent grain pest image detection.
Highlights
With the development of computer technology, the requirements for informatization of the food industry are getting higher
As an important part of the monitoring of grain quality, grain pest detection based on image processing has become a popular research in recent years
We propose a feature fusion method, which maintains high accuracy and enough speed for grain pests
Summary
With the development of computer technology, the requirements for informatization of the food industry are getting higher. One-stage object detection algorithm is represented by YOLO [2] (You Only Look Once), YOLOv2 [3], YOLOv3[4] and SSD (Single Shot Multi-Box Detector) [5], which is known for its fast detection speed. According to the small object characteristics of grain pests, we use the top-down module and fuse the lowlevel and high-level features to introduce stronger semantic information, and cutting the basic network block of SSD. Two-stage Detectors: Wenjie Guan etc [11] proposed a new MOD method based on Faster R-CNN framework by introducing a feature fusion module and a novel Region Objectness Network. The designer of DSSD (Deconvolutional Single Shot Detector) [16] used the Top-Down strategy to improve the accuracy and designed a reasonable network to introduce more semantic information into the feature layer. Grain Pest is typically small object and according to the use requirements, it is necessary to improve the detection accuracy and speed, so that it can detect grain pests in real time
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
