SB: A NOVEL DATASET FOR IMPROVING INSECT DETECTION PERFORMANCE

Nguyen Duc Tuan Anh; Ho Bach Tuyet; Cao Thi Bich Lien; Do Quoc Hung; Nguyen Xuan Hoan

Nguyen Duc Tuan Anh Hung Yen University of Technology and Education
Ho Bach Tuyet Hung Yen University of Technology and Education
Cao Thi Bich Lien Halong University
Do Quoc Hung Thanh Dong University
Nguyen Xuan Hoan Trane Vietnam Services Co., Ltd.

Keywords: Stink bug, object detection, dataset

Abstract

Stink bug are one of the major causes of Longan damage - a crop of considerable economic value that is extensively cultivated in Vietnam. Early detection of this insect pest enables growers to implement effective control measures, thereby enhancing fruit quality and yield. In recent years, convolutional neural network- -based object detection models have garnered significant attention and obtained impressive performance. Nevertheless, the accuracy of detecting stink bug has not met expectations due to the scarcity of adequate datasets for training and evaluation purposes. This study aims to address the challenges associated with stink bug detection by introducing a novel dataset named SB. The SB dataset comprises 4,579 real-world stink bug images with bounding box annotations. The SB dataset is employed to train three state-of-the-art object detection models, including SSD512, RetinaNet, and YOLOv7. Experimental findings indicate that the models achieve pothole detection performance of up to 75.62%.

References

Boedeker, Wolfgang, Meriel Watts, Peter Clausing, and Emily Marquez. “The global distribution of acute unintentional pesticide poisoning: estimations based on a systematic review.” BMC public health, 2020, 20, pp. 1-19.

Doan, T.N., Large-scale insect detection with fine-tuning yolox. International Jour-nal of Membrane Science and Technology, 2023, 10, pp. 892–915.

Moura, Rafael Rios, and Raquel Luiza Carvalho, “A novel trophobiotic interaction between a Neotropical stink bug and an ant species: insights into potential benefits to the host plant.” Behavioural Processes, 2021, 182, 104296.

S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” in Advances in neural information processing systems, 2015, pp. 91–99.

W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “Ssd: Single shot multibox detector,” in European conference on computer vision. Springer, 2016, pp. 21–37.

T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Doll ´ar, “Focal loss for dense object detection,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980–2988.

Wang, Chien-Yao, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. “YOLOv7: Trainable bagof-freebies sets new state-of-the-art for real-time object detectors.” In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 7464-7475.

Le, Trung-Hieu, Shih-Chia Huang, and Quoc-Viet Hoang. “Multilevel Knowledge Transmission for Object Detection in Rainy Night Weather Conditions.” IEEE Transactions on Industrial Informatics, 2024.

Huang, Shih-Chia, Da-Wei Jaw, Quoc-Viet Hoang, and Trung-Hieu Le. “3FL-Net: an efficient approach for improving performance of lightweight detectors in rainy weather conditions.” IEEE Transactions on Intelligent Transportation Systems, 2023, 24, no. 4, pp. 4293-4305.

Huang, Shih-Chia, Quoc-Viet Hoang, and Da-Wei Jaw. “Self-adaptive feature transformation networks for object detection in low luminance images.” ACM Transactions on Intelligent Systems and Technology (TIST), 2022, 13, no. 1, pp. 1-11.

Huang, Shih-Chia, Quoc-Viet Hoang, and Trung-Hieu Le. “SFA-Net: A selective features absorption network for object detection in rainy weather conditions.” IEEE Transactions on Neural Networks and Learning Systems, 2022, 34, no. 8, pp. 5122-5132.

Hoang, Quoc-Viet, Trung-Hieu Le, and Shih-Chia Huang. “Data augmentation for improving SSD performance in rainy weather conditions.” In 2020 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan), IEEE, 2020, pp. 1-2.

Hoang, Quoc-Viet, Trung-Hieu Le, and Shih-Chia Huang. “An improvement of RetinaNet for hand detection in intelligent homecare systems.” In 2020 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan), IEEE, 2020, pp. 1-2.

Huang, Shih-Chia, Trung-Hieu Le, and Da-Wei Jaw. “DSNet: Joint semantic learning for object detection in inclement weather conditions.” IEEE transactions on pattern analysis and machine intelligence, 2020, 43, no. 8, pp. 2623-2633.

Le, Trung-Hieu, Shih-Chia Huang, and Da-Wei Jaw. “Cross-resolution feature fusion for fast hand detection in intelligent homecare systems.” IEEE Sensors Journal, 2019, 19, no. 12, pp. 4696-4704.

Wu, Xiaoping, Chi Zhan, Yu-Kun Lai, Ming-Ming Cheng, and Jufeng Yang. “Ip102: A largescale benchmark dataset for insect pest recognition.” In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 8787-8796.

Tzutalin. Labelimg: A Graphical Image Annotation Tool and Label Object Bounding Boxes in Images. Accessed: Oct. 8, 2020. [Online]. Available: https://github.com/tzutalin/labelImg