Abstract
Pest species recognition suffers from the problems of easy loss of small targets, dense pest distribution, and low individual recognition rate. To improve the efficiency of pest monitoring, this paper proposed a pest species recognition algorithm called DF-YOLO based on the YOLOv4 network. First, the DenseNet network is introduced into the YOLOv4 backbone network CSPDarknet53 to enhance the feature extraction capability of the model and improve the individual recognition rate of densely distributed targets. Second, the focal loss function is used to improve the effect of sample imbalance on training and optimize the mining process of complex samples. The algorithm was tested on a homemade pest dataset. And the results show that the mAP (mean average precision) of the method is 94.89%, which is 4.66% higher than that before improvement, and the detection speed is 18.92 f/s, which is better than the mainstream algorithm. Experiments were conducted under different light sources, different backgrounds, and different densities. The mAP of our method is 93.96% with an accuracy within 1%, which proves the high robustness of the method. This study improves the intelligence of pest control, and the proposed method is more effective in pest species identification compared with other methods, which can meet the needs of practical use.
Similar content being viewed by others
Data availability
Our homemade dataset contains 1360 different pest images with a total of 15,300 enhanced images, divided into a training set, a validation set, and a test set in a ratio of 8:1:1. The datasets used in the current study can be obtained from the corresponding authors upon reasonable request.
References
Elkhateeb, W.A., Mousa, K.M., ELnahas, M.O., Daba, G.M.: Fungi against insects and contrariwise as biological control models. Egypt. J. Biol. Pest Control 31(1), 1–9 (2021). https://doi.org/10.1186/s41938-020-00360-8
Arun, A.R., Umamaheswari, S.: Effective and efficient multi-crop pest detection based on deep learning object detection models. Intell. Fuzzy Syst. 43(4), 1–19 (2022)
Zhao, Zh.Q., Zheng, P., Xu, Sh.T., Wu, X.D.: Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3212–3232 (2019)
Stefopoulou, A., Maselou, D.A., Papachristos, D., Kolimenakis, A., Michaelakis, A., Athanassiou, C., Vlontzos, G.: Pest control in primary sector: towards the identification of knowledge gaps. Agronomy 11(8), 1596 (2021). https://doi.org/10.3390/agronomy11081596
Amrani, A., Sohel, F., Diepeveen, D., Murray, D., Jones, M.G.K.: Insect detection from imagery using YOLOv3-based adaptive feature fusion convolution network. Crop Pasture Sci. (2022). https://doi.org/10.1071/CP21710
Ding, W.J., Taylor, G.: Automatic moth detection from trap images for pest management. Comput. Electron. Agric. 123, 17–28 (2016). https://doi.org/10.1016/j.compag.2016.02.003
Liu, Z.Y., Gao, J.F., Yang, G.G., Zhang, H., He, Y.: Localization and classification of paddy field pests using a saliency map and deep convolutional neural network. Sci. Rep. 6(1), 1–12 (2016). https://doi.org/10.1038/srep20410
Song, L.M., Kang, J.W., Zhang, Q.L., Wang, Sh.P.: A weld feature points detection method based on improved YOLO for welding robots in strong noise environment. SIViP 16(8), 1–9 (2022). https://doi.org/10.1007/s11760-022-02391-0
Li, D., Ahmed, F., Wu, N., Sethi, A.I.: YOLO-JD: a deep learning network for jute diseases and pests detection from images. Plants 11(7), 937 (2022). https://doi.org/10.3390/plants11070937
Dong, S., Du, J., Jiao, L., Wang, F.M., Liu, K., Teng, Y., Wang, R.J.: Automatic crop pest detection oriented multiscale feature fusion approach. Insects 13(6), 554 (2022). https://doi.org/10.3390/insects13060554
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., Ali, F.: Yolov3: an incremental improvement. arXiv preprint (2018). https://arxiv.org/abs/1804.02767
Bochkovskiy, A., Wang, Ch.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint (2020). https://arxiv.org/abs/2004.10934
Wang, K., Jiang, P., Meng, J.: Attention-based DenseNet for pneumonia classification. IRBM. 43(5), 479–485 (2022). https://doi.org/10.1016/j.irbm.2021.12.004
Dong, C.X., Zhao, Y., Zhang, G., Xue, M.R., Chu, D., He, J.T., Ge, X.T.: Attention-based graph ResNet with focal loss for epileptic seizure detection. Ambient Intell. Smart Environ. 14(1), 61–73 (2022). https://doi.org/10.3233/AIS-210086
Das, H., Park, H.: MCU-less biphasic electrical stimulation circuit for miniaturized neuromodulator. Biomed. Eng. Lett. 12(3), 285–293 (2022). https://doi.org/10.1007/s13534-022-00239-7
Liu, Ch., Wang, XCh., Wu, Q.L., Jiang, J.B.: Light weight target detection algorithm based on YOLOv4. Real-Time Image Process. 19, 1123–1137 (2022)
He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015). https://doi.org/10.1109/TPAMI.2015.238
Fu, J., Chen, X., Lv, Z.: Rail fastener status detection based on MobileNet-YOLOv4. Electronics 11(22), 3677 (2022). https://doi.org/10.3390/electronics11223677
Ren, S.Q., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process Syst. (2015). https://doi.org/10.1109/TPAMI.2016.2577031
Vales, V.B., Fernández, O.C., Domínguez-Bolaño, T., Escudero, C.J., Garcia-Naya, J.A.: Fine time measurement for the Internet of things: a practical approach using ESP32. IEEE Internet Things J. 9(19), 18305–18318 (2022)
Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Computer Vision and Pattern Recognition, pp. 936–944 (2017)
Nayef, B.H., Abdullah, S.N.H.S., Sulaiman, R., Alyasseri, Z.A.A.: Optimized leaky ReLU for handwritten Arabic character recognition using convolution neural networks. Multimed. Tools Appl. 81(2), 2065–2094 (2022). https://doi.org/10.1007/s11042-021-11593-6
Dan, Z.J., Zhao, Y., Bi, X.J., Wu, L.C., Ji, Q.: Multi-task transformer with adaptive cross-entropy loss for multi-dialect speech recognition. Entropy 24(10), 1429 (2022). https://doi.org/10.3390/e24101429
Lin, T.Y., Goyal, P., Girshick, R.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. (2017). https://doi.org/10.1109/ICCV.2017.324
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 142–158 (2015). https://doi.org/10.1109/TPAMI.2015.2437384
Funding
This work was supported by the Program for Innovative Research Team in University of Tianjin (No. TD13-5036) and the Tianjin Science and Technology Popularization Project (No. 22KPXMRC00090).
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Song, L., Liu, M., Liu, S. et al. Pest species identification algorithm based on improved YOLOv4 network. SIViP 17, 3127–3134 (2023). https://doi.org/10.1007/s11760-023-02534-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-023-02534-x