Abstract
With the development of modern technology and the application of the times, the accuracy of high-resolution image target detection is gradually improved. In this paper, a multi feature extraction and multi feature fusion network is proposed for the loss function of feature extraction, feature fusion and uneven positive and negative samples. In order to solve the problem of multiple features in multi feature extraction, combined with the two-dimensional CA spatial attention mechanism and residual network, the global features are preserved and sensitive information extraction is strengthened; Aiming at the problem of feature redundancy in multi feature fusion, the improved bifpn structure is used to effectively solve the problem of feature redundancy after feature extraction; Aiming at the training model degradation caused by the imbalance of positive and negative samples, the focal loss function is improved to effectively solve the model degradation caused by samples. The improved multi feature extraction and multi feature fusion network effectively improves the accuracy of target detection. The improved algorithm has the highest accuracy in dota data set, and the test accuracy is 78.98%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fang, L., He, H., Zhou, G.A.: Survey of target detection algorithms. Comput. Eng. Appl. 54(13), 9 (2018)
Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., Smeulders, A.W.M.: Selective search for object recognition. Int. J. Comput. Vision 104(2), 154–171 (2013). https://doi.org/10.1007/s11263-013-0620-5
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM. 60, 84–90 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science (2014)
Huang, G., Liu, Z., Laurens, V., et al.: Densely connected convolutional networks. In: IEEE Computer Society (2016)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: IEEE (2016)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: IEEE Computer Society (2014)
Liu, B.: Research on Object Detection and Image Segmentation Based on Depth Learning in Traffic Scenes. Xi'an University of Electronic Science and Technology (2021)
Qin, H., Lei, X., Jiang, Z.: Traffic recognition of Huawei unmanned vehicle based on object detection Chinese stereology and image analysis. 26(03), 245–252 (2021)
Wang, X.: Design of intelligent control device for traffic lights based on Yolo v5 target detection algorithm highway traffic technology. 38(01), 142–148 (2022)
Xiao, Y., Yang, H.: Application of object detection algorithm in traffic scene. 57(06), 30–41 (2021)
An, Y.: Research on Ship Target Detection and Recognition in Naval Battlefield. Harbin Engineering University (2015)
Chen, C.: Research on Target Detection and Scene Recognition Technology of Image Intelligence Based on Convolutional Neural Network. National University of Defense Technology (2018)
Guo, H., Yu, L., Liu, Z.: An improved military target detection method based on YOLOv4. 41(06), 53–58 (2021)
Zhang, C.: Application electronic test of target detection technology based on military aircraft image and FCN. 10, 53–54+48 (2019)
Hong, M., Wu, G., Liu, X., et al.: Computer engineering and design of lung nodule detection algorithm based on attention mechanism. Comput. Eng. Des. 42(01), 83–88 (2021)
Liu, H.: Research on FCOS Based Improved 2.5D Lung CT Lesion Area Detection Algorithm. Jilin University (2021)
Long, K.: Small Target Detection and Segmentation in Medical Images. University of Electronic Science and Technology (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Beijing HIWING Sci. and Tech. Info Inst
About this paper
Cite this paper
Zhang, Z., Sun, W., Song, Z. (2023). High Precision Target Detection Algorithm Based on Dual Channel Attention Perception Fusion. In: Fu, W., Gu, M., Niu, Y. (eds) Proceedings of 2022 International Conference on Autonomous Unmanned Systems (ICAUS 2022). ICAUS 2022. Lecture Notes in Electrical Engineering, vol 1010. Springer, Singapore. https://doi.org/10.1007/978-981-99-0479-2_114
Download citation
DOI: https://doi.org/10.1007/978-981-99-0479-2_114
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0478-5
Online ISBN: 978-981-99-0479-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)