AMDet: An Efficient Infrared Small Object Detection Model Based on Visual Attention and Multi-dilation Feature
Pages 130 - 135
Abstract
Infrared small object detection had made many breakthroughs in early warning systems, precision-guided weapons, and maritime surveillance systems. However, infrared small object occupies less pixels and lacks color, shape and texture features, which makes infrared small object detection a challenging subject. In order to improve the detection performance of infrared small object, a novel algorithm (i.e., AMDet) based on visual attention and multi-dilation feature is proposed in this paper. First, Darknet53 is employed as the backbone of the AMDet. In addition, the attention refining module is proposed to enhance the ability of fine-grained feature extraction by utilizing the global context information. Furthermore, the multi-scale dilated convolution module is designed by expanding the receptive field of feature map, to characterize the multi-scale information, thus can further improve the feature expression ability of infrared small object. Experiment results on infrared small object detection dataset demonstrate that our method is superior to the other methods in detection accuracy, and is more applicable for infrared small object detection in sophisticated background.
References
[1]
Vaishnavi R, Unnikrishnan G. 2019. Implementation of algorithms for Point target detection and tracking in Infrared image sequences. In International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT). IEEE, 904-909.
[2]
Zhao P, Cui S. 2016. An improved weak light detector used for infrared Imaging guidance system. Optik - International Journal for Light and Electron Optics 127(4), 2316-2318.
[3]
Jiang Y, Deng L, and Zang P. 2011. Developmental State and Technical Features of American Space-Based Infrared Early Warning System.Journal of Air Force Radar Academy.
[4]
Ciurczak E W, Igne B. 2014. Pharmaceutical and medical applications of near-infrared spectroscopy. CRC Press.
[5]
Tanino K, Willick I R, and Hamilton K. 2017. Chemotyping using synchrotron midinfrared and X-ray spectroscopy to improve agricultural production. Canadian Journal of Plant Science 97(6), 982-996.
[6]
Johnson J B. 2020. An overview of near-infrared spectroscopy (NIRS) for the detection of insect pests in stored grains. Journal of Stored Products Research 86101558.
[7]
Hua L, Shao G. 2017. The progress of operational forest fire monitoring with infrared remote sensing. Journal of forestry research 28(2), 215-229.
[8]
Marvasti F S, Mosavi M R, and Nasiri M. 2018. Flying small object detection in IR images based on adaptive toggle operator. IET Computer Vision 12(4), 527-534.
[9]
Anju T S, Raj N R N. 2016. Shearlet transform based image denoising using histogram thresholding. In: International Conference on Communication Systems and Networks (ComNet). IEEE, 162-166.
[10]
Wei Y, You X, and Li H. 2016. Multiscale patch-based contrast measure for small infrared object detection. Pattern Recognition 58, 216-226.
[11]
He Y J, Li M, and Zhang J L. 2015. Small infrared object detection based on low-rank and sparse representation. Infrared Physics & Technology 68, 98-109.
[12]
Wang K, Li S, and Niu S. 2019. Detection of infrared small targets using feature fusion convolutional network. IEEE Access 7, 146081-146092.
[13]
Liangkui L I N, Shaoyou W, and Zhongxing T. 2018. Using deep learning to detect small targets in infrared oversampling images. Journal of Systems Engineering and Electronics 29(5), 947-952.
[14]
Sinn Y U, Hopkinson K M, and Borghetti B J. 2019. IR small target detection and prediction with ANNs trained using ASSET. In 2019 IEEE Aerospace Conference. IEEE, 1-11.
[15]
Dai Y, Wu Y, and Zhou F. 2021. Asymmetric Contextual Modulation for Infrared Small Target Detection. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 950-959.
[16]
Redmon J, Farhadi A. 2018. Yolov3: An incremental improvement.
[17]
Li C, Wang R, and Li J. 2020. Face detection based on YOLOv3. Recent Trends in Intelligent Computing, Communication and Devices. Springer, Singapore, 277-284.
[18]
Zhang X, Zhu X. 2019. Vehicle Detection in the aerial infrared images via an improved YOLOv3 network. In: 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP). IEEE, 372-376.
[19]
Yi Z, Yongliang S, and Jun Z. 2019. An improved tiny-yolov3 pedestrian detection algorithm. 183, 17-23.
[20]
Chen L C, Papandreou G, and Kokkinos I. 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence 40(4), 834-848.
[21]
Dai Y, Wu Y, and Zhou F. 2021. Asymmetric Contextual Modulation for Infrared Small Object Detection. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 950-959.
[22]
Cao C, Wang B, and Zhang W. 2019. An improved faster R-CNN for small object detection. IEEE Access 7, 106838-106846.
[23]
Duan K, Bai S, and Xie L. 2019. Centernet: Keypoint triplets for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. 6569-6578.
[24]
Bochkovskiy A, Wang C Y, and Liao H Y M. 2020. Yolov4: Optimal speed and accuracy of object detection. 10934.
Index Terms
- AMDet: An Efficient Infrared Small Object Detection Model Based on Visual Attention and Multi-dilation Feature
Index terms have been assigned to the content through auto-classification.
Recommendations
UEFPN: Unified and Enhanced Feature Pyramid Networks for Small Object Detection
Object detection models based on feature pyramid networks have made significant progress in general object detection. However, small object detection is still a challenge for the existing models. In this paper, we think that two factors in the existing ...
Attentional feature pyramid network for small object detection
AbstractRecent state-of-the-art detectors generally exploit the Feature Pyramid Networks (FPN) due to its advantage of detecting objects at different scales. Despite significant advances in object detection owing to the design of feature ...
Improving small object detection via context-aware and feature-enhanced plug-and-play modules
AbstractDetecting small objects is a challenging task in computer vision due to the objects only occupying a limited number of pixels and having blurred contours. These factors result in minimal discriminative features being available to effectively model ...
Comments
Information & Contributors
Information
Published In
October 2021
393 pages
ISBN:9781450390439
DOI:10.1145/3497623
Copyright © 2021 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 04 February 2022
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICCPR '21
ICCPR '21: 2021 10th International Conference on Computing and Pattern Recognition
October 15 - 17, 2021
Shanghai, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 57Total Downloads
- Downloads (Last 12 months)18
- Downloads (Last 6 weeks)1
Reflects downloads up to 26 Jul 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format