An efficient object detection framework with modified dense connections for small objects optimizations
Pages 174 - 181
Abstract
Object detection frameworks for small objects are increasingly demanded in some specific fields such as high-speed object tracking and remote sensing image recognition. In this paper, we propose an efficient object detection framework with modified dense connections for small objects. In order to improve both the detection accuracy and speed for small objects, the proposed framework constructs a convolutional neural network by using modified dense and residual cross-layer connections between multi-scale convolutional layers to extract deep features effectively. Based on the modified dense structure, a hybrid-scale feature fusion method is proposed to concatenate the multi-channel high-dimensional features and performs cross-entropy calculation and regression prediction. By using this method, this framework not only improves the detection accuracy for small objects significantly, but also improves the overall detection accuracy and optimizes the network parameters to reduce the detection time greatly. The experimental results show that the proposed framework achieves 90.6% mAP for small objects on a public ship dataset which is 25.2% more than SSD-VGGNet. Due to the detection efficiency for small objects, it improves the overall detection accuracy and detection speed by 9% and 40% respectively while about 70% network parameters are reduced.
References
[1]
T. Chen, M. Li, Y. Li, M. Lin, N. Wang, M. Wang, T. Xiao, B. Xu, C. Zhang, and Z. Zhang. 2015. MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. arXiv:preprint arXiv:1512.01274
[2]
R. Girshick. 2015. Fast R-CNN. In IEEE International Conference on Computer Vision (ICCV). 1440--1448.
[3]
R. Girshick, J. Donahue, T. Darrell, and J. Malik. 2014. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 580--587.
[4]
K. He, X. Zhang, and S. Ren. 2016. Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778.
[5]
A. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv:arXiv preprint arXiv:1704.04861
[6]
G. Huang, Z. Liu, L. Maaten, and K. Weinberger. 2017. Densely Connected Convolutional Networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 4700--4708.
[7]
S. Ioffe and C. Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In International Conference on Machine Learning (ICML). 448--456.
[8]
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Fuand, and A. Berg. 2016. SSD: Single Shot MultiBox Detector. In European Conference on Computer Vision (ECCV). 21--37.
[9]
Z. Liu, J. Hu, L. Weng, and Y. Yang. 2017. Rotated Region Based CNN for Ship Detection. In IEEE International Conference on Image Processing (ICIP). 900--904.
[10]
V. Nair and G. Hinton. 2010. Rectified Linear Units Improve Restricted Boltzmann Machines. In International Conference on Machine Learning (ICML). 807--814.
[11]
M. Rahman and Y. Wang. 2016. Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation. In Advances in Visual Computing. 234--244.
[12]
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 779--788.
[13]
J. Redmon and A. Farhadi. 2017. YOLO9000: Better, Faster, Stronger. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7263--7271.
[14]
S. Ren, K. He, R. Girshick, and J. Sun. 2017. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 6 (June 2017), 1137--1149.
[15]
R. Rothe, M. Guillaumin, and G. Van. 2014. Non-Maximum Suppression for Object Detection by Passing Messages Between Windows. In Asian Conference on Computer Vision (ACCV). 290--306.
[16]
K. Simonyan and A. Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:arXiv preprint arXiv:1409.1556
[17]
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research 15, 56 (2014), 1929--1958.
[18]
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. 2015. Going Deeper with Convolutions. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1--9.
Index Terms
- An efficient object detection framework with modified dense connections for small objects optimizations
Recommendations
Small Object Detection Using Deep Feature Pyramid Networks
Advances in Multimedia Information Processing – PCM 2018AbstractRecent studies have achieved great progress on the object detection in terms of accuracy and speed using convolutional neural networks (CNNs). However, no matter the one-stage detector or the two-stage detector, usually it is still a challenging ...
Multi-scale Feature Fusion Single Shot Object Detector Based on DenseNet
Intelligent Robotics and ApplicationsAbstractSSD (Single Shot Multibox Detector) is one of advanced object detection methods and apparently can detect objects with high accuracy and fast speed. However, detecting small objects accurately remains a problem full of challenges for SSD. To ...
CNN-based single object detection and tracking in videos and its application to drone detection
AbstractThis paper presents convolutional neural network (CNN)-based single object detection and tracking algorithms. CNN-based object detection methods are directly applicable to static images, but not to videos. On the other hand, model-free visual ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
May 2020
298 pages
ISBN:9781450379564
DOI:10.1145/3387902
- General Chairs:
- Maurizio Palesi,
- Gianluca Palermo,
- Program Chairs:
- Cat Graves,
- Eishi Arima
Copyright © 2020 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]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 23 May 2020
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Tsinghua University Initiative Scientific Research Program
- China Postdoctoral Science Foundation
Conference
CF '20
Sponsor:
Acceptance Rates
Overall Acceptance Rate 273 of 785 submissions, 35%
Upcoming Conference
CF '25
- Sponsor:
- sigmicro
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 191Total Downloads
- Downloads (Last 12 months)16
- Downloads (Last 6 weeks)2
Reflects downloads up to 21 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in