research-article

Complex object detection using deep proposal mechanism

Author:

Juan TanAuthors Info & Claims

Volume 87, Issue C

https://doi.org/10.1016/j.engappai.2019.09.003

Published: 01 January 2020 Publication History

Abstract

Complex object detection is one of the most important and challenging problems in computer vision tasks. To provide a high-performance complex object detection method, a deep proposal mechanism (DPM) is proposed. (1) A region proposal strategy is used to localize potential objects in most top methods; however, this process also represents an intractable computational bottleneck. Therefore, to localize potential complex effectively, a region proposal mechanism (RPM) is proposed. The mechanism shares common features with ResNet and achieves excellent performance. (2) To solve the problem of insufficient amount of labeled training data, an efficient semisupervised pretraining method, instead of traditional unsupervised pretraining, is carried out. (3) To further improve the computational speed, a novel joint learning strategy is introduced. Extensive experiments are performed, and the results show that DPM achieves much better performance than state-of-the-art methods.

References

[1]

Chen X., Kundu K., Zhu Y., et al., 3D object proposals using stereo imagery for accurate object class detection, IEEE Trans. Pattern Anal. Mach. Intell. 40 (5) (2018) 1259–1272.

[2]

Cheng Gong, Zhou Peicheng, Han Junwei, Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images, IEEE Trans. Geosci. Remote Sensing 54 (12) (2016) 7405–7415.

[3]

Dhiman Chhavi, Kumar Dinesh, Vishwakarma, A review of state-of-the-art techniques for abnormal human activity recognition, Eng. Appl. Artif. Intell. 77 (2019) 21–45.

[4]

Dou H., Wu X., Coarse-to-fine trained multi-scale convolutional neural networks for image classification, in: International Joint Conference on Neural Networks, IEEE, 2015, pp. 1–7.

[5]

Guo F., Wang W., Shen J., et al., Video saliency detection using object proposals, IEEE Trans. Cybern. 48 (11) (2017) 3159–3170.

[6]

He, K., Zhang, X., Ren, S., et al., Deep residual learning for image recognition, 2015.

[7]

Hinton, G.E., Krizhevsky, A., Wang, S.D., Transforming auto-encoders, in: 2011 International Conference on Artificial Neural Networks, 2011, pp. 44–51.

[8]

Jia Y., Shelhamer E., Donahue J., et al., Caffe: Convolutional architecture for fast feature embedding, in: ACM International Conference on Multimedia, ACM, 2014, pp. 675–678.

[9]

Juan C.P., Beatriz P., Sparse matrix classification on imbalanced datasets using convolutional neural networks, IEEE Access (7) (2019) 82377–82389.

[10]

Ko Kwang-Eun, Sim Kwee-Bo, Deep convolutional framework for abnormal behavior detection in a smart surveillance system, Eng. Appl. Artif. Intell. 67 (2018) 226–234.

[11]

Koh Y.J., Kim C.S., Unsupervised primary object discovery in videos based on evolutionary primary object modeling with reliable object proposals, IEEE Trans. Image Process. 26 (11) (2017) 5203–5216.

[12]

Kurakin, A., Goodfellow, I., Bengio, S., Adversarial examples in the physical world, 2016, arXiv preprint arXiv:1607.02533.

[13]

Liu Y., Liu S., Wang Y., et al., A stochastic computational multi-layer perceptron with backward propagation, IEEE Trans. Comput. 67 (9) (2018) 1273–1286.

Digital Library

[14]

Liu Y., Sioshansi R., Conejo A., Multistage stochastic investment planning with multiscale representation of uncertainties and decisions, IEEE Trans. Power Syst. 33 (1) (2018) 781–791.

[15]

Liu H., Wu J., Liu T., et al., Spectral ensemble clustering via weighted k-means: Theoretical and practical evidence, IEEE Trans. Knowl. Data Eng. 29 (5) (2017) 1129–1143.

Digital Library

[16]

Long J., Shelhamer E., Darrell T., Fully convolutional networks for semantic segmentation, IEEE Trans. Pattern Anal. Mach. Intell. 39 (4) (2017) 640–651.

Digital Library

[17]

Oord, A.V.D., Kalchbrenner, N., Kavukcuoglu, K., Pixel recurrent neural networks, 2016, arXiv preprint arXiv:1601.06759.

[18]

Pinheiro P.O., Collobert R., Dollar P., Learning to segment object candidates, Comput. Sci. (2015).

[19]

Pont-Tuset J., Arbelaez P., Barron J., et al., Multiscale combinatorial grouping for image segmentation and object proposal generation, IEEE Trans. Pattern Anal. Mach. Intell. 39 (2016) 1.

[20]

Russakovsky O., Deng J., Su H., et al., Imagenet large scale visual recognition challenge, Int. J. Comput. Vis. 115 (3) (2015) 211–252.

Digital Library

[21]

Sermanet, P., Eigen, D., Zhang, X., et al., OverFeat: Integrated recognition, localization and detection using convolutional networks, 2013, Eprint Arxiv.

[22]

Tang Y., Wang X., Dellandrea E., et al., Weakly supervised learning of deformable part-based models for object detection via region proposals, IEEE Trans. Multimed. 19 (2) (2017) 393–407.

Digital Library

[23]

Uijlings J.R.R., Sande K.E.A.V.D., Gevers T., et al., Selective search for object recognition, Int. J. Comput. Vis. 104 (2) (2013) 154–171.

Digital Library

[24]

Vicente S., Carreira J., Agapito L., et al., Reconstructing PASCAL VOC, in: Computer Vision and Pattern Recognition, IEEE, 2014, pp. 41–48.

[25]

Wu Di, Pigou Lionel, Kindermans Pieter-Jan, et al., Deep dynamic neural networks for multimodal gesture segmentation and recognition, IEEE Trans. Pattern Anal. Mach. Intell. 8 (38) (2016) 1583–1597.

[26]

Zhang Ansi, Li Shaobo, Cui Yuxin, et al., Limited data rolling bearing fault diagnosis with few-shot learning, IEEE Access 7 (2019) 110895–110904.

[27]

Zhao P., Zhu H., Li H., et al., A directional-edge-based real-time object tracking system employing multiple candidate-location generation, IEEE Trans. Circuits Syst. Video Technol. 23 (3) (2013) 503–517.

[28]

Zitnick C.L., Dollár P., Edge boxes: Locating object proposals from edges, Computer Vision – ECCV 2014, Springer International Publishing, 2014, pp. 391–405.

Cited By

Yu HLiu XQin HYang LChen Y(2022)Automatic Detection of Peeled Shrimp Based on Image Enhancement and Convolutional Neural NetworksProceedings of the 8th International Conference on Computing and Artificial Intelligence10.1145/3532213.3532279(439-450)Online publication date: 18-Mar-2022
https://dl.acm.org/doi/10.1145/3532213.3532279

Index Terms

Complex object detection using deep proposal mechanism
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Object recognition
      2. Computer vision tasks
        Scene understanding
  2. Machine learning

Index terms have been assigned to the content through auto-classification.

Recommendations

Weakly Supervised Region Proposal Network and Object Detection
Computer Vision – ECCV 2018
Abstract
The Convolutional Neural Network (CNN) based region proposal generation method (i.e. region proposal network), trained using bounding box annotations, is an essential component in modern fully supervised object detectors. However, Weakly ...
Object detection with class aware region proposal network and focused attention objective
Highlights
- The paper proposes the CARPN method to produce high-quality region proposals for object detection.
Abstract
In this paper, we propose a novel deep CNN-based framework to improve object detection performance. First, we introduce the Class Aware Region Proposal Network (CARPN) to produce high quality region proposals by using a new strategy ...
Edge-preserving image denoising using a deep convolutional neural network
Highlights
- This paper makes use of a deep CNN for image denoising.
- The network is trained ...
Abstract
This paper introduces a novel denoising approach making use of a deep convolutional neural network to preserve image edges. The network is trained by using the edge map obtained from the well-known Canny algorithm and aims at ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Engineering Applications of Artificial Intelligence

Engineering Applications of Artificial Intelligence Volume 87, Issue C

Jan 2020

758 pages

ISSN:0952-1976

Issue’s Table of Contents

Copyright © 2019.

Publisher

Pergamon Press, Inc.

United States

Publication History

Published: 01 January 2020

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 10 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Yu HLiu XQin HYang LChen Y(2022)Automatic Detection of Peeled Shrimp Based on Image Enhancement and Convolutional Neural NetworksProceedings of the 8th International Conference on Computing and Artificial Intelligence10.1145/3532213.3532279(439-450)Online publication date: 18-Mar-2022
https://dl.acm.org/doi/10.1145/3532213.3532279

View Options

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.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents