Abstract
Moving object detection is still a challenging task in complex scenes. The existing methods based on deep learning mainly use U-Nets and have achieved amazing results. However, they ignore the local continuity between pixels. In order to solve this problem, a method based on a superpixel fusion network (SF-Net) is proposed in this article. First, the median filter is used to extract the candidate foreground (called pixel features) and the image sequence is segmented by superpixel. Then, the histogram features (called superpixel features) of the candidate foreground superpixels are extracted. Next, the pixel features and the superpixel features are the inputs of SF-Net, respectively. Experiments show the effectiveness of SF-Net on 34 image sequences and the average F-measure reaches 0.84. SF-Net can remove more background noise and has stronger expression ability than a network with the same depth.
- [1] . 2018. BSCGAN: Deep background subtraction with conditional generative adversarial networks. International Conference on Image Processing (ICIP’18). IEEE, Athens, 4018–4022.Google Scholar
Cross Ref
- [2] . 2010. ViBe: A universal background subtraction algorithm for video sequences. IEEE Transactions on Image Processing 20, 6 (2010), 1709–1724.Google Scholar
Digital Library
- [3] . 2020. Moving object detection under different weather conditions using full-spectrum light sources. Pattern Recognition Letters 129 (2020), 205–212.Google Scholar
Cross Ref
- [4] . 2011. Recent advanced statistical background modeling for foreground detection: A systematic survey. Recent Patents on Computer Science 4, 3 (2011), 147–176.Google Scholar
- [5] . 2011. Robust principal component analysis? Journal of the ACM 58, 3 (2011), 1–37.Google Scholar
Digital Library
- [6] . 2022. Enhanced the moving object detection and object tracking for traffic surveillance using RBF-FDLNN and CBF algorithm. Expert Systems with Applications 191 (2022), 116306.Google Scholar
Digital Library
- [7] . 2017. Spatiotemporal GMM for background subtraction with superpixel hierarchy. IEEE Transactions on Pattern Analysis and Machine Intelligence 40, 6 (2017), 1518–1525.Google Scholar
Cross Ref
- [8] . 2000. Non-parametric model for background subtraction. European Conference on Computer Vision. Springer, Berlin, Heidelberg, 751–767.Google Scholar
Digital Library
- [9] . 2018. Background subtraction based on random superpixels under multiple scales for video analytics. IEEE Access 6 (2018), 33376–33386.Google Scholar
Cross Ref
- [10] . 2020. Change detection based on tensor RPCA for longitudinal retinal fundus images. Neurocomputing 387 (2020), 1–12.Google Scholar
Digital Library
- [11] . 2016. Superpixel convolutional networks using bilateral inceptions. In European Conference on Computer Vision. Springer, Amsterdam, 597–613.Google Scholar
Cross Ref
- [12] . 2015. Superpixel-based video object segmentation using perceptual organization and location prior. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, MA, 4814–4822.Google Scholar
Cross Ref
- [13] . 2022. Graph moving object segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 5 (2022), 2485–2503.Google Scholar
- [14] . 2021. Graph CNN for moving object detection in complex environments from unseen videos. International Conference on Computer Vision Workshops (ICCVW), Montreal, BC, 225–233.Google Scholar
- [15] . 2017. An efficient motion detection and tracking scheme for encrypted surveillance videos. ACM Transactions on Multimedia Computing, Communications, and Applications 13, 4 (2017), 1–23.Google Scholar
Digital Library
- [16] . 2015. SuperCNN: A superpixelwise convolutional neural network for salient object detection. International Journal of Computer Vision 115, 3 (2015), 330–344.Google Scholar
Digital Library
- [17] . 2012. Background segmentation with feedback: The pixel-based adaptive segmenter. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. IEEE, Providence, RI, 38–43.Google Scholar
Cross Ref
- [18] . 2020. A super-fast deep network for moving object detection. In 2020 IEEE International Symposium on Circuits and Systems (ISCAS’20), IEEE, Seville, 1–5.
DOI: Google ScholarCross Ref
- [19] . 2021. A fast lightweight 3D separable convolutional neural network with multi-input multi-output for moving object detection. IEEE Access 9 (2021), 148433–148448.Google Scholar
Cross Ref
- [20] . 2018. SWCD: A sliding window and self-regulated learning-based background updating method for change detection in videos. Journal of Electronic Imaging 27, 2 (2018), 023002.Google Scholar
Cross Ref
- [21] . 2018. Superpixel sampling networks. In Proceedings of the European Conference on Computer Vision (ECCV’18), Springer, Munich, 352–368.Google Scholar
Digital Library
- [22] . 2015. Background subtraction via superpixel-based online matrix decomposition with structured foreground constraints. In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW). IEEE, Santiago, 930–938.Google Scholar
Digital Library
- [23] . 2018. Moving object detection in complex scene using spatiotemporal structured-sparse RPCA. IEEE Transactions on Image Processing 28, 2 (2018), 1007–1022.Google Scholar
Digital Library
- [24] . 2017. Superpixels based manifold structured sparse RPCA for moving object detection. In International Workshop on Activity Monitoring by Multiple Distributed Sensing (BMVC’17). BMVA Press, London, 1–13.Google Scholar
- [25] . 2020. CS-RPCA: Clustered sparse RPCA for moving object detection. In 2020 IEEE International Conference on Image Processing (ICIP’20). IEEE, Abu Dhabi, 3209–3213.Google Scholar
Cross Ref
- [26] . 2018. Robust PCA and robust subspace tracking: A comparative evaluation. In 2018 IEEE Statistical Signal Processing Workshop (SSP’18), IEEE, Freiburg im Breisgau, 836–840.Google Scholar
- [27] . 2019. Moving object detection based on smoothing three frame difference method fused with RPCA. Multimedia Tools and Applications 78, 21 (2019), 29937–29951.Google Scholar
Digital Library
- [28] . 2021. Background subtraction for moving object detection: Explorations of recent developments and challenges. The Visual Computer (2021), 1–28.Google Scholar
- [29] . 2007. Segmentation and recognition of motion streams by similarity search. ACM Transactions on Multimedia Computing, Communications, and Applications 3, 3 (2007), 16–es.Google Scholar
Digital Library
- [30] . 2022. Moving object detection for unseen videos via truncated weighted robust principal component analysis and salience convolution neural network. Multimedia Tools and Applications (2022), 1–12.Google Scholar
- [31] . 2019. Moving object detection via segmentation and saliency constrained RPCA. Neurocomputing 323 (2019), 352–362.Google Scholar
Cross Ref
- [32] . 2018. Combination of local binary pattern operator with sample consensus model for moving objects detection. Infrared Physics and Technology 92 (2018), 44–52.Google Scholar
Cross Ref
- [33] Y. Yang, A. Loquercio, D. Scaramuzza, and S. Soatto. 2019. Unsupervised moving object detection via contextual information separation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Long Beach, CA, 879–888.Google Scholar
- [34] . 2018. Foreground segmentation using convolutional neural networks for multiscale feature encoding. Pattern Recognition Letters 112 (2018), 256–262.Google Scholar
Cross Ref
- [35] . 2021. Residual refinement network with attribute guidance for precise saliency detection. ACM Transactions on Multimedia Computing, Communications, and Applications 17, 3 (2021), 1–19.Google Scholar
Digital Library
- [36] . 2018. Deep learning and superpixel feature extraction based on contractive autoencoder for change detection in SAR images. IEEE transactions on industrial informatics 14, 12 (2018), 5530–5538.Google Scholar
Cross Ref
- [37] . 2021. 3DCD: Scene independent end-to-end spatiotemporal feature learning framework for change detection in unseen videos. IEEE Transactions on Image Processing 30 (2021), 546–558.Google Scholar
Digital Library
- [38] . 2022. An empirical review of deep learning frameworks for change detection: Model design, experimental frameworks, challenges and research needs. IEEE Transactions on Intelligent Transportation Systems 23, 7 (2022), 6101–6122.Google Scholar
Digital Library
- [39] . 2020. Rethinking background and foreground in deep neural network-based background subtraction. IEEE International Conference on Image Processing (ICIP’20), IEEE, Abu Dhabi, 3229–3233.Google Scholar
Cross Ref
- [40] . 2018. Analytics of deep neural network-based background subtraction. Journal of Imaging 4, 6 (2018), 78.Google Scholar
Cross Ref
- [41] . 2021. Fast background subtraction with adaptive block learning using expectation value suitable for real-time moving object detection. Journal of Real-Time Image Processing 18, 3 (2021), 967–981.Google Scholar
Digital Library
- [42] . 2018. MSFgNet: A novel compact end-to-end deep network for moving object detection. IEEE Transactions on Intelligent Transportation Systems 20, 11 (2018), 4066–4077.Google Scholar
Cross Ref
- [43] . 2018. MsEDNet: Multi-scale deep saliency learning for moving object detection. In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC’18). IEEE, Miyazaki, 1670–1675.Google Scholar
Digital Library
- [44] . 2022. An improved statistical approach for moving object detection in thermal video frames. Multimedia Tools and Applications 81, 7 (2022), 9289–9311.Google Scholar
Digital Library
- [45] . 1999. Adaptive background mixture models for real-time tracking. In Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), IEEE, Fort Collins, CO, 246–252.Google Scholar
Cross Ref
- [46] . 2020. Unsupervised moving object detection in complex scenes using adversarial regularizations. IEEE Transactions on Multimedia 23 (2020), 2005–2018.Google Scholar
Cross Ref
- [47] . 2008. An improved adaptive background modeling algorithm based on Gaussian Mixture Model. In 9th International Conference on Signal Processing. IEEE, Beijing, 1436–1439.Google Scholar
- [48] . 2020. BSUV-Net: A fully-convolutional neural network for background subtraction of unseen videos. IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, Snowmass, CO, 2763–2772.Google Scholar
- [49] . 2014. CDnet 2014: An expanded change detection benchmark dataset. IEEE Conference on Computer Vision and Pattern Recognition Workshops, IEEE, Columbus, OH, 393–400.Google Scholar
Digital Library
- [50] . 2021. Visual attention and background subtraction with adaptive weight for hyperspectral anomaly detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14 (2021), 2270–2283.Google Scholar
Cross Ref
- [51] . 2019. Unsupervised moving object detection via contextual information separation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Long Beach, CA, 879–888.Google Scholar
Cross Ref
- [52] . 2017. Saliency detection on light field: A multi-cue approach. ACM Transactions on Multimedia Computing, Communications, and Applications 13, 3 (2017), 1–22.Google Scholar
Digital Library
- [53] . 2021. Meta-knowledge learning and domain adaptation for unseen background subtraction. IEEE Transactions on Image Processing 30 (2021), 9058–9068.Google Scholar
Digital Library
- [54] . 2016. Background subtraction based on superpixels under multi-scale in complex scenes. In Chinese Conference on Pattern Recognition. Springer, Chendu, 392–403.Google Scholar
Cross Ref
- [55] . 2018. FLIC: Fast linear iterative clustering with active search. Computational Visual Media 4, 4 (2018), 333–348.Google Scholar
Cross Ref
- [56] . 2020. Motion-aware structured matrix factorization for foreground detection in complex scenes. ACM Transactions on Multimedia Computing, Communications, and Applications 16, 4 (2020), 1–23.Google Scholar
Digital Library
Index Terms
(auto-classified)Detection of Moving Object Using Superpixel Fusion Network
Recommendations
Moving Object Detection for Moving Cameras on Superpixel Level
ICIG '13: Proceedings of the 2013 Seventh International Conference on Image and GraphicsIn this paper, we will present a novel algorithm for detecting moving objects from relatively dynamic background in particular video sequences. To achieve our goal, we introduced a new conception called "feature super pixel". As is well known, by ...
Superpixel-Based Segmentation of Glioblastoma Multiforme from Multimodal MR Images
Proceedings of Third International Workshop on Multimodal Brain Image Analysis - Volume 8159Due to complex imaging characteristics such as large diversity in shapes and appearances combining with deformation of surrounding tissues, it is a challenging task to segment glioblastoma multiforme (GBM) from multimodal MR images. In particular, it is ...
Aerial Image Object Detection Based on Superpixel-Related Patch
Image and GraphicsAbstractAerial image object detection and recognition has attracted increasing attention in recent years. Many excellent detectors have been proposed. However, due to the high-resolution of aerial images, these detectors are difficult to directly apply to ...






Comments