MSFgNet: A Novel Compact End-to-End Deep Network for Moving Object Detection

Patil, Prashant W.; Murala, Subrahmanyam

doi:10.1109/tits.2018.2880096

Cited by 90 publications

(41 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. The results also show the potential of 3D convolution over 2D convolution [16][17][18][19][20][21][22]25] in designing deep networks for change detection in videos.…”

Section: B Results and Discussionmentioning

confidence: 73%

“…This intuitive approach helps the model to learn the underlying problem of change detection. Therefore, our model performs [24] Temporal Division No Yang et al [26] Temporal Division No Babaee et al [21] Temporal Division No Nguyen et al [20] Random Division No Lin et al [16] Leave-one-video-out Yes Lim et al [17] Selective Division No Zeng et al [18] Random Division No Lim et al [19] Leave-one-video-out No Bakkay et al [27] Temporal Division No Brahman et al [22] Temporal Division No Patil and Murala [25] Random Division No Proposed 3DFR…”

Section: E Analysis Of 3dfr Networkmentioning

confidence: 99%

“…The CNN based methods for change detection in the literature [16][17][18][19][20][21][22][23][24][25][26][27] have evaluated their models in various train-test divisions without properly ensuring scene independence. For example, the most commonly adopted scheme is to divide the frame sequences from a single video into training and testing group with certain temporal proportions (50%-50% [22,24,27], 90%-10% [26]).…”

Section: A Need For Scene Independent Evaluation In Deep Learningmentioning

confidence: 99%

“…Moreover, the abovementioned supervised learning methods [16][17][18][19][20][21][22][23][24][25][26][27] By scene independence, we mean that the train set should not contain partial data of the videos used in the test set. The intuition behind this is that the background remains more or less similar in the entire video sequences.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection

Mandal

Dhar

Mishra

et al. 2019

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

In this paper we propose an end-to-end swift 3D feature reductionist framework (3DFR) for scene independent change detection. The 3DFR framework consists of three feature streams: a swift 3D feature reductionist stream (AvFeat), a contemporary feature stream (ConFeat) and a temporal median feature map. These multilateral foreground/background features are further refined through an encoder-decoder network. As a result, the proposed framework not only detects temporal changes but also learns high-level appearance features. Thus, it incorporates the object semantics for effective change detection. Furthermore, the proposed framework is validated through a scene independent evaluation scheme in order to demonstrate the robustness and generalization capability of the network. The performance of the proposed method is evaluated on the benchmark CDnet 2014 dataset. The experimental results show that the proposed 3DFR network outperforms the state-of-the-art approaches.

show abstract

“…2. The results also show the potential of 3D convolution over 2D convolution [16][17][18][19][20][21][22]25] in designing deep networks for change detection in videos.…”

Section: B Results and Discussionmentioning

confidence: 73%

Section: E Analysis Of 3dfr Networkmentioning

confidence: 99%

Section: A Need For Scene Independent Evaluation In Deep Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection

Mandal

Dhar

Mishra

et al. 2019

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

show abstract

“…MOG [11] GMM [12] KNN [13] SBS [17] SuperBE [18] MOG2 [26] Cuevas [27] Berjón [28] Haines [29] SC-SOBS [30] WNN [31] CNN [32] DeepBS [33] RB-SOM [34] MSFgNet [35] MS-ST [36] BMN-BSN [37] FIGURE 2. A taxonomy of background subtraction-based moving object detection approach.…”

Section: Prior Workmentioning

confidence: 99%

Fast-D: When Non-Smoothing Color Feature Meets Moving Object Detection in Real-Time

2020

View full text Add to dashboard Cite

The moving object detection refers to the detection of physical moving objects from a video, which is applied in video surveillance, object recognition, object counting, human-computer interaction, and so on. Moreover, nowadays, real-time moving object detection is used as services in the cloud, edge, and fog computing. However, the existing methods do not meet the trade-off between accuracy and complexity. To address these issues, we present a background subtraction-based moving object detection method, called Fast-D. In this paper, we look at the 'non-smoothing color feature' to make the moving object detection more robust in real-time. Each color feature is given equal significance during the classification of a pixel. Background model and threshold are initialized for each pixel. And then, the background model and threshold are updated dynamically when there are changes in the background of the video. Adaptive post-processing is considered to discard salt and pepper noise and fill holes in the detected moving object silhouettes. The evaluation of our proposed method on four complex datasets exhibits the significance. INDEX TERMS Real-time moving object detection, background subtraction, object segmentation, change detection.

show abstract

Dense Haze Removal Using Convolution Neural Network

Dongare¹,

Kendule²

2021

Techno-Societal 2020

View full text Add to dashboard Cite

MSFgNet: A Novel Compact End-to-End Deep Network for Moving Object Detection

Cited by 90 publications

References 42 publications

3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection

3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection

Fast-D: When Non-Smoothing Color Feature Meets Moving Object Detection in Real-Time

Dense Haze Removal Using Convolution Neural Network

Contact Info

Product

Resources

About