Semantic background subtraction

Braham, Marc; Pierard, Sébastien; Droogenbroeck, Marc Van

doi:10.1109/icip.2017.8297144

Cited by 101 publications

(81 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Quantitative Evaluation: Firstly, to demonstrate one of our key contribution, the proposed RTSS framework is preferable to the method presented in [17] by taking a semantic segmentation as a post-processing operation to refine the BGS segmentation result (we call this algorithm SemanticBGS), in Table V, we present the performance comparison results. The first row shows the seven metric results of the original SuBSENSE BGS algorithm, the second row gives the comparison results of SemanticBGS and RTSS when cooperated with the ICNet [45] semantic segmentor, and the third row shows the results when using the PSPNet [18].…”

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

“…Now, the remaining key problem is how can we make use of the semantic foreground segmentation result S t to compensate for the errors of the background subtraction result B t and to produce a more accurate result D t . In this work, we use a similar strategy presented in [17]. First, we want to extract two useful information from the semantic foreground segmentation S t .…”

Section: Rtss Frameworkmentioning

confidence: 99%

“…Our idea is inspired by Braham et al [17], who present a method to improve the BGS segmentation with a postprocessing operation by fusing the segmentation output of a BGS algorithm and a semantic segmentation algorithm. This method has however several drawbacks.…”

Section: Introductionmentioning

confidence: 99%

“…Finally, the refined FG/BG mask D t is fed back to update the background model. In contrast to [17], the proposed method can not only run in real time but also achieves higher detection precision due to the feedback mechanism.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Background Subtraction With Real-Time Semantic Segmentation

et al. 2019

View full text Add to dashboard Cite

Accurate and fast foreground object extraction is very important for object tracking and recognition in video surveillance. Although many background subtraction (BGS) methods have been proposed in the recent past, it is still regarded as a tough problem due to the variety of challenging situations that occur in real-world scenarios. In this paper, we explore this problem from a new perspective and propose a novel background subtraction framework with real-time semantic segmentation (RTSS). Our proposed framework consists of two components, a traditional BGS segmenter B and a real-time semantic segmenter S. The BGS segmenter B aims to construct background models and segments foreground objects. The realtime semantic segmenter S is used to refine the foreground segmentation outputs as feedbacks for improving the model updating accuracy. B and S work in parallel on two threads. For each input frame It, the BGS segmenter B computes a preliminary foreground/background (FG/BG) mask Bt. At the same time, the real-time semantic segmenter S extracts the object-level semantics St. Then, some specific rules are applied on Bt and St to generate the final detection Dt. Finally, the refined FG/BG mask Dt is fed back to update the background model. Comprehensive experiments evaluated on the CDnet 2014 dataset demonstrate that our proposed method achieves stateof-the-art performance among all unsupervised background subtraction methods while operating at real-time, and even performs better than some deep learning based supervised algorithms. In addition, our proposed framework is very flexible and has the potential for generalization.

show abstract

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Section: Rtss Frameworkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Background Subtraction With Real-Time Semantic Segmentation

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Zhang et al [8] proposed binary features calculated from the features extracted by stacked denoising autoencoder. Braham et al [21] used a semantic segmentation map generated from PSPNet [22] for modeling foregrounds and backgrounds. They provided better results than handcraft-based features.…”

Section: Related Workmentioning

confidence: 99%

Analytics of Deep Neural Network-Based Background Subtraction

et al. 2018

View full text Add to dashboard Cite

Deep neural network-based (DNN-based) background subtraction has demonstrated excellent performance for moving object detection. The DNN-based background subtraction automatically learns the background features from training images and outperforms conventional background modeling based on handcraft features. However, previous works fail to detail why DNNs work well for change detection. This discussion helps to understand the potential of DNNs in background subtraction and to improve DNNs. In this paper, we observe feature maps in all layers of a DNN used in our investigation directly. The DNN provides feature maps with the same resolution as that of the input image. These feature maps help to analyze DNN behaviors because feature maps and the input image can be simultaneously compared. Furthermore, we analyzed important filters for the detection accuracy by removing specific filters from the trained DNN. From the experiments, we found that the DNN consists of subtraction operations in convolutional layers and thresholding operations in bias layers and scene-specific filters are generated to suppress false positives from dynamic backgrounds. In addition, we discuss the characteristics and issues of the DNN based on our observation.

show abstract