Segmenting foreground objects from a dynamic textured background via a robust Kalman filter

Zhong, Jue; Sclaroff,

doi:10.1109/iccv.2003.1238312

Cited by 172 publications

(8 citation statements)

References 22 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• We evaluate our work on six methods at both pixel and object levels. Furthermore, we test them on a set of sequences from different datasets, namely CDNet [14,15], LASIESTA [16] and J. Zhong and S. Sclaroff [17]. • Our results show a considerable increase in object-wise performance metrics, while also improving or maintaining the pixel-wise results.…”

Section: Introductionmentioning

confidence: 87%

“…Results on sequences from J. Zhong and S. Sclaroff [17]. Lastly, we evaluated our method on two sequences from J. Zhong and S. Sclaroff [17] containing challenging dynamic backgrounds.…”

Section: Methodsmentioning

confidence: 99%

“…Results on sequences from J. Zhong and S. Sclaroff [17]. Lastly, we evaluated our method on two sequences from J. Zhong and S. Sclaroff [17] containing challenging dynamic backgrounds. One of them shows an escalator moving continuously, while the other displays a floating plastic bottle.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Statistical modeling of deep features reduces false alarms in video change detection

Bou,

Artola,

Ehret

et al. 2024

Preprint

View full text Add to dashboard Cite

Detecting relevant changes is a fundamental problem of video surveillance. Because of the high variability of data and the difficulty of properly annotating changes, unsupervised methods dominate the field. Arguably one of the most critical issues to make them practical is to reduce their false alarm rate. In this work, we develop a method-agnostic weakly supervised a-contrario validation process, based on high dimensional statistical modeling of deep features, to reduce the number of false alarms of any change detection algorithm. We also raise the insufficiency of the conventionally used pixel-wise evaluation, as it fails to precisely capture the performance needs of most real applications. For this reason, we complement pixel-wise metrics with object-wise metrics and evaluate the impact of our approach at both pixel and object levels, on six methods and several sequences from different datasets. Experimental results reveal that the proposed a-contrario validation is able to largely reduce the number of false alarms at both pixel and object levels.

show abstract

Section: Introductionmentioning

confidence: 87%

“…Results on sequences from J. Zhong and S. Sclaroff [17]. Lastly, we evaluated our method on two sequences from J. Zhong and S. Sclaroff [17] containing challenging dynamic backgrounds.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Statistical modeling of deep features reduces false alarms in video change detection

Bou,

Artola,

Ehret

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In our implementation, YOLOv5s [32] is employed to detect the foreground and extract the object representation parameters. Different from the traditional foreground extraction method [33][34][35], the YOLOv5s based on deep learning can obtain semantics of the foreground including object class and location. The original YOLOv5s is trained on COCO datasets [36] and the objects of the apron surveillance video are not fully covered.…”

Section: Extracting Foreground Objects and Backgroundmentioning

confidence: 99%

Apron surveillance video coding based on compositing virtual reference frame with object library

Lyu

Zhang

2023

IET Image Processing

View full text Add to dashboard Cite

A video coding framework for the apron surveillance scene has been proposed in this paper, which aims to improve coding efficiency by eliminating long-term redundancy at the object level. To achieve this goal, this study first develops an existing block-based hybrid video coding framework by exploiting the video redundancy on the object level to perform video coding. Second, an object-library mechanism is designed to collect the representative object images as coding references on larger temporal and spatial scales. Finally, a virtual reference frame, which blends background and foreground references from the object library, is adaptively composited according to the video content to improve the interprediction performance. Preliminary experimental results demonstrate that the proposed method achieves a high BD rate reduction of up to 23.97% in apron surveillance video sequences, compared to the standard high efficiency video coding (HEVC).

show abstract

“…Traditional background subtraction schemes such as AMF (Approximated Median Filter) [12], Kalman filter [13], and single Gaussian filter [14] reflect some irrelevant pixels on the foreground due to lack of correlation between the spatial and temporal constraints in their background maintenance schemes. Nevertheless, adjusting the learning rate to background pixels is another potential problem in background maintenance [15].…”

Section: Introductionmentioning

confidence: 99%

Segmentation of Moving Object Using Background Subtraction Method in Complex Environments

Kumar¹,

Yadav²

2016

RADIOENGINEERING

View full text Add to dashboard Cite

Segmenting foreground objects from a dynamic textured background via a robust Kalman filter

Abstract: The algorithm presented in this paper aims to segment the foreground objects in video (e.g., people)

Cited by 172 publications

References 22 publications

Statistical modeling of deep features reduces false alarms in video change detection

Statistical modeling of deep features reduces false alarms in video change detection

Apron surveillance video coding based on compositing virtual reference frame with object library

Segmentation of Moving Object Using Background Subtraction Method in Complex Environments

Contact Info

Product

Resources

About