Robust Real-Time Detection of Abandoned and Removed Objects

Li, Qiujie; Mao, Yaobin; Wang, Zhiquan; Xiang, Wenbo

doi:10.1109/icig.2009.166

Cited by 18 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other approaches [9,61,71,94] are based on the fact that the color of the static FG regions is usually inconsistent with the one of the BG around it, while the color of the region occupied by the object is often similar with the one of the surrounding region. In this way, they can discriminate between SFOs and ROs by analyzing the color richness of the detected static regions.…”

Section: Ro Detectionmentioning

confidence: 98%

“…In the strategy proposed by Porikli, and some other later works [69,71,98], the models are constructed using multiple Gaussians. However, other modeling choices can also be found in the literature: non-statistical models (basic) in [80], [86], [87] and [107], SGMs in [61], MMs in [63], or CMs in [44].…”

Section: Dual Fg Comparison (Dfc)mentioning

confidence: 99%

“…In [46] the RGA modeling is combined with Markov Random Fields (MRFs), which spatially smooths the BG modeling results, thus avoiding the need of applying an independent threshold to each pixel and improving the quality of the results in sequences with camera jitter. In [61] the FG masks are constructed from two BG models: the first one (shortterm model) is obtained with the RGA method, whereas the second one (long-term model) is an approximation of the average of the previous. [18] None Classifier x x 1999-Wang [19] Basic x x…”

Section: Single Gaussian Models (Sgm)mentioning

confidence: 99%

See 2 more Smart Citations

Detection of stationary foreground objects: A survey

Cuevas

Martínez

García

2016

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Section: Ro Detectionmentioning

confidence: 98%

Section: Dual Fg Comparison (Dfc)mentioning

confidence: 99%

Section: Single Gaussian Models (Sgm)mentioning

confidence: 99%

See 1 more Smart Citation

Detection of stationary foreground objects: A survey

Cuevas

Martínez

García

2016

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…Color We use the change of the color richness of a expanded true static region to discriminate between abandoned or removed objects [7]. We compute the color richness in the input image and the color richness of the region that corresponds to the expanded static region in the background image.…”

Section: Event Feature Setmentioning

confidence: 99%

Nonparametric state machine with multiple features for abnormal object classification

Kim

Kang

2014

2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

Abandoned object and removed object are important abnormal objects in visual surveillance area to predict the crimes such as explosion or theft event. In real situations, most of existing methods using CCD camera show inconsistent performance because they use a lot of threshold values depending on the environmental conditions of target scene such as illumination change, high traffic volume and complex background. We propose a nonparametric state machine with hierarchical structure consisting of three layers. As shown in the experimental results, the proposed method can be applied to general situations because the state transitions is performed by trained SVM classifiers.

show abstract

“…Discrimination is determined as the lowest distance. Similarly, a color-richness measure is proposed in [13] to count the number of colors (i.e., histogram bins above a threshold) and perform the same comparison as [7]. Moreover, [14] proposed to use image inpainting to reconstruct the hidden background and compare it against the external region using color histograms.…”

Section: Related Workmentioning

confidence: 99%