Combination of Video Change Detection Algorithms by Genetic Programming

Bianco, Simone; Ciocca, Gianluigi; Schettini, Raimondo

doi:10.1109/tevc.2017.2694160

Cited by 148 publications

(61 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MC), achieving a F-measure that is 7.2% higher. For comparison, we also report here (see Figure 2) the solution trees of IUTIS-3 and IUTIS-5, that we recall have been generated by the same method here described but in a purely performance-based scenario [3]. The set of algorithms C available for GP to build IUTIS-3 were the three top performing algorithms on CDNET 2014, i.e.…”

Section: Resultsmentioning

confidence: 99%

“…In the case of IUTIS-5 this difference increases to 5.4%. It is worth noting that all our solutions are better than majority vote solutions (denoted with MV) applied to the corresponding sets C. In [3] we also experimented with larger cardinalities of C, i.e. #C = 7 and 9, but in both cases the corresponding solutions found by GP, i.e.…”

Section: Resultsmentioning

confidence: 99%

“…the values in the configuration files provided in the BGSLibrary. We set the parameters of GP as in [3]. Also, the GP solutions are generated by considering the shortest video sequence in each of the 11 CDNET 2014 categories as training set.…”

Section: Methodsmentioning

confidence: 99%

“…In table 3 we also report the computational time of IUTIS-3 , and IUTIS-5used in [3]. For these algorithms, the computational time is an estimated of an hypothetical parallel implementation and corresponds to the slowest algorithm used in the solution tree.…”

Section: Computational Timementioning

confidence: 99%

See 3 more Smart Citations

How Far Can You Get by Combining Change Detection Algorithms?

Bianco

Ciocca

Schettini

2017

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Given the existence of many change detection algorithms, each with its own peculiarities and strengths, we propose a combination strategy, that we termed IUTIS (In Unity There Is Strength), based on a genetic Programming framework. This combination strategy is aimed at leveraging the strengths of the algorithms and compensate for their weakness. In this paper we show our findings in applying the proposed strategy in two different scenarios. The first scenario is purely performance-based. The second scenario performance and efficiency must be balanced. Results demonstrate that starting from simple algorithms we can achieve comparable results with respect to more complex state-of-the-art change detection algorithms, while keeping the computational complexity affordable for real-time applications.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Computational Timementioning

confidence: 99%

See 2 more Smart Citations

How Far Can You Get by Combining Change Detection Algorithms?

Bianco

Ciocca

Schettini

2017

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to further verify the superiority and applicability of the proposed enhancement method, we apply it to detection masks of three foreground detection algorithms, i.e., GRBM [37], MD [38], IUTIS_5 [39], on 14 complete video sequences in CDnet2012. In CDnet competition, the three methods have medium, low and high ranks, respectively.…”

Section: Experiments On Some Complete Sequencesmentioning

confidence: 99%

An Integrated Image Filter for Enhancing Change Detection Results

Yan

Cai

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Change detection is a fundamental task in computer vision. Despite significant advances have been made, most of the change detection methods fail to work well in challenging scenes due to ubiquitous noise and interferences. Nowadays, post-processing methods (e.g. MRF, and CRF) aiming to enhance the binary change detection results still fall short of the requirements on universality for distinctive scenes, applicability for different types of detection methods, accuracy, and real-time performance. Inspired by the nature of image filtering, which separates noise from pixel observations and recovers the real structure of patches, we consider utilizing image filters to enhance the detection masks. In this paper, we present an integrated filter which comprises a weighted local guided image filter and a weighted spatiotemporal tree filter. The spatiotemporal tree filter leverages the global spatiotemporal information of adjacent video frames and meanwhile the guided filter carries out local window filtering of pixels, for enhancing the coarse change detection masks. The main contributions are three: (i) the proposed filter can make full use of the information of the same object in consecutive frames to improve its current detection mask by computations on a spatiotemporal minimum spanning tree; (ii) the integrated filter possesses both advantages of local filtering and global filtering; it not only has good edge-preserving property but also can handle heavily textured and colorful foreground regions; and (iii) Unlike some popular enhancement methods (MRF, and CRF) that require either a priori background probabilities or a posteriori foreground probabilities for every pixel to improve the coarse detection masks, our method is a versatile enhancement filter that can be applied after many different types of change detection methods, and is particularly suitable for video sequences. Experiments demonstrate that our method are suitable to be applied after a wide range of change detection methods, and it also works effectively on various scenes. In comparison, it evidently outperforms seven popular enhancement approaches.

show abstract