Limits...
Marginalised Stacked Denoising Autoencoders for Robust Representation of Real-Time Multi-View Action Recognition.

Gu F, Flórez-Revuelta F, Monekosso D, Remagnino P - Sensors (Basel) (2015)

Bottom Line: Based on the internal evaluation, the codebook size of BoWs and the number of layers of mSDA may not significantly affect recognition performance.According to results on three multi-view benchmark datasets, the proposed framework improves recognition performance across all three datasets and outputs record recognition performance, beating the state-of-art algorithms in the literature.It is also capable of performing real-time action recognition at a frame rate ranging from 33 to 45, which could be further improved by using more powerful machines in future applications.

View Article: PubMed Central - PubMed

Affiliation: School of Computing and Information Systems, Kingston University, Penrhyn Road, Kingston upon Thames KT1 2EE, UK. F.Gu@kingston.ac.uk.

ABSTRACT
Multi-view action recognition has gained a great interest in video surveillance, human computer interaction, and multimedia retrieval, where multiple cameras of different types are deployed to provide a complementary field of views. Fusion of multiple camera views evidently leads to more robust decisions on both tracking multiple targets and analysing complex human activities, especially where there are occlusions. In this paper, we incorporate the marginalised stacked denoising autoencoders (mSDA) algorithm to further improve the bag of words (BoWs) representation in terms of robustness and usefulness for multi-view action recognition. The resulting representations are fed into three simple fusion strategies as well as a multiple kernel learning algorithm at the classification stage. Based on the internal evaluation, the codebook size of BoWs and the number of layers of mSDA may not significantly affect recognition performance. According to results on three multi-view benchmark datasets, the proposed framework improves recognition performance across all three datasets and outputs record recognition performance, beating the state-of-art algorithms in the literature. It is also capable of performing real-time action recognition at a frame rate ranging from 33 to 45, which could be further improved by using more powerful machines in future applications.

No MeSH data available.


Related in: MedlinePlus

Performance comparisons on the IXMAS actions dataset, of proposed methods, with respect to the size of BoWs (from 4 K to 20 K when the number of layers of mSDA is 5) and the number of layers of mSDA (from 1 to 5 when the size of BoWs is 4 K), in terms of average recognition rates. (a) The size of BoWs; (b) The number of layers of mSDA.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541930&req=5

f5-sensors-15-17209: Performance comparisons on the IXMAS actions dataset, of proposed methods, with respect to the size of BoWs (from 4 K to 20 K when the number of layers of mSDA is 5) and the number of layers of mSDA (from 1 to 5 when the size of BoWs is 4 K), in terms of average recognition rates. (a) The size of BoWs; (b) The number of layers of mSDA.

Mentions: Figure 5 displays the evaluation of the codebook size of BoWs and the number of layers of mSDA on the IXMAS actions dataset. Similar trends can be observed here. On one hand, the increase in the codebook size results in minor improvements initially, however the recognition performances drop as the size is close to 20 K. This is due to much more sparse and less discriminative representation when the size is larger. On the other hand, the increase in the number of layers of mSDA leads to slight but consistent improvements. This is due to the higher dimensional representation that is denser and more robust with respect to discrimination between different action classes. The results of all compared methods on the IXMAS action dataset are displayed in Table 2, the top half the table consists of the algorithms proposed in [18] using instances that are clean, i.e., the occluded examples that are supposed to be more difficult to recognise are removed. While the bottom half lists all the methods applied to the entire dataset with a majority of occluded examples. All the methods described in this paper, even the basic ones using the IDT descriptor and BoWs representation outperform those in [18]. Similar trends can be observed on this dataset as well, that is, the MKL algorithm outperforms the simple fusion strategies and the new representation generated by the mSDA is more discriminative than that generated by only the BoWs, resulting significant improvements on the recognition rates. The best performance is achieved by the MKL algorithm using the representation generated by the IDT descriptor and mSDA algorithm, reaching 0.842 at 40 FPS.


Marginalised Stacked Denoising Autoencoders for Robust Representation of Real-Time Multi-View Action Recognition.

Gu F, Flórez-Revuelta F, Monekosso D, Remagnino P - Sensors (Basel) (2015)

Performance comparisons on the IXMAS actions dataset, of proposed methods, with respect to the size of BoWs (from 4 K to 20 K when the number of layers of mSDA is 5) and the number of layers of mSDA (from 1 to 5 when the size of BoWs is 4 K), in terms of average recognition rates. (a) The size of BoWs; (b) The number of layers of mSDA.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541930&req=5

f5-sensors-15-17209: Performance comparisons on the IXMAS actions dataset, of proposed methods, with respect to the size of BoWs (from 4 K to 20 K when the number of layers of mSDA is 5) and the number of layers of mSDA (from 1 to 5 when the size of BoWs is 4 K), in terms of average recognition rates. (a) The size of BoWs; (b) The number of layers of mSDA.
Mentions: Figure 5 displays the evaluation of the codebook size of BoWs and the number of layers of mSDA on the IXMAS actions dataset. Similar trends can be observed here. On one hand, the increase in the codebook size results in minor improvements initially, however the recognition performances drop as the size is close to 20 K. This is due to much more sparse and less discriminative representation when the size is larger. On the other hand, the increase in the number of layers of mSDA leads to slight but consistent improvements. This is due to the higher dimensional representation that is denser and more robust with respect to discrimination between different action classes. The results of all compared methods on the IXMAS action dataset are displayed in Table 2, the top half the table consists of the algorithms proposed in [18] using instances that are clean, i.e., the occluded examples that are supposed to be more difficult to recognise are removed. While the bottom half lists all the methods applied to the entire dataset with a majority of occluded examples. All the methods described in this paper, even the basic ones using the IDT descriptor and BoWs representation outperform those in [18]. Similar trends can be observed on this dataset as well, that is, the MKL algorithm outperforms the simple fusion strategies and the new representation generated by the mSDA is more discriminative than that generated by only the BoWs, resulting significant improvements on the recognition rates. The best performance is achieved by the MKL algorithm using the representation generated by the IDT descriptor and mSDA algorithm, reaching 0.842 at 40 FPS.

Bottom Line: Based on the internal evaluation, the codebook size of BoWs and the number of layers of mSDA may not significantly affect recognition performance.According to results on three multi-view benchmark datasets, the proposed framework improves recognition performance across all three datasets and outputs record recognition performance, beating the state-of-art algorithms in the literature.It is also capable of performing real-time action recognition at a frame rate ranging from 33 to 45, which could be further improved by using more powerful machines in future applications.

View Article: PubMed Central - PubMed

Affiliation: School of Computing and Information Systems, Kingston University, Penrhyn Road, Kingston upon Thames KT1 2EE, UK. F.Gu@kingston.ac.uk.

ABSTRACT
Multi-view action recognition has gained a great interest in video surveillance, human computer interaction, and multimedia retrieval, where multiple cameras of different types are deployed to provide a complementary field of views. Fusion of multiple camera views evidently leads to more robust decisions on both tracking multiple targets and analysing complex human activities, especially where there are occlusions. In this paper, we incorporate the marginalised stacked denoising autoencoders (mSDA) algorithm to further improve the bag of words (BoWs) representation in terms of robustness and usefulness for multi-view action recognition. The resulting representations are fed into three simple fusion strategies as well as a multiple kernel learning algorithm at the classification stage. Based on the internal evaluation, the codebook size of BoWs and the number of layers of mSDA may not significantly affect recognition performance. According to results on three multi-view benchmark datasets, the proposed framework improves recognition performance across all three datasets and outputs record recognition performance, beating the state-of-art algorithms in the literature. It is also capable of performing real-time action recognition at a frame rate ranging from 33 to 45, which could be further improved by using more powerful machines in future applications.

No MeSH data available.


Related in: MedlinePlus