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 original IXMAS 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

f4-sensors-15-17209: Performance comparisons on the original IXMAS 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 4 shows the evaluation of the codebook size of BoWs and the number of layers of mSDA on the original IXMAS dataset. 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 the fact the number of selected descriptor features in the training set is limited, as the codebook size increases the number of clusters generated during the K-Means clustering increases accordingly. As a result, the average number of descriptor features per cluster has been significantly reduced, and the resulting representation become much more sparse and less discriminative. On the other hand, the increase in the number of layers of mSDA leads to slight but consistent improvements. A large number of layers results in a 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 original IXMAS dataset are listed in Table 1, where the top half of the table consists of the offline systems while the bottom half lists the online systems with frames per second (FPS). As reported in [5], the simple fusion strategies and MKL algorithm using the IDT descriptor and the BoWs representation outperform the state-of-the-art algorithms in terms of average recognition rate. The FPS has been improved as well due to the downscaled resolution of video, which reduces the time required to compute IDT descriptors of each video. More importantly, the incorporation of mSDA further improve the overall performance of all the methods, especially the MKL algorithm has reached 0.965 at 45 FPS. This implies that the mSDA algorithm can indeed improve the basic BoWs representation by providing a more robust and useful representation, which leads to significant gains in the system's overall recognition performance.


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 original IXMAS 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

f4-sensors-15-17209: Performance comparisons on the original IXMAS 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 4 shows the evaluation of the codebook size of BoWs and the number of layers of mSDA on the original IXMAS dataset. 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 the fact the number of selected descriptor features in the training set is limited, as the codebook size increases the number of clusters generated during the K-Means clustering increases accordingly. As a result, the average number of descriptor features per cluster has been significantly reduced, and the resulting representation become much more sparse and less discriminative. On the other hand, the increase in the number of layers of mSDA leads to slight but consistent improvements. A large number of layers results in a 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 original IXMAS dataset are listed in Table 1, where the top half of the table consists of the offline systems while the bottom half lists the online systems with frames per second (FPS). As reported in [5], the simple fusion strategies and MKL algorithm using the IDT descriptor and the BoWs representation outperform the state-of-the-art algorithms in terms of average recognition rate. The FPS has been improved as well due to the downscaled resolution of video, which reduces the time required to compute IDT descriptors of each video. More importantly, the incorporation of mSDA further improve the overall performance of all the methods, especially the MKL algorithm has reached 0.965 at 45 FPS. This implies that the mSDA algorithm can indeed improve the basic BoWs representation by providing a more robust and useful representation, which leads to significant gains in the system's overall recognition performance.

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