Real-time action recognition based on cumulative Motion shapes

Alcântara, Maria Regina; Moreira, Thierry Pinheiro; Pedrini, Hélio

doi:10.1109/icassp.2014.6854134

Cited by 10 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, our results (in terms of accuracy) are superior compared to those in Ref. 15 for the majority of the tested datasets.…”

Section: Resultscontrasting

confidence: 58%

“…Unlike the method developed by Alcantara et al, 15 our strategy for creating the CMS descriptor uses all the available information and, due to that, requires more computational time for the processing. However, our results (in terms of accuracy) are superior compared to those in Ref.…”

Section: Resultsmentioning

confidence: 99%

“…A sliding window is used to build CMSs, 15 which are a simple union of all binary foregrounds of the video frames in a time interval. The CMS for the k 0 th frame of the video (CMS k ) is given by Eq.…”

Section: Methodsmentioning

confidence: 99%

“…The major contributions of the current work compared against the approach developed by Alcantara et al 15 include: (i) the proposition of a multilayer descriptor (the descriptor in Ref. 15 has one layer); (ii) the descriptor's ability to selfadjust to a nonsegmented scene with variable duration and, due to that, the descriptor's applicability to more datasets; (iii) the combination of multiple responses of classifiers and decisions for the most representative outcome as the final verdict.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real-time action recognition using a multilayer descriptor with variable size

Alcântara

Moreira

Pedrini

2016

J. Electron. Imaging

Self Cite

View full text Add to dashboard Cite

Video analysis technology has become less expensive and more powerful in terms of storage resources and resolution capacity, promoting progress in a wide range of applications. Video-based human action detection has been used for several tasks in surveillance environments, such as forensic investigation, patient monitoring, medical training, accident prevention, and traffic monitoring, among others. We present a method for action identification based on adaptive training of a multilayer descriptor applied to a single classifier. Cumulative motion shapes (CMSs) are extracted according to the number of frames present in the video. Each CMS is employed as a self-sufficient layer in the training stage but belongs to the same descriptor. A robust classification is achieved through individual responses of classifiers for each layer, and the dominant result is used as a final outcome. Experiments are conducted on five public datasets (Weizmann, KTH, MuHAVi, IXMAS, and URADL) to demonstrate the effectiveness of the method in terms of accuracy in real time.

show abstract

“…However, our results (in terms of accuracy) are superior compared to those in Ref. 15 for the majority of the tested datasets.…”

Section: Resultscontrasting

confidence: 58%

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-time action recognition using a multilayer descriptor with variable size

Alcântara

Moreira

Pedrini

2016

J. Electron. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…Accuracy% Real-time Intensive training Year Michalis, et al [5] 100 No Yes 2014 Marlon, et al [22] 2013 Romain, et al [8] 82.79 No Yes 2013 Zhuolin, et al [3] 100 Yes Yes 2012 Saad, et al [7] 95.75 No Yes 2010 Elden, et al [23] 93.6 Yes No 2009 Saad, et al [24] 92. reported to be fast but requires intensive training and uses optical flow which is usually computationally expensive. Hence, these methods are not suitable for real-world applications.…”

Section: Methodsmentioning

confidence: 99%

Hierarchical Relaxed Partitioning System for Activity Recognition

Azhar

2017

IEEE Trans. Cybern.

View full text Add to dashboard Cite

A hierarchical relaxed partitioning system (HRPS) is proposed for recognizing similar activities which has a feature space with multiple overlaps. Two feature descriptors are built from the human motion analysis of a 2-D stick figure to represent cyclic and noncyclic activities. The HRPS first discerns the pure and impure activities, i.e., with no overlaps and multiple overlaps in the feature space, respectively, then tackles the multiple overlaps problem of the impure activities via an innovative majority voting scheme. The results show that the proposed method robustly recognizes various activities of two different resolution data sets, i.e., low and high (with different views). The advantage of HRPS lies in the real-time speed, ease of implementation and extension, and nonintensive training.

show abstract