Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

General diagram.

General diagram of the proposed method.

More »

Fig 1 Expand

Fig 2.

Fight sequence.

Four consecutive frames from a fight sequence where the four largest motion blobs have been marked.

More »

Fig 2 Expand

Fig 3.

Non-Fight sequence.

Four consecutive frames from of a non-fight sequence where the four largest motion blobs have been marked. Compare with those of Fig 2. In the previous figure the motion blobs are larger and clustered, whereas in the current figure the motion blobs are smaller and not clustered.

More »

Fig 3 Expand

Fig 4.

Global movement sequence.

Four consecutive frames from with global movement where the four largest motion blobs have been marked.

More »

Fig 4 Expand

Fig 5.

Movie and Hockey datasets.

Sample fight videos from the action movie (top) dataset and the Hockey (bottom) datase

More »

Fig 5 Expand

Fig 6.

UCF101 dataset.

The 101 actions in UCF101 shown with one sample frame.

More »

Fig 6 Expand

Fig 7.

Fights on UCF101.

Sample frames of Sumo and Punch categories in UCF101.

More »

Fig 7 Expand

Table 1.

This table shows the mean and standard deviation of the Accuracy for these three classifiers for variant 1 of the proposed method.

More »

Table 1 Expand

Table 2.

This table shows the mean and standard deviation of the Accuracy for three classifiers for variant 2 of the proposed method.

More »

Table 2 Expand

Table 3.

This table shows the results for the three datasets using Support Vector Machines (SVM), AdaBoost and Random Forests (RF) classifiers for the related methods and the two proposed variants.

Three measures have been calculated: mean accuracy, standard deviation accuracy and AUC.

More »

Table 3 Expand

Fig 8.

ROCs on Movies dataset.

ROC curves for the five related methods and the two considered variants. The Random Forests classifier on Movies dataset is used.

More »

Fig 8 Expand

Fig 9.

ROCs on Hockey dataset.

ROC curves for the five related methods and the two considered variants. The Random Forests classifier on Hockey dataset is used.

More »

Fig 9 Expand

Fig 10.

ROCs on UCF101 dataset.

ROC curves for the five related methods and the two considered variants. The Random Forests classifier on UCF101 dataset is used.

More »

Fig 10 Expand

Fig 11.

ViF results comparing accuracy vs feature extraction time.

More »

Fig 11 Expand

Fig 12.

LMP results comparing accuracy vs feature extraction time.

More »

Fig 12 Expand

Table 4.

Feature extraction times. Average times measured with the non-fight videos in the UCF101 dataset, on an Intel Xeon computer with 2 processors at 2.90Ghz.

More »

Table 4 Expand

Table 5.

Sub-steps of the proposed method.

More »

Table 5 Expand