Video Behavioral recognition-1 database

1. Common Behavior Database:

URL link 1:http://www.cs.utexas.edu/~chaoyeh/web_action_data/dataset_list.html#list_of_data_sets

1.1 Weizmann

WEIZMANN[27] Database contains 10 actions are walking, running, jumping, jumping, moving to one side, single hand-waving, 2 hand-waving, one-hop, 2-arm-waving jump, each action has 10 people to perform. In this video set, the background is static, and the foreground provides the silhouette information. This data set is simpler.

1.2 KTH

KTH[45] The pedestrian database contains 6 actions, namely walking, jogging, waving and clapping. Each action is done by 25 different people. Each of these moves was completed in 4 different scenarios, with 4 scenes, outdoor, indoor, outdoor, outdoor and in different colours.

URL link 2:http://www.nada.kth.se/cvap/actions/

1.3 PETS

PETS[51], which is called tracking and monitoring performance evaluation meeting, its database is obtained from the real life, mainly from video surveillance system directly from the video, such as the supermarket monitoring system. Since 2000, this meeting has been organized almost every year.

1.4 YouTube

YouTube contains 11 kinds of actions, because it is real-life video data, so its background is more complex, these kinds of actions are difficult to identify.

URL link 3:http://www.cs.ucf.edu/-liujg/youtube\_action\_dataset.html

1.5 UCF Sports

UCF contains several datasets, which are the motion database for UCF, which includes 150 video sequences and a total of 9 types of actions. Because it is real-life video data, so its background is more complex, these kinds of actions are difficult to identify.

1.6 Inria XMAS

The Inria xmas database [53] is taken from 5 angles, 4 directions in the room and 1 directions from the top of the head. A total of 11 people complete 14 different movements, which can be carried out in any direction. The camera is stationary, and the ambient lighting conditions are virtually unchanged. In addition, the data set provides information such as body contour and volume element.

1.7 Hollywood and Hollywood2

Hollywood Movie Database contains several, one Hollywood video set has 8 kinds of action, namely answer phone, sedan, handshake, hug, kiss, sit down, stand up, stand. These movements are drawn directly from the film and are performed by different actors in different environments. The second Hollywood2 on the basis of the above added 4 more actions, cycling, eating, fighting, running. and its training set gives the automatic description text annotation of the movie, and some of it is manually labeled. This data set is very challenging due to factors such as occlusion, moving cameras, dynamic backgrounds, and so on.

1.8 HMDB51

HMDB51 contains 51 types of actions, a total of 6,849 videos, of which the author provides 70% for training, the remainder for testing, 320*240,. From YouTube, movie, and others.

1.9 UCF101

UCF101 contains 101 types of actions, each of which consists of 25 people doing the action, each doing 4-7 groups, a total of 13,320 videos, 320*240.

URL link 4:http://www.nada.kth.se/cvap/actions/

2015-12-16

Video Behavioral recognition-1 database