Abstract | ||
---|---|---|
The automatic recognition of a crowd movement captured by a CCTV camera can be of considerable help to security forces whose mission is to ensure the safety of people on the public area. In this context, we propose to fine-tune a model from the TwoStream Inflated 3D architecture, pre-trained on the ImageNet and the Kinetics source datasets, to classify video sequences of crowd movements from the Crowd-11 target dataset. The evaluation of our model demonstrates its superiority over the state-of-the-art in terms of classification accuracy. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ISPA.2019.8868704 | 2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA) |
Keywords | Field | DocType |
Video-surveillance,Crowd Behavior Analysis,Convolutional Neural Networks,Transfer Learning | Computer vision,Architecture,Computer science,Transfer of learning,Real-time computing,Kinetic theory,Artificial intelligence,Security forces,Solid modeling,Optical imaging,Trajectory | Conference |
ISSN | ISBN | Citations |
1845-5921 | 978-1-7281-3141-2 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mounir Bendali-Braham | 1 | 0 | 0.34 |
Jonathan Weber | 2 | 92 | 8.97 |
germain forestier | 3 | 467 | 42.14 |
Lhassane Idoumghar | 4 | 145 | 25.07 |
Pierre-Alain Muller | 5 | 511 | 54.09 |