Back to Search
Start Over
Binary 'proximity patches motion' descriptor for action recognition in videos
- Source :
- ICIMCS
- Publication Year :
- 2018
- Publisher :
- ACM, 2018.
-
Abstract
- Building action recognition systems that are simultaneously fast, robust and requiring small memory space is very challenging. Though current state-of-the-art frameworks proposed the best performance on accuracy, speed or memory, they do not offer simultaneously best performance on all three metrics. Thus, it is still possible to achieve a good trade-off among all these three metrics. Using a compact patch-based pattern, this paper introduces a novel binary motion descriptor to efficiently describe motion in video. The descriptor, namely the Proximity Patches Motion (PPM), compares in two different ways a 3 x 3 central patch centered on a detected keypoint with other 24 patches compactly positioned around it between three consecutive frames. Experimental results on the Weizmann and KTH datasets show that the proposed method not only requires a small amount of memory, but is also faster and achieves competitive accuracy when compared to the state-of-the-art spatio-temporal binary descriptors.
- Subjects :
- 0209 industrial biotechnology
Current (mathematics)
Computer science
business.industry
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Matrix norm
Motion (geometry)
Binary number
Pattern recognition
02 engineering and technology
Space (mathematics)
X.3
020901 industrial engineering & automation
0202 electrical engineering, electronic engineering, information engineering
Action recognition
020201 artificial intelligence & image processing
Artificial intelligence
Binary descriptor
business
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Proceedings of the 10th International Conference on Internet Multimedia Computing and Service
- Accession number :
- edsair.doi...........b1c6162347e930e0da444ef9c5104beb