Gait Recognition Based on GF-CNN and Metric Learning
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Gait recognition, as a promising biometric, can be used in video-based surveillance and other security systems. However, due to the complexity of leg movement and the difference of external sampling conditions, gaitrecognition still faces many problems to be addressed. In this paper, an improved convolutional neural network(CNN) based on Gabor filter is therefore proposed to achieve gait recognition. Firstly, a gait feature extractionlayer based on Gabor filter is inserted into the traditional CNNs, which is used to extract gait features from gaitsilhouette images. Then, in the process of gait classification, using the output of CNN as input, we utilize metriclearning techniques to calculate distance between two gaits and achieve gait classification by k-nearestneighbors classifiers. Finally, several experiments are conducted on two open-accessed gait datasets anddemonstrate that our method reaches state-of-the-art performances in terms of correct recognition rate on theOULP and CASIA-B datasets.
Abstract
Gait recognition, as a promising biometric, can be used in video-based surveillance and other security systems. However, due to the complexity of leg movement and the difference of external sampling conditions, gaitrecognition still faces many problems to be addressed. In this paper, an improved convolutional neural network(CNN) based on Gabor filter is therefore proposed to achieve gait recognition. Firstly, a gait feature extractionlayer based on Gabor filter is inserted into the traditional CNNs, which is used to extract gait features from gaitsilhouette images. Then, in the process of gait classification, using the output of CNN as input, we utilize metriclearning techniques to calculate distance between two gaits and achieve gait classification by k-nearestneighbors classifiers. Finally, several experiments are conducted on two open-accessed gait datasets anddemonstrate that our method reaches state-of-the-art performances in terms of correct recognition rate on theOULP and CASIA-B datasets.
참고문헌 (9)
- J. P. Singh, "Vision-based gait recognition : a survey", IEEE Access, 6, pp.70497~70527 (2018)
- Y. He, "Deep learning for gait recognition : a survey", Pattern Recognition and Artificial Intelligence, 31(5), pp.442~451 (2018)
- X. Wang, "Human gait recognition based on frame-by-frame gait energy images and convolutional long short-term memory", International Journal of Neural Systems, 30(1), pp.1950027~ (2019)
- Y. LeCun, "Deep learning", Nature, 521(5), pp.436~445 (2015)
- Z. Wu, "A comprehensive study on cross-view gait based human identification with deep CNNs", IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(2), pp.209~226 (2017)
- N. Takemura, "On input", output architectures for convolutional neural network-based cross-view gait recognition, 2019, pp.29(9), 2708~2719
- J. Han, "Individual recognition using gait energy image", IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(2), pp.316~322 (2006)
- S. Choi, "Skeleton-based gait recognition via robust frame-level matching", IEEE Transactions on Information Forensics and Security, 14(10), pp.2577~2592 (2019)
- X. Wang, "Gait recognition based on Gabor wavelets and(2D)2PCA", Multimedia Tools and Applications, 77(10), pp.12545~12561 (2018)