A Method of Object Identification Based on Gabor-Network and UWB
UWB communication has obvious advantages in the aspect of transmission rate, power consumption and price cost. Therefore, it has become the focus of the academia and industry. For the low power consumption, high multipath resolution and strong penetrating power, UWB radar has great potential in person positioning, object detection and obstacle recognition. This paper takes the advantage of UWB radar’s environmental perception ability and combines it with Gabor transform in the scenes with different obstacle such as los, human body and metal barrier. We extract the UWB radar signal’s Gabor coefficients and combine them with neural network to identify categories and locations.
KeywordsUWB Gabor Neural network Identification
This work was supported by NSFC (61171176).
- 1.Maherin I, Liang Q (2011) An entropy based approach for sense-through foliage target detection using uwb radar. WASA 6843:180–189Google Scholar
- 2.Yanfei S (2009) Combined neural network and PCA for complicated damage detection of bridge. Nat Comput 2:524–528Google Scholar
- 4.Kong AW-K (2010) “An alternative gabor filtering scheme image processing”. 2010 17th IEEE international conference on digital object identifier. p 1925–1928Google Scholar
- 5.Dolu O, Kirtac K, Gokmen M (2009) “Ensembled gabor nearest neighbor classifier for face recognition”. Comput Inform Sci, p 99–104Google Scholar
- 7.Lajevardi SM, Lech M (2008) “Facial expression recognition using neural networks and log-gabor filters”. Digital image computing: techniques and applications (DICTA), p 77–83Google Scholar
- 8.Areekul V, Watchareeruetai U, Suppasriwasuseth K, Tantaratana S (2005) “Separable Gabor filter realization for fast fingerprint enhancement”. Image Processing, 2005. ICIP 2005, vol 3, p III-253–256Google Scholar