基于尺度显著性算法的车型识别方法  

Vehicle type recognition based on scale saliency algorithm

作　　者：袁爱龙[1,2] 陈怀新[2] 吴云峰[1] 

机构地区：[1]电子科技大学光电信息学院,四川成都610054 [2]中国电子科技集团公司第十研究所,四川成都610036

出　　处：《微型机与应用》2012年第15期39-42,共4页Microcomputer & Its Applications

摘　　要：针对复杂背景的视频图像车型识别,提出了一种利用尺度显著性的车型识别方法。由于尺度显著性对图像均一亮度变化、缩放、旋转以及噪声都具有不变性,因此引入尺度显著性算法提取车辆图像的分类特征。最后采用RBF网络分类验证该方法对多种车型的识别。实验结果表明,提取尺度显著性特征能够有效地识别汽车车型。In light of the complicate background of vehicle image in vehicle identification system, this paper proposes a method of vehicle type recognition based on scale saliency algorithm. Because the image features extracted by scale saliency algorithm is invariant on image uniform brightness variations, scaling change, rotation and noise, the scale saliency algorithm is introduced to extract classification features to various vehicle types. At last, the RBF neural network is constructed to verify the feasibility of the proposed method. Experimental result show that the vehicle types are recognized effectively and accurately by the method of scale salient features.

关 键 词：车型识别 尺度显著性算法 特征提取 RBF神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]