计算机科学 ›› 2015, Vol. 42 ›› Issue (10): 321-324.
• 图形图像与模式识别 • 上一篇
陶军,刘建明,王明文,万剑怡
TAO Jun, LIU Jian-ming, WANG Ming-wen and WAN Jian-yi
摘要: 现有的对象检测方法主要针对特定对象,当类别比较多时,难以实现实时检测与识别。提出了一种基于Objectness和梯度方向模板的大量类别下非纹理对象的实时检测与识别算法。该方法首先通过计算图像Objectness值来评价待测图像中可能出现对象的区域,大量减少可能匹配的窗口。在此基础上,在可能出现对象的区域,采用基于模板主方向和查找表的模板匹配方法,实现大量类别下非纹理对象的实时检测与识别。该方法对非纹理物体的鲁棒性较好,同时在匹配的过程中也是方向无关的。
[1] Olson C F,Huttenlocher D P.Automatic Target Recognition by Matching Oriented Edge Pixels[J].IEEE Transactions on Image Processing,1997,6(1):103-113 [2] Gavrila D,Philomin V.Real-Time Object Detection for smartVehicles[C]∥IEEE international Conference on Computer Vision,2010:533-542 [3] Holzer S,Hinterstoisser S,Ilic S,et al.Distance transform templates for object detection and pose estimation[C]∥CVPR.2009:1177-1184 [4] Steger C.Occlusion Clutter,and Illumination Invariant ObjectRecognition[C]∥IAPRS.2002 [5] Dalal N,Triggs B.Histograms of Oriented Gradients for Human Detection.http://lear.inrialpes.fr/people/triggs/pubs/Dalal-os.pdf.cvpr [6] Ferrari V,Jurie F,Schmid C.From images to shape models for object detection[J].IJCV,2009,87(3):284-303 [7] Tombari F,Franchi A,Automation D,et al.BOLD features to detect texture-less objects[C]∥2013 IEEE International Conference on Computer Vision(ICCV 2013).2013:1265-1272 [8] Hinterstoisser S,Cagniart C,Ilic S,et al.Gradient responsemaps for real-time detection of textureless objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(5):876-888 [9] Cheng M M,Zhang Z,Lin W Y,et al.Bing:Binarized normed gradients for objectness estimation at 300fps[C]∥CVPR.2014:3286-3293 |
No related articles found! |
|