Online object detection and recognition using motion information and local feature co-occurrence  

基于运动信息和局部特征并发性的在线目标检测和识别(英文)

作　　者：张索非[1] Filliat David 吴镇扬[1] 

机构地区：[1]东南大学水声信号处理教育部重点实验室,南京210096 [2]UEI,ENSTA ParisTech

出　　处：《Journal of Southeast University(English Edition)》2012年第4期404-409,共6页东南大学学报（英文版）

基　　金：The National Natural Science Foundation of China(No.60672094,60971098)

摘　　要：An object learning and recognition system is implemented for humanoid robots to discover and memorize objects only by simple interactions with non-expert users. When the object is presented, the system makes use of the motion information over consecutive frames to extract object features and implements machine learning based on the bag of visual words approach. Instead of using a local feature descriptor only, the proposed system uses the co-occurring local features in order to increase feature discriminative power for both object model learning and inference stages. For different objects with different textures, a hybrid sampling strategy is considered. This hybrid approach minimizes the consumption of computation resources and helps achieving good performances demonstrated on a set of a dozen different daily objects.实现了一个为类人型机器人设计的目标学习和识别系统,机器人可以利用该系统仅通过和非专业用户简单的互动来发现并记住目标.当目标展示时,系统利用连续帧间的运动信息提取目标特征并基于视觉单词包方法实现机器学习.在目标模型的学习与测试阶段,不仅直接使用了局部特征描述子,还使用了局部特征的并发性以提升特征的可鉴别性.同时,针对目标视觉特征的纹理程度,还采用了一种混合的采样策略.该混合策略使用了更小的计算资源开销并在一个12类常见目标构成的集合上取得了良好的识别效果.

关 键 词：object recognition online learning motion information computer vision 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]