摘要
为了降低识别复杂度,提高识别效率,实现手势的快速高效跟踪,提出一种分情况检测思想和搜索框概念。首先对图像进行细检测,得到目标的准确位置,然后通过粗检测与跟踪相结合的方式进行目标跟踪,并对跟踪结果进行修正和可信度判断。实验结果显示:算法对图像手势的平均检测跟踪正确率可以达到97.36%,且保证平均漏检率在5%以下,对各种外界因素具有较好的鲁棒性;算法对视频图像的处理速度达19.42帧/秒,满足人机交互系统中的实时性需求;与TLD算法相比,本算法在处理速度上有数量级的改善,算法结果的正确率也有明显优势。
An algorithm for gesture detection and tracking in HCI （human-computer interaction） is designed to meet real-time and accuracy requirements. An innovative conception, which includes using distinguishing detection methods to detect hand-gesture for different conditions and using searching-box to decrease the searching zone, is proposed. The result shows that the detection rate can reach 97.36% while the missing rate lowers than 5%. It is robust to various external factors. However, it also meets the real-time, as the frame rate can reach 19.42. Compared with TLD, this algorithm has not only magnitude improvement in processing speed but also obvious advantages in accuracy.
出处
《北京大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2015年第6期999-1007,共9页
Acta Scientiarum Naturalium Universitatis Pekinensis
基金
中国工程物理研究院科学技术发展基金(2012A0403021)
深圳技术创新计划(CXZZ20120831104503786)资助
关键词
目标跟踪
人机交互
分情况检测
搜索框
object tracking
human-machine interaction
distinguishing detection
searching box
