基于人计算的小鼠行为识别

Mouse behavior recognition based on human computation

已有的计算机视觉自动分析系统很难准确识别小鼠行为,因此普遍采用专家对大量的视频图像进行行为标注的方法获得真实值,但专家标注存在一定的主观误判。针对上述问题,提出将人计算思想应用于小鼠行为识别中,让人辅助计算机识别小鼠行为。首先利用人在视觉感知等方面的优势,以及网络的分众、协同性,把人作为分布式个体处理单元,将小鼠行为视频按帧分配给网络上的人,同一帧图像由若干人进行行为分类;然后计算机系统对所有有效的分类结果进行统计、分析和处理,实现对视频图像序列的行为分类。实验表明,该方法在有限代价下,能够有效地提高小鼠行为的正确识别率。

The mouse behaviors cannot be accurately recognized by the existing computer vision-based automatic analysis system, and the ground truth is generally achieved from experts＇ annotation on a massive number of video images. However, to some extent, subjective misjudgments are unavoidable. To solve these problems, a human computation-based mouse behavior recognition method was proposed in this paper. Because of the superiority of human visual perception, and the decentralization and cooperation of the Internet, human brains were treated as processors in a distributed system. Firstly, every mouse behavior frames were distributed to on-line individuals randomly, and each behavior frame was classified by a large number of on-line individuals. Secondly, all the effective classifications from the on-line individuals were collected, analyzed and processed by computer system, thus realizing the final mouse behavior classification based on these frame sequences. The experimental results show that the proposed method is effective to improve the correct recognition rate of mouse behaviors with limited cost.