一种计量青鳉鱼胸鳍和尾鳍摆动频率和幅值的计算机视觉算法

青鳉鱼在饮用水安全领域具有很高的应用价值,其鱼鳍的活动状态可以反映水质的污染状况。但由于技术条件的限制,传统的方法无法实时而有效地提取到这些特征。针对这个问题,提出了一种可以高效识别并测量青鳉鱼胸、尾鳍摆动频率和幅值的计算机视觉算法。其中,为了快速地提取到这2个细节,自动阈值分割、帧差法、背景差分法、重心法、图像卷积和骨架细化等耗时极短的图像处理方法被应用到这项研究当中。初步试验显示这种算法在应用过程中是高效而可行的。它可以被广泛地应用到水环境监测领域,如研究有毒物质对青鳉鱼行为特性的影响和评估水环境的危险程度。

A Computer Vision Algorithm Which Was Used for Measuring the Oscillation Frequency of the Japanese Medaka' s Pectoral Fin and Caudal Fin

Japanese medaka (Oryzias latipes) has high value of application in the field of drinking water safety. The active state of fins can reflect the pollution status of waters. However, due to the limitation of technical conditions, the traditional methods cannot effectively extract these features in real time. To address this issue, this paper proposed an efficient method based on the computer vision to efficiently identify and measure the swing frequency and amplitude of pectoral and tail fins. Several image processing algorithms, such as automatic threshold segmentation, frame difference, background subtraction, gravity method, image convolution and skeleton thinning, were employed in this paper to extract the details quickly. The preliminary results demonstrated that the proposed method is effective and feasible, and can be widely applied to the field of water environment monitoring, such as the research of toxic substances on the behavior characteristic of medaka, and evaluation of the risk levels of the water environment.