基于机器视觉的鱼类模式生物在线监测技术方法研究

水污染的防治问题是我国关注的重中之重,现有理化监测方法的实时性和综合性较差,特别是对于一些极端可变化的环境,更需要新的方法以辅助和解决。生物式水质监测方法被提出,通过利用生物对环境污染或变化所产生的反应来直接或间接体现水质的污染情况。然而,观测指标与量化标准是面临的一大难题。文章利用机器视觉的方法,以青鳉鱼为模式生物,并以青鳉鱼的生理特征以及运动特征(呼吸频率、胸鳍摆动频率、摆尾频率)为观测指标,两方面综合评定青鳉鱼应激状态,实时监测与分析。实验结果表明该方法能为生物式水质监测和预警的发展提供一定支持与参考。测得青鳉鱼呼吸频率为3.06 Hz,胸鳍摆动频率为4.83 Hz,尾鳍摆动频率为5.08 Hz,结果与实际指标一致。

Study on the Method of Fish Model Organism On-line Monitoring Technology Based on Machine Vision

Prevention and control of water pollution is a top-priority issue in China. The real-time and comprehensive performance of the existing physical and chemical monitoring methods are poor. Especially, some new approaches are required to assist and resolve in the extremely variable environment. Thus, a biological method of water quality monitoring is proposed in this paper. The water quality is detected by the biological response to reflect the direct or indirect water pollution. However, the observation indexes and quantitative criteria are major problems to estimate in the complex water environment. To this end, the medaka fish is chosen as the model organism, and the corresponding physiological characteristics and movement characteristics is observation indexes, such as breathing frequency, pectoral oscillation frequency, tail beat frequency, and etc. By adopting machine vision based method, the real-time monitoring and analysis are achieved. Experiments were performed under the clean water conditions, and multiple sets of images were captured and the above indexes were estimated. The measured breathing frequency of medaka fish was 3.06 Hz, the pectoral oscillation frequency was 4.83 Hz and the tail beat frequency was 5.08 Hz, all of which are consistent with the actual index. Experimental results show that the proposed method can provide the support and reference for the development of bio-type water quality monitoring and early warning.