基于单回波检测跟踪的深水网箱生物量评估模型研究  

Research on a novel biomass estimation model for deep water net cages based on single echo detection and tracking

作　　者：黄健[1] 关长涛[2] 汤涛林[1] 李娇[2] 

机构地区：[1]中国水产科学研究院渔业机械仪器研究所农业部渔业装备与工程重点开放实验室,上海200092 [2]中国水产科学研究院黄海水产研究所,青岛266071

出　　处：《渔业现代化》2008年第6期9-13,共5页Fishery Modernization

基　　金：国家"863"高技术研发计划项目(2006AA100302)

摘　　要：构造了基于声纳信号处理的深水网箱生物量评估数学模型。运用单回波脉宽检测和跟踪方法,结合二维低通滤波器,对声纳数据进行处理,去除背景噪声和其他回波,在单体鱼连续的回波踪迹中可以检测出鱼的游速和方向。同时,结合图像分析有效压缩噪声,提取有用特征来识别检测到的鱼迹,形成一种自动计数方法,提高生物量的检测概率。该方法通过提取和使用原始的回声图像,检测出运动目标,同时压缩回声图中的噪声,从而在低信噪比数据中实现对网箱中生物量的检测和估计,适合实际工程应用。The mathematical model for biomass estimation in deep water net cages is constructed based on sonar signal processing. Signal echo detection and tracking ter is applied to process sonar data in order to dismiss speed and direction of a single fish can be detected from method for pulse width together with 2-D low-pass filbackground noises and other echoes. The swimming its continuous echo track. Image analysis is also added to compress noises efficiently and pick up useful features to identify detected fish tracks, and then produce an automatic counting method to improve the biomass detection probability. This method is used to detect moving objects and compress image noises by picking up and employing original echo images, and accordingly achieves the detection and estimation for the biomass by means of low signal to noise ratio data, which is suitable for engineering application.

关 键 词：单回波检测 低通滤波 深水网箱 生物量评估 

分 类 号：S646.903.5[农业科学—蔬菜学] TP391.41[农业科学—园艺学]