海产品智能分拣装备与系统设计

目的：解决当前中国水产行业分选加工效能不足、准确率低、成本高的现状问题。方法：选用智能机器人与传统机械相结合开发新的机械结构对海产品进行分级；同时运用基于机器视觉的智能识别技术对海产品进行分类(采用了适应海产品的改进的新型Faster R-CNN算法)，协同构建了一个能够智能、高效、自动分拣海产品的装备系统。结果：改进的新型Faster R-CNN算法识别技术在海产品检测中具有更高的检测准确率(海螺75.1%，扇贝80.3%，贻贝82.9%，蛤蜊86.2%)。结论：装备系统可以代替传统的人工操作模式，完成海产品的智能分拣过程。

Intelligent sorting equipment and system design of seafood

Objective:Aiming at the present situation of low efficiency, low accuracy and high cost in the sorting and processing of fishery industry in China, the intelligent sorting equipment and system of seafood based on robot was developed.Methods:Using the combination of intelligent robot and traditional machinery to develop a new mechanical structure to classify seafood, an intelligent recognition technology based on machine vision was used to classify seafood (the improved novel Faster R-CNN algorithm was adopted for seafood), and an equipment system that could automatically sort seafood intelligently, efficiently was constructed.Results:The improved novel Faster R-CNN algorithm has high detection accuracy in seafood detection.Conclusion:The equipment system can replace the traditional manual operation mode and complete the intelligent sorting process of seafood.