Research in the autonomous underwater detection system has become rapidly increasing in Ocean Technology. In a recent object detection research study, there a need to enhance the quality, which needs to handle submerged object image processing techniques and a lot of demand to develop an intelligent vision system to improve the Blurred Images and low-quality illumination. Manual research in undersea water leads to more significant pressures and complex environments in cost and workforce. It is necessary to develop a high acceptable autonomous image quality system to upgrade image quality. This paper proposed two approaches: (i) Gray shade and Max-RGB filter techniques to improve image quality. (ii) For optimization and low illumination problem modified Convolution Neural Technique (CNN) incorporated for classification and detection. Moreover, our proposed model has compared with Single-shot Detector (SDD), You Only Look Once (Yolo), Fast RCNN, Faster RCNN to uphold the quality detection found objects. This research article aids to found real-time underwater objects classification and detection. It helps to incorporate an Autonomous operation Vehicle (AOV) underwater research. Our experiment results show detection runs speed as 30 FPs (Frame per second).

海洋技术对自主水下探测系统的研究已迅速增加。在最近的物体检测研究中，需要提高质量，这需要处理浸入物体的图像处理技术，并且对开发智能视觉系统以改善模糊图像和低质量照明的需求很高。在海底进行人工研究会导致更大的压力以及成本和劳动力的复杂环境。有必要开发高度可接受的自主图像质量系统以提高图像质量。本文提出了两种方法：（i）灰色阴影和Max-RGB滤镜技术，以提高图像质量。（ii）为了优化和解决低照度问题，采用了改进的卷积神经技术（CNN）进行分类和检测。而且，我们提出的模型已与单发检测器（SDD），“只看一次”（Yolo），快速RCNN，快速RCNN进行了比较，以支持发现的质量检测对象。这篇研究文章有助于发现实时水下物体的分类和检测。它有助于合并自动驾驶飞行器（AOV）水下研究。我们的实验结果表明，检测运行速度为30 FP（每秒帧）。