基于改进RetinaNet网络的水下机器人目标检测与实验

Underwater vehicle target detection and experiment based on improved RetinaNet network

针对目前水下机器人目标检测算法存在图像退化严重和目标识别率低的问题,提出了一种融合改进RetinaNet和注意力机制的水下目标检测算法。首先,把RetinaNet骨干网络替换成DenseNet网络,保留了更多目标特征并减少了参数量。其次,替换初始卷积为深度分离可变形卷积,从而大大减少了模型的参数量,提高了模型的运算速度。最后,引入CBAM注意力模块,利用CBAM模块在空间和通道2个维度加强特征,减少了水下复杂环境对目标检测的干扰。水下机器人抓取实验结果表明,与初始的RetinaNet算法相比,改进后的算法mAP值可达81.9%,参数量为56.8 MB,检测速度为16.8 f/s,在水下目标检测方面性能优异。

Aiming at the problems of serious image degradation and low target recognition rate in current underwater vehicle target detection methods,an underwater target detection method combining improved RetinaNet and attention mechanism is proposed.Firstly,RetinaNet backbone network is replaced with DenseNet network,which retains more target features and reduces the number of parameters.Secondly,in order to increase the operation speed of the network model,the initial convolution is replaced by the depth separated deformable convolution,thus greatly reducing the parameters of the model.Finally,CBAM attention module is introduced to enhance features in space and channel dimensions,reducing the interference of underwater complex environment to target detection.The experimental results of underwater robot grasping show that compared with the initial RetinaNet methods,The mAP value of the improved method can reach 81.9%,the parameters are 56.8 MB,and the detection speed is 16.8 frames.The improved method has excellent performance in underwater target detection.