School of Physics and Microelectronics, Zhengzhou University, Zhengzhou 450001, China.
Institute of Optoelectronic Information Science, Zhengzhou University, Zhengzhou 450001, China.
Sensors (Basel). 2023 Apr 25;23(9):4261. doi: 10.3390/s23094261.
The identification of wear rubber balls in the rubber ball cleaning system in heat exchange equipment directly affects the descaling efficiency. For the problem that the rubber ball image contains impurities and bubbles and the segmentation is low in real time, a multi-scale feature fusion real-time instance segmentation model based on the attention mechanism is proposed for the object segmentation of the rubber ball images. First, we introduce the Pyramid Vision Transformer instead of the convolution module in the backbone network and use the spatial-reduction attention layer of the transformer to improve the feature extraction ability across scales and spatial reduction to reduce computational cost; Second, we improve the feature fusion module to fuse image features across scales, combined with an attention mechanism to enhance the output feature representation; Third, the prediction head separates the mask branches separately. Combined with dynamic convolution, it improves the accuracy of the mask coefficients and increases the number of upsampling layers. It also connects the penultimate layer with the second layer feature map to achieve detection of smaller images with larger feature maps to improve the accuracy. Through the validation of the produced rubber ball dataset, the Dice score, Jaccard coefficient, and mAP of the actual segmented region of this network with the rubber ball dataset are improved by 4.5%, 4.7%, and 7.73%, respectively, and our model achieves 33.6 fps segmentation speed and 79.3% segmentation accuracy. Meanwhile, the average precision of Box and Mask can also meet the requirements under different IOU thresholds. We compared the DeepMask, Mask R-CNN, BlendMask, SOLOv1 and SOLOv2 instance segmentation networks with this model in terms of training accuracy and segmentation speed and obtained good results. The proposed modules can work together to better handle object details and achieve better segmentation performance.
在换热设备的橡胶球清洗系统中，识别出磨损的橡胶球直接影响除垢效率。针对实时橡胶球图像中存在杂质和气泡，分割率低的问题，提出了一种基于注意力机制的多尺度特征融合实时实例分割模型，用于橡胶球图像的目标分割。首先，我们在骨干网络中引入了 Pyramid Vision Transformer 代替卷积模块，利用变压器的空间降维注意力层提高跨尺度的特征提取能力和空间降维以降低计算成本；其次，我们改进了特征融合模块，以融合跨尺度的图像特征，结合注意力机制增强输出特征表示；第三，预测头分别分离掩模分支。结合动态卷积，提高了掩模系数的准确性，增加了上采样层的数量。它还将倒数第二层与第二层特征图连接起来，以用更大的特征图检测更小的图像，从而提高准确性。通过对生成的橡胶球数据集进行验证，该网络在橡胶球数据集上的实际分割区域的 Dice 分数、Jaccard 系数和 mAP 分别提高了 4.5%、4.7%和 7.73%，并且我们的模型实现了 33.6 fps 的分割速度和 79.3%的分割精度。同时，Box 和 Mask 的平均精度也可以在不同的 IOU 阈值下满足要求。我们将 DeepMask、Mask R-CNN、BlendMask、SOLOv1 和 SOLOv2 实例分割网络与该模型在训练精度和分割速度方面进行了比较，并取得了较好的结果。所提出的模块可以协同工作，更好地处理对象细节，实现更好的分割性能。
