School of Automation, Beijing Information Science and Technology University, Beijing 100192, China.
Computer School, Beijing Information Science and Technology University, Beijing 100192, China.
Comput Intell Neurosci. 2022 Mar 3;2022:1712258. doi: 10.1155/2022/1712258. eCollection 2022.
In this paper, we first propose an accurate edge detector using a distance field-based convolutional neural network (DF-CNN). In recent years, CNNs have been proved to be effective in image processing and computer vision. As edge detection is a fundamental problem among them, we try to improve the accuracy of edge detection based on the deep learning framework. The proposed network combines a feature extraction backbone that can fully exploit the multiscale and multilevel information of the edge with the supervised training of the distance field branch to realize the accurate end-to-end object edge detection. The distance field branch is applied to predict the Euclidean distance from nonedge points to the nearest edge point in the feature maps. And the distance information embedded in the predicted distance field map can effectively improve the accuracy of edge detection. The network is trained to minimize the weighted sum of the distance field branch loss and the cross-entropy loss. Our experimental results show that the proposed edge detector achieves better performance than previous approaches and the effectiveness of the proposed distance field branch.
在本文中，我们首先提出了一种基于距离场的卷积神经网络（DF-CNN）的精确边缘检测器。近年来，CNN 在图像处理和计算机视觉中已被证明是有效的。由于边缘检测是其中的一个基本问题，我们试图基于深度学习框架来提高边缘检测的准确性。所提出的网络结合了特征提取主干，可以充分利用边缘的多尺度和多层次信息，以及距离场分支的监督训练，以实现精确的端到端目标边缘检测。距离场分支用于预测特征图中非边缘点到最近边缘点的欧几里得距离。嵌入在预测距离场图中的距离信息可以有效地提高边缘检测的准确性。网络的训练目标是最小化距离场分支损失和交叉熵损失的加权和。我们的实验结果表明，所提出的边缘检测器比以前的方法和所提出的距离场分支具有更好的性能。
