Abstract:

Superpixels exhibit excellent image representation capability and high computational efficiency， which are widely applied in subsequent computer vision tasks. However， existing superpixel segmentation algorithms fail to fully integrate semantic and spatial information， resulting in insufficient spatial coherence and semantic consistency of the generated superpixels， as well as blurred and misclassified details when processing images with complex scenes. To address these problems， this paper proposed a Superpixel Segmentation algorithm based on the Inverted Feature Pyramid Network （SSIFPNet）. Through the cascaded coupling of an encoder and an Inverted Feature Pyramid Network （IFPN） decoder， the proposed algorithm better fused end-to-end multi-scale semantic information and spatial detail information. Meanwhile， a perceptual boundary-driven composite loss function was designed to further improve the semantic consistency of superpixels. Comparative experiments on the BSDS500， NYUv2， and KITTI datasets were conducted to compare SSIFPNet with state-of-the-art algorithms， including the Simple Linear Iterative Clustering superpixel segmentation algorithm （SLIC）， Superpixel Sampling Network （SSN）， and Superpixel segmentation algorithm with fully Convolutional neural Network （SCN）. Experimental results show that SSIFPNet achieves superior performance across all datasets. Specifically， the achievable segmentation accuracy （ASA） and Boundary Precision （BP） of SSIFPNet reach 0.972 0 and 0.130 6 on the BSDS500 dataset， 0.948 2 and 0.199 9 on the NYUv2 dataset， and 0.965 5 and 0.147 0， along with a COmpactness （CO） of 0.372 0， on the KITTI dataset. It is demonstrated that the superpixels generated by SSIFPNet possess favorable spatial coherence and semantic consistency and achieve superior performance in processing detailed texture regions， which fully demonstrates the superiority and generalizability of SSIFPNet.

Key words: superpixel segmentation, Inverted Feature Pyramid Network (IFPN), perceptual boundary driven, U-Net, multi-scale fusion

摘要：

超像素具有优异的图像表示能力和高计算效率，已经被广泛应用于后续的计算机视觉任务。然而，现有的超像素分割算法未充分考虑语义信息与空间信息的融合关系，导致生成的超像素空间连贯性和语义一致性不足，在处理复杂场景图像时会出现模糊错分细节的问题。针对这些问题，本文提出一种基于倒置特征金字塔网络的超像素分割算法（SSIFPNet）。通过编码器和倒置特征金字塔网络（IFPN）解码器的级联耦合，更好地融合端到端的多尺度语义信息与空间细节信息。同时，设计一个以感知边界驱动的复合损失函数，进一步提升超像素的语义一致性。SSIFPNet在BSDS500、NYUv2和KITTI这3个数据集上和简单线性迭代聚类超像素分割算法（SLIC）、超像素采样网络（SSN）和基于全卷积神经网络的超像素分割算法（SCN）等算法进行对比实验。实验结果表明，SSIFPNet在BSDS500数据集上的可达分割精度（ASA）和边界精确率（BP）分别提升至0.972 0和0.130 6，在NYUv2数据集上的ASA和BP分别提升至0.948 2和0.199 9，在KITTI数据集上ASA、BP和紧凑性（CO）分别提升至0.965 5、0.147 0和0.372 0。可见，SSIFPNet生成的超像素不仅展现出较好的空间连贯性和语义一致性，同时在细节纹理区域的处理表现优越，充分验证了SSIFPNet的优越性和泛化性。

关键词: 超像素分割, 倒置特征金字塔网络, 感知边界驱动, U-Net, 多尺度融合