Existing satellite remote sensing change detection (CD) methods often crop large-scale bitemporal image pairs into small patch pairs and then use pixel-level CD methods for fair processing. However, due to the sparsity of change, existing pixel-level methods suffer from a waste of computational cost and memory resources on many unchanged areas, which reduces the processing efficiency on hardware platforms with extremely limited computation and memory resources. To address this issue, we propose a lightweight patch-level CD network (LPCDNet) to rapidly remove a lot of unchanged patch pairs in large-scale bitemporal optical image pairs, helping to accelerate the subsequent pixel-level CD process and reduce memory cost. In our LPCDNet, a sensitivity-guided network pruning method is proposed to remove unimportant channels and construct the lightweight backbone network based on the ResNet18 network. Then, the multilayer feature compression (MLFC) module with multiscale max-pooling structure is designed to compress and fuse the multilevel feature information of image patches. The output of MLFC module is fed into the fully connected decision network to generate the predicted binary label. Finally, a weighted cross-entropy loss is utilized in the training process to tackle the change/unchanged class imbalance problem. Experiments on two CD datasets demonstrate that our LPCDNet achieves more than 1000 frames/s on an edge computation platform, i.e., NVIDIA Jetson AGX Orin, which is more than three times that of the existing methods without noticeable performance loss. In addition, the computational cost of the pixel-level CD processing stage can be reduced by more than 60%.

中文翻译：

---

基于多层特征压缩和灵敏度引导网络剪枝的轻量级补丁级变化检测网络


现有的卫星遥感变化检测（CD）方法通常将大规模双时图像对裁剪成小块对，然后使用像素级CD方法进行公平处理。然而，由于变化的稀疏性，现有的像素级方法在许多未变化的区域上浪费了计算成本和内存资源，这降低了计算和内存资源极其有限的硬件平台上的处理效率。为了解决这个问题，我们提出了一种轻量级的补丁级 CD 网络（LPCDNet），可以快速去除大规模双时光学图像对中大量未更改的补丁对，有助于加速后续的像素级 CD 过程并降低内存成本。在我们的LPCDNet中，提出了一种敏感性引导的网络剪枝方法来删除不重要的通道，并基于ResNet18网络构建轻量级骨干网络。然后，设计具有多尺度最大池结构的多层特征压缩（MLFC）模块来压缩和融合图像块的多级特征信息。 MLFC 模块的输出被馈送到全连接决策网络中以生成预测的二进制标签。最后，在训练过程中利用加权交叉熵损失来解决变化/不变类不平衡问题。在两个 CD 数据集上的实验表明，我们的 LPCDNet 在边缘计算平台（即 NVIDIA Jetson AGX Orin）上实现了超过 1000 帧/秒，是现有方法的三倍以上，且没有明显的性能损失。此外，像素级CD处理阶段的计算成本可降低60%以上。