Convolutional neural networks (CNNs) have been increasingly used in remote sensing scene classification/recognition. The conventional CNNs are sensitive to the rotation of the image scene, which will inevitably result in the misclassification of remote sensing scene images that belong to the same category. In this work, we equip the networks with a new pooling strategy, “concentric circle pooling”, to alleviate the above problem. The new network structure, called CCP-net can generate a concentric circle-based spatial-rotation-invariant representation of an image, hence improving the classification accuracy. The square kernel is adopted to approximate the circle kernels in concentric circle pooling, which is much more efficient and suitable for CNNs to propagate gradients. We implement the training of the proposed network structure with standard back-propagation, thus CCP-net is an end-to-end trainable CNNs. With these advantages, CCP-net should in general improve CNN-based remote sensing scene classification methods. Experiments using two publicly available remote sensing scene datasets demonstrate that using CCP-net can achieve competitive classification results compared with the state-of-art methods.

Deep convolutional neural networks (DCNNs) have shown significant improvements in remote sensing image scene classification for powerful feature representations. However, because of the high variance and volume limitations of the available remote sensing datasets, DCNNs are prone to overfit the data used for their training. To address this problem, this paper proposes a novel scene classification framework based on a deep Siamese convolutional network with rotation invariance regularization. Specifically, we design a data augmentation strategy for the Siamese model to learn a rotation invariance DCNN model that is achieved by directly enforcing the labels of the training samples before and after rotating to be mapped close to each other. In addition to the cross-entropy cost function for the traditional CNN models, we impose a rotation invariance regularization constraint on the objective function of our proposed model. The experimental results obtained using three publicly-available scene classification datasets show that the proposed method can generally improve the classification performance by 2~3% and achieves satisfactory classification performance compared with some state-of-the-art methods.

The Lhasa to Nyingchi Expressway in Xizang made efforts to protect the ecological environment during its construction, but it still caused varying degrees of damage to the fragile ecosystems along the route. Accurately assessing the process of change in the ecological environment quality in this region holds significant research value. This study selected the Linzhi-to-Gongbo’gyamda section of the Lhasa-to-Nyingchi Expressway as the research area. Firstly, based on the remote sensing ecological index (RSEI), this study constructed an ecological environmental quality evaluation system for the Xizang region. Subsequently, using the Google Earth Engine (GEE) platform, sub-indicators were extracted, and the combination weighting method of game theory was employed to determine indicator weights. This process resulted in the calculation of the MRSEI for the study area from 2012 to 2020. Finally, by utilizing the spatial distribution of the MRSEI, monitoring the level of MRSEI changes, and employing the transition matrix, this study analyzed the changing trend of the ecological environmental quality from 2012 to 2020. The results indicate that the MRSEI are 0.5885, 0.5951, 0.5296, 0.6202, 0.59, 0.5777, 0.5898, 0.5703, and 0.5987, showing a gradual increasing trend with an initial decrease followed by an ascent. This trend is mainly attributed to concentrated road construction and subsequent ecological restoration, leading to an improvement in the restoration effect. Simultaneously, the ecological environmental quality remains relatively stable, with 69.5% of the region showing no change, and the remaining 30.5% experiencing improvement exceeding degradation. Specifically, there were significant improvements in the land with ecological quality levels categorized as poor, fair, moderate, and good. The types of degradation primarily involved lands originally classified as excellent and good degrading to good and moderate levels, respectively. The above results serve as a theoretical reference for the ecological restoration project of the Lhasa-to-Nyingchi Expressway.

Most existing deep learning-based methods use feature maps extracted from convolutional neural networks (CNNs) for classification and detection of high-resolution remote sensing images (HRSI). However, directly applying these features to classification and object detection in HRSI is problematic because of rotational variations. In this work, we design networks using the polycentric circle pooling (PCP) strategy to alleviate the above problem. The PCP network (PCP-net) structure can generate a fixed-length representation for different input image sizes and encode rotation-invariant information. With these advantages, PCP-net should in general improve the CNN-based HRSI classification methods. Specifically, on the basis of the concentric circle pooling network structure, we improve the structure using multiple concentric circle centers to generate more robust rotation-invariant information. Using two challenging HRSI scene datasets, we prove that PCP-net improves the accuracy of CNN architectures for scene classification tasks. PCP-net can be conveniently applied to object detection because the output size is fixed regardless of image size. Experiments applying the Faster region-CNN to a publicly available 10-class object detection dataset demonstrate that our proposed polycentric circle pooling can achieve accuracy higher than that of region of interest pooling in the HRSI object detection task.

Benggang is a typical erosional landform in southern and southeastern China. Since benggang poses significant risks to local ecological environments and economic infrastructure, it is vital to accurately detect benggang-eroded areas. Relying only on remote sensing imagery for benggang detection cannot produce satisfactory results. In this study, we propose integrating high-resolution Digital Orthophoto Map (DOM) and Digital Surface Model (DSM) data for efficient and automatic benggang discovery. The fusion of complementary rich information hidden in both DOM and DSM data is realized by a two-stream convolutional neural network (CNN), which integrates aggregated terrain and activation image features that are both extracted by supervised deep learning. We aggregate local low-level geomorphic features via a supervised diffusion-convolutional embedding branch for expressive representations of benggang terrain variations. Activation image features are obtained from an image-oriented convolutional neural network branch. The two sources of information (DOM and DSM) are fused via a gated neural network, which learns the most discriminative features for the detection of benggang. The evaluation of a challenging benggang dataset demonstrates that our method exceeds several baselines, even with limited training examples. The results show that the fusion of DOM and DSM data is beneficial for benggang detection via supervised convolutional and deep fusion networks.