Object detection in high spatial resolution remote sensing images (HSRIs) is an important part of image information automatic extraction, analysis, and understanding. The region of interest (ROI) scale of object detection and the object feature representation are two vital factors in HSRI object detection. With respect to these two issues, this article presents a novel HSRI object detection method based on convolutional neural networks (CNNs) with suitable object scale features. First, the suitable ROI scale of object detection is obtained by compiling statistics for the scale range of objects in HSRIs. Then, a CNN framework for object detection in HSRIs is designed using a suitable ROI scale of object detection. The object features obtained using a CNN have good universality and robustness. Finally, a CNN framework with a suitable ROI scale of object detection is trained and tested. Using the WHU-RSONE data set, the proposed method is compared with the faster region-based CNN (Faster-RCNN) framework. The experimental results show that the proposed method outperforms the Faster-RCNN framework and provides good object detection results in HSRIs.

Image segmentation is the foundation of object-based image analysis, and many researchers have sought optimal segmentation results. The initial image oversegmentation and the optimal segmentation scale are two vital factors in high spatial resolution remote sensing image segmentation. With respect to these two issues, a novel image segmentation method combining superpixels with a minimum spanning tree is proposed in this paper. First, the image is oversegmented using a simple linear iterative clustering algorithm to obtain superpixels. Then, the superpixels are clustered by regionalization with a dynamically constrained agglomerative clustering and partitioning (REDCAP) algorithm using the initial number of segments, and the local variance (LV) and the rate of LV change (ROC-LV) indicator diagrams corresponding to the number of segments are obtained. The suitable number of image segments is determined according to the LV and ROC-LV indicator diagrams corresponding to the number of segments. Finally, the superpixels are reclustered using the REDCAP algorithm based on the suitable number of image segments to obtain the image segmentation result. Through two sets of experiments, the proposed method is compared with two other segmentation algorithms. The experimental results show that the proposed method outperforms the others and obtains good image segmentation results.

In high-resolution earth observation systems, object detection in high spatial resolution remote sensing images (HSRIs) is the key technology for automatic extraction, analysis and understanding of image information. With respect to the multi-angle features of object orientation in HSRIs object detection, this paper presents a novel HSRIs object detection method based on convolutional neural networks (CNN) with adaptive object orientation features. First, an adaptive object orientation regression method is proposed to obtain object regions in any direction. In the adaptive object orientation regression method, five coordinate parameters are used to regress the object region with any direction. Then, a CNN framework for object detection of HSRIs is designed using the adaptive object orientation regression method. Using multiple object detection datasets, the proposed method is compared with some state-of-the-art object detection methods. The experimental results show that the proposed method can more accurately detect objects with large aspect ratios and densely distributed objects than some state-of-the-art object detection methods using a horizontal bounding box, and obtain better object detection results for HSRIs.

As a significant and cost-effective method of obtaining shallow seabed topography, satellite derived bathymetry (SDB) can acquire a wide range of shallow sea depth by integrating a small quantity ofin-situwater depth data. This method is a beneficial addition to traditional bathymetric topography. The seafloor’s spatial heterogeneity leads to inaccuracies in bathymetric inversion, which reduces bathymetric accuracy. By utilizing multispectral data with multidimensional features, an SDB approach incorporating spectral and spatial information of multispectral images is proposed in this study. In order to effectively increase the accuracy of bathymetry inversion throughout the entire area, first the random forest with spatial coordinates is established to control bathymetry spatial variation on a large scale. Next, the Kriging algorithm is used to interpolate bathymetry residuals, and the interpolation results are used to adjust bathymetry spatial variation on a small scale. The data from three shallow water sites are experimentally processed to validate the method. Compared with other established bathymetric inversion techniques, the experimental results show that the method effectively reduces the error in bathymetry estimation caused by spatial heterogeneity of the seabed, producing high-precision inversion bathymetry with a root mean square error of 0.78 to 1.36 meters.

The linear array push broom imaging mode is widely used for high resolution optical satellites (HROS). Using double-cameras attached by a high-rigidity support along with push broom imaging is one method to enlarge the field of view while ensuring high resolution. High accuracy image mosaicking is the key factor of the geometrical quality of complete stitched satellite imagery. This paper proposes a high accuracy image mosaicking approach based on the big virtual camera (BVC) in the double-camera system on the GaoFen2 optical remote sensing satellite (GF2). A big virtual camera can be built according to the rigorous imaging model of a single camera; then, each single image strip obtained by each TDI-CCD detector can be re-projected to the virtual detector of the big virtual camera coordinate system using forward-projection and backward-projection to obtain the corresponding single virtual image. After an on-orbit calibration and relative orientation, the complete final virtual image can be obtained by stitching the single virtual images together based on their coordinate information on the big virtual detector image plane. The paper subtly uses the concept of the big virtual camera to obtain a stitched image and the corresponding high accuracy rational function model (RFM) for concurrent post processing. Experiments verified that the proposed method can achieve seamless mosaicking while maintaining the geometric accuracy.

The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) can obtain underwater elevation due to its strong penetration ability. However, the photons recorded by ICESat-2 include a large amount of noise that needs to be removed. Although density-based clustering methods can finish signal photon extraction, heterogeneous density and weak connectivity in photon data distribution impede their denoising performance, especially for sparse signals in deep water and drastic topographic change areas. In this paper, a novel fused denoising method based on the local outlier factor and inverse distance metric is proposed to overcome the above problems. The local outlier factor and inverse distance metric are calculated based on K-nearest neighbors (KNNs), taking into account not only the difference in density but also the directional uniformity of the data distribution. Using six trajectories under various seabed topographies, the proposed method is compared with state-of-the-art ICESat-2 photon denoising algorithms and official ATL03 results. The results indicate that the overall accuracy of the proposed method can surpass 96%, and the proposed method maintains higher recall but also has a lower false positive rate. Compared with the results of other methods, the proposed method can better adopt areas with abrupt topographic changes and deep water. The extracted signal strips are more unbroken and continuous. This study can contribute to pioneering a new perspective for ICESat-2 photon-counting data denoising research that is limited to using only density-based algorithms.