Xian Sun

Automatic Target Detection in High-Resolution Remote Sensing Images Using Spatial Sparse Coding Bag-of-Words Model

Automatic detection for targets with complex shape in high-resolution remote sensing images is a challenging task. In this letter, we propose a new detection framework based on spatial sparse coding bag-of-words (BOW) (SSCBOW) model to solve this problem. Specifically, after selecting a processing unit by the sliding window and extracting features, a new spatial mapping strategy is used to encode the geometric information, which not only represents the relative position of the parts of a target but also has the ability to handle rotation variations. Moreover, instead of K-means for visual-word encoding in the traditional BOW model, sparse coding is introduced to achieve a much lower reconstruction error. Finally, the SSCBOW representation is combined with linear support vector machine for target detection. The experimental results demonstrate the precision and robustness of our detection method based on the SSCBOW model.

Automatic Annotation of Satellite Images via Multifeature Joint Sparse Coding With Spatial Relation Constraint

In this letter, we propose a novel framework for large-satellite-image annotation using multifeature joint sparse coding (MFJSC) with spatial relation constraint. The MFJSC model imposes an l1, 2-mixed-norm regularization on encoded coefficients of features. The regularization will encourage the coefficients to share a common sparsity pattern, which will preserve the cross-feature information and eliminate the constraint that they must have identical coefficients. Spatial dependences between patches of large images are useful for the annotation task but are usually ignored or insufficiently exploited in other methods. In this letter, we design a spatial-relation-constrained classifier to utilize the output of MFJSC and the spatial dependences to annotate images more precisely. Experiments on a data set of 21 land-use classes and QuickBird images show the discriminative power of MFJSC and the effectiveness of our annotation framework.

A New Method on Inshore Ship Detection in High-Resolution Satellite Images Using Shape and Context Information

In this letter, we present a new method to detect inshore ships using shape and context information. We first propose a new energy function based on an active contour model to segment water and land and minimize it with an iterative global optimization method. The proposed energy performs well on the different intensity distributions between water and land and produces a result that can be well used in shape and context analyses. In the segmented image, ships are detected with successive shape analysis, including shape analysis in the localization of ship head and region growing in computing the width and length of ship. Finally, to locate ships accurately and remove the false alarms, we unify them with a binary linear programming problem by utilizing the context information. Experiments on QuickBird images show the robustness and precision of our method.

Object Detection in High-Resolution Remote Sensing Images Using Rotation Invariant Parts Based Model

In this letter, we propose a rotation invariant parts-based model to detect objects with complex shape in high-resolution remote sensing images. Specifically, the geospatial objects with complex shape are firstly divided into several main parts, and the structure information among parts is described and regulated in polar coordinates to achieve the rotation invariance on configuration. Meanwhile, the pose variance of each part relative to the object is also defined in our model. In encoding the features of the rotated parts and objects, a new rotation invariant feature is proposed by extending histogram oriented gradients. During the final detection step, a clustering method is introduced to locate the parts in objects, and that method can also be used to fuse the detection results. By this way, an efficient detection model is constructed and the experimental results demonstrate the robustness and precision of our proposed detection model.

Aircraft Recognition in High-Resolution Satellite Images Using Coarse-to-Fine Shape Prior

Automatic aircraft recognition in high-resolution satellite images has many important applications. Due to the diversity and complexity of fore-/background, recognition using pixel-based methods usually does not perform well. In this letter, we propose a new method integrating the high-level information of a shape prior, which is considered as a coarse-to-fine process. In the coarse stage, the pose of an aircraft is roughly estimated by a single template matching with a defined score criterion. In the fine stage, we derive a parametric shape model by applying principal component analysis and kernel density function, which have good effects on both dimension reduction and sample space description; then, a new variational formulation combining region information and a shape prior is proposed to segment the object using a level set method. Finally, the parameters of the segmentation result are directly applied to verify aircraft type with two k-nearest neighbor steps. Experiments on QuickBird images demonstrate the robustness and accuracy of the proposed method.

Efficient Saliency-Based Object Detection in Remote Sensing Images Using Deep Belief Networks

Object detection has been one of the hottest issues in the field of remote sensing image analysis. In this letter, an efficient object detection framework is proposed, which combines the strength of the unsupervised feature learning of deep belief networks (DBNs) and visual saliency. In particular, we propose an efficient coarse object locating method based on a saliency mechanism. The method could avoid an exhaustive search across the image and generate a small number of bounding boxes, which can locate the object quickly and precisely. After that, the trained DBN is used for feature extraction and classification on subimages. The feature learning of the DBN is operated by pretraining each layer of restricted Boltzmann machines (RBMs) using the general layerwise training algorithm. An unsupervised blockwise pretraining strategy is introduced to train the first layer of RBMs, which combines the raw pixels with a saliency map as inputs. This makes an RBM generate local and edge filters. The precise edge position information and pixel value information are more efficient to build a good model of images. Comparative experiments are conducted on the data set acquired by QuickBird with a 60-cm resolution. The results demonstrate the accuracy and efficiency of our method.

Automatic Target Detection in High-Resolution Remote Sensing Images Using a Contour-Based Spatial Model

In this letter, we propose a contour-based spatial model which can detect geospatial targets accurately in high-resolution remote sensing images. To detect the geospatial targets with complex structures, each image was partitioned into pieces as target candidate regions using multiple segmentations at first. Then, the automatic identification of target seed regions is achieved by computing the similarity of the contour information with the target template using dynamic programming. Finally, the contour-based similarity was further updated and combined with spatial relationships to figure out the missing parts. In this way, a more accurate target detection result can be achieved. The precision, robustness, and effectiveness of the proposed method were demonstrated by the experimental results.

Automatic Detection of Inshore Ships in High-Resolution Remote Sensing Images Using Robust Invariant Generalized Hough Transform

In this letter, we propose a new detection framework based on robust invariant generalized Hough transform (RIGHT) to solve the problem of detecting inshore ships in high-resolution remote sensing imagery. The invariant generalized Hough transform is an effective shape extraction technique, but it is not adaptive to shape deformation well. In order to improve its adaptability, we use an iterative training method to learn a robust shape model automatically. The model could capture the shape variability of the target contained in the training data set, and every point in the model is equipped with an individual weight according to its importance, which greatly reduces the false-positive rate. Through the iteration process, the model performance is gradually improved by extending the shape model with these necessary weighted points. Experimental result demonstrates the precision, robustness, and effectiveness of our detection framework based on RIGHT.

Automatic Detection of Geospatial Objects Using Taxonomic Semantics

In this letter, we propose a novel method to solve the problem of detecting geospatial objects present in high-resolution remote sensing images automatically. Each image is represented as a segmentation tree by applying a multiscale segmentation algorithm at first, and all of the tree nodes are described as coherent groups instead of binary classified values. The trees are matched to select the maximally matched subtrees, denoted as common subcategories. Then, we organize these subcategories to learn the embedded taxonomic semantics of objects categories, which allow categories to be defined recursively, and express both explicit and implicit spatial configuration of categories. Detection, recognition, and segmentation of the geospatial objects in a new image can be simultaneously conducted by using the learned taxonomic semantics. This procedure also provides a meaningful explanation for image understanding. Experiments for complex and compound objects demonstrate the precision, robustness, and effectiveness of the proposed method.

A Geometrical-Based Simulator for Target Recognition in High-Resolution SAR Images

Target recognition in high-resolution synthetic aperture radar (SAR) images is a challenging task. In this letter, a novel geometrical-based SAR image simulator is proposed to assist target recognition. Specifically, in addition to the using of Lamberitian-specular mixed model for single-bounce simulation, we propose a dihedral corner model for double-bounce simulation, which allows directly retrieving structure information from scattering patterns. In addition, a dihedral tracing technique is taken instead of ray tracing for double-bounce detection to reduce computation time. Also, a new primitive-by-primitive visualization approach which is well combined with our scattering model is proposed to obtain high efficiency. The efficiency of the simulator is demonstrated by the comparison between the simulated results and MiniSAR images and by the application in vehicle recognition.