Due to the rapid development of deep learning techniques and the collection of large-scale remote sensing datasets, convolutional neural networks (CNNs) have made significant progress in remote sensing object detection. However, due to the diversity of objects in remote sensing images, multiscale object detection is still a challenging task. In this letter, a novel object detection framework based on feature pyramid network (FPN) is proposed to improve the detection performance of multiscale objects. First, a receptive field expansion block (RFEB) is designed and added on the top of the backbone to expand the receptive field of FPN adaptively. In this way, the context information around each object is well captured. Then, the features obtained via RFEB are delivered to feature maps at all pyramid levels, remedying the drawback of FPN that semantic information captured by deep layers is gradually diluted when transmitted to lower layers. Third, since the classic backbone of FPN, which produces large receptive fields based on large downsampling factors, may limit the effectiveness of RFEB, the backbone of the original FPN is modified using dilated convolution to ease the resolution drop of feature maps while maintaining a large receptive field. As a feature extractor, the proposed framework can be easily deployed in other FPN-based methods. The experiments on the benchmark for object DetectIon in Optical Remote sensing images (DIOR) dataset demonstrate the proposed method’s superiority over considered state-of-the-art baseline methods in terms of detection accuracy.

Recently, deep learning algorithms, especially feature pyramid network (FPN), have achieved significant progress in object detection of natural scene images. However, due to the complex scenes of remote sensing images and the diversity of remote sensing objects, FPN still faces the following drawback when applied to remote sensing object detection. Specifically, in the original FPN, the features of each proposal are extracted by RoIAlign. However, these features have limited effective receptive fields, making FPN lack of crucial contextual information to accurately classify and locate objects, as well as filter some background noises that possess similar appearance with objects. To alleviate the above problem, in this letter, we propose a gated context aware module (G-CAM), and replace the original RoIAlign in FPN with the proposed G-CAM to adaptively incorporate the useful local context surrounding each proposal and the global context of the whole image into FPN, enabling FPN to effectively detect objects in remote sensing images Extensive experiments have been conducted on the DIOR and RSOD datasets, which validates that the proposed method achieves superior performance to the considered state-of-the-art methods in terms of detection accuracy.

In this letter, a novel object detection method based on feature pyramid network (FPN) is proposed to improve the detection performance of remote sensing objects. First, since the information in the background regions may interfere with object detection, a novel multi-scale deformable attention module (MSDAM) is designed and added on the top of the backbone of FPN to make the network suppress the background features while highlight the target features. The proposed MSDAM generates attention maps from feature maps with multi-scale deformable receptive fields, thus can fit remote sensing objects of various shapes and sizes better and predict more precise attention maps for remote sensing images. Second, in the original FPN, each proposal is predicted based on feature grids pooled from only one feature level. This process is suboptimal as the information discarded in other feature levels and the global contextual information are also meaningful to object detection. Thus, a multi-level features aggregation module (MLFAM) is proposed to aggregate the multi-level outputs of FPN and the global context of the whole image, generating more powerful pyramidal representations for the subsequent object detection. The experiments conducted on the DIOR and RSOD datasets demonstrate the superiority of the proposed method over the considered state-of-the-art baseline methods in terms of detection accuracy.

Remote sensing image registration is valuable for image-based navigation system despite posing many challenges. As the search space of image registration is usually nonconvex, the optimization algorithm, which aims to find the optimal parameters in search space, is a challenging step. Conventional optimization algorithms can hardly reconcile the contradiction of rapid convergence and global optimization. In this letter, a novel learning-based optimization algorithm named image registration optimizer network (IRON) is proposed, which can predict the global optimum straightforwardly. The IRON is trained by a 3-D tensor ($9\times 9\,\,\times9$) which consists of similar metric values. Each value of the 3-D tensor corresponds to the initial parameters’$9 \times 9 \times 9$neighbors in the search space. The 3-D tensor’s label is a vector which points to the global optimal parameters from the initial parameters. Because of the special design, our IRON could predict the global optimum directly. The experimental results demonstrate that the proposed algorithm performs better than other classical optimization algorithms as it shows higher accuracy, lower root-of-mean-square error (RMSE), and more convergence efficiency. The code is publicly available athttps://www.github.com/jaxwangkd04/IRON.

Most of the traditional convolution neural network (CNN)‐based classification models are flat classifiers, which have an underlying assumption that all classes are equally difficult to distinguish. However, visual separability between different object categories is highly uneven in the real world. Recently, hierarchical classification has been proven effective for CNNs, more and more attempts have been made to exploit category hierarchies in CNN models. In this study, the authors propose a novel hierarchical CNN architecture, called coarse‐to‐fine CNN. It is simple, with a proposed coarse‐to‐fine layer on the top of a generic CNN. The coarse‐to‐fine layer is inspired by the Bayesian equation, where the coarse prediction can affect the fine prediction directly. Arbitrary CNNs can perform the hierarchical classification by adding the proposed layer. The training of a coarse‐to‐fine CNN is end‐to‐end, it can be optimised by typical stochastic gradient descent. In the test phase, it outputs multiple hierarchical predictions simultaneously. Experimental results on the benchmark datasets MNIST, CIFAR‐10, and CIFAR‐100 show clear advantages over the compared baselines.

Figure‐ground segmentation is used to extract the foreground from the background, where the foreground is usually defined as the region containing the most meaningful object of the image. In fact, the algorithms that take advantage of human–computer interaction often attain better performance and they are based on the ‘one‐to‐one’ model. In this study, the authors present a novel algorithm for figure‐ground segmentation based on the GrabCut algorithm, which is a common segmentation algorithm that is user interactive. However, instead of a real user, they attempt to use a pre‐trained deep convolutional neural network to interact with GrabCut for completing its job successfully. Weizmann's segmentation evaluation database is used as the test dataset and the results show that their algorithm works well for figure‐ground segmentation. While the previous automatic segmentation algorithms are required to rank their segments empirically in order to find the position of the foreground after the segmentation, their algorithm is fully automatic.

Maximum common sub-graph isomorphism (MCS) is a famous NP-hard problem in graph processing. The problem has found application in many areas where the similarity of graphs is important, for example in scene matching, video indexing, chemical similarity and shape analysis. In this paper, a novel algorithm Qwalk is proposed for approximate MCS, utilizing the discrete-time quantum walk. Based on the new observation that isomorphic neighborhood group matches can be detected quickly and conveniently by the destructive interference of a quantum walk, the new algorithm locates an approximate solution via merging neighborhood groups. Experiments show that Qwalk has better accuracy, universality and robustness compared with the state-of-the-art approximate MCS methods. Meanwhile, Qwalk is a general algorithm to solve the MCS problem approximately while having modest time complexity.

The registration of a forward-looking infrared (FLIR) image and an optical satellite image (visible image) is challenging but important for image-based navigation systems. To solve this problem effectively, a coarse-to-fine matching algorithm is proposed. First, geometric rectification based on the attitude angles and height parameter is carried out to eliminate the distinct rotation and scale discrepancies between the FLIR and visible images. Then, in the fine registration step, the edges of the visible image and rectified infrared image are extracted, and a robust point set registration algorithm which can deal with the similarity transformation distortion is proposed. Finally, the experiments on both the simulated images and real images show that our algorithm can achieve excellent performance in terms of both robustness and accuracy, and the registration precision of real images can be around one pixel.

In the above titled paper (ibid., vol. 9, no. 4, pp.599-603, Jul. 2012), formulas (10) and (12) are incorrect. Their correct forms are presented here.

A contour edge detector combing SUSAN principle and surround suppression is proposed in this paper. Specifically, the operator follows the flow of the Canny edge detector. Firstly, the edge gradient information and modified SUSAN principle are utilized to classify contour edge points and texture edge points approximately. Secondly, surround suppression is applied on the texture edges to suppress them. Finally, contour map is constructed through two hysteresis thresholding procedures. Performance comparison with three other detectors is made and experimental results show that our contour detector performs better.