Target detection is a critical task in interpreting hyperspectral remote sensing images. Small target (such as airplanes) detection is challenging, especially in large-scale complex scenes with high spectral variability of different land cover types. In this paper, we propose a transfer learning-based, large-scale, robust hyperspectral target detector (TLH2TD) to improve the accuracy of hyperspectral target detection (HTD) in large-scale complex scenes. TLH2TD learns the spatial features of hyperspectral targets from high-resolution remote sensing images and achieves high-precision HTD with fused spatial-spectral features. It comprises three parts: (1) The coupled target-background sample expansion (CTBSE) module is designed to expand the labeled hyperspectral target and background samples with sufficient high-resolution, labeled RGB images and a few labeled hyperspectral samples. (2) The hard positive and negative example mining (HPNEM) module trains the hard positive and negative samples to enhance the discriminative ability of the network, addressing the problem of inadequate sample training in large-scale hyperspectral images (HSIs). (3) The spatial-spectral weighted subspace (SSWS) module is designed to fuse the spatial features extracted from the target detection network and the spectral features based on the Mahalanobis distance. The results show that: (1) The TLH2TD achieves average area under the curve (AUC) values of 0.96, 0.96, and 0.93 on small-sized, medium-sized, and large-sized HSIs, respectively, achieving the highest accuracy compared with other HTD algorithms. (2) The TLH2TD exhibits the highest detection time efficiency for medium-sized and large-sized HSIs. (3) For large-sized HSIs, when most HTD algorithms fail, TLH2TD exhibits significantly higher accuracy and time efficiency than other methods. This is an important achievement to meet the robust target detection tasks of large-scale hyperspectral remote sensing images.

Recently, many lightweight neural networks have been deployed on airborne or satellite remote sensing platforms for real-time object detection. To bridge the performance gap between lightweight models and complex models, many knowledge distillation (KD) methods are investigated. However, existing KD methods ignore to transfer effective directional knowledge. Meanwhile, knowledge of different subtasks interfere with each other. To this end, a directional alignment instance knowledge distillation (DAIK) method for improving the performance of the lightweight object detection model is proposed. Specifically, an angle distillation (AD) module is developed to combine the circular smooth label and teacher logits to transfer effective directional knowledge. Angular-distance Aspect-ratio Look-up-table (AAL) is incorporated into label assignment and re-weighting loss to enhance the prediction sensitivity of direction and shape in a discrete manner. Sample alignment distillation (SAD) reduces the spatial misalignment by mimicking the teacher model’s distribution of anchor points. Extensive experiments are performed on several public remote sensing object detection datasets, which demonstrates the effectiveness of the proposed DAIK.

Change detection (CD) is an essential task in optical remote sensing, and it can be used to extract the valid information from sequential multitemporal images. However, since the character of long-term revisiting and very high resolution (VHR) development, the great differences of illumination, season, and interior textures between bitemporal images bring considerable challenges for pixel-wise CD. In this letter, focusing on accurate pixel-wise CD, a bilateral semantic fusion Siamese network (BSFNet) is proposed. First, to better map bitemporal images into semantic feature domain for comparison, a novel BSFNet is designed to effectively integrate shallow and deep semantic features, which can provide pixel-wise CD results with complete regions and clear boundary locations. Then, in order to facilitate the reasonable convergence of the proposed BSFNet, a scale-invariant sample balance (SISB) loss is designed for metric learning to avoid the problems of sample imbalance and scale variance. Finally, extensive experiments are carried out on two published CDD and LEVIR CD datasets, and results indicate that the proposed BSFNet can provide superior performance than the other state-of-the-art methods. Our work is available athttps://github.com/ClarissaDHL/BSFNet.

Scene classification of optical remote sensing is a basic but important task because of its broad application in a range of fields. Due to the powerful feature extraction capabilities, convolutional neural networks (CNNs) have been widely used in optical remote sensing scene classification tasks. Despite the remarkable efforts have been achieved, there are still several problems existed, including the effective multiscale feature description for complex scene, rotation, and low interclass diversity problems. In this letter, to address these mentioned problems and construct a powerful CNN for optical remote sensing scene classification, an effective multiscale residual network with a high-order feature representation (MRHNet) is proposed. First, data preprocessing is utilized to adapt the rotation invariance problem. Second, related to the original residual module, a pyramid convolution is introduced to realize the multiscale feature extraction, and then, its feature description ability is further improved by an effective channel attention module. Third, inspired by the tensor decomposition and its completion, a high-order feature representation structure is designed for recovering discriminative fine-scale details into deep layers to solve the low interclass diversity problem. Finally, extensive experiments are carried on two widely used scene classification datasets (e.g., AID and NWPU-RESISC45), and comparing results show that the proposed MRHNet can achieve superior performances.

With the wide vision and high flexibility, unmanned aerial vehicle (UAV) has been widely used into object tracking in recent years. However, its limited computing capability poses a great challenges to tracking algorithms. On the other hand, Discriminative Correlation Filter (DCF) based trackers have attracted great attention due to their computational efficiency and superior accuracy. Many studies introduce spatial and temporal regularization into the DCF framework to achieve a more robust appearance model and further enhance the tracking performance. However, such algorithms generally set fixed spatial or temporal regularization parameters, which lack flexibility and adaptability under cluttered and challenging scenarios. To tackle such issue, in this letter, we propose a novel DCF tracking model by introducing dynamic spatial regularization weight, which encourage the filter focuses on more reliable region during training stage. Furthermore, our method could optimize the spatial and temporal regularization weight simultaneously using Alternative Direction Method of Multiplies (ADMM) technique method, where each sub-problem has closed-form solution. Through the joint optimization, our tracker could not only suppress the potential distractors but also construct robust target appearance on the basis of reliable historical information. Experiments on two UAV benchmarks have demonstrated that our tracker performs favorably against other state-of-the-art algorithms.

Discriminative correlation filters (DCFs) have recently achieved competitive performance in visual tracking benchmarks. However, most of the existing DCF trackers only consider the spatial features of the target and could hardly benefit from the inter-frame and historical information, which may degrade the tracking performance when occlusion and deformation occurs. To tackle the above-mentioned issues, in this letter, by introducing the temporal constrain into the DCF tracker, we advocate our spatial-temporal context-aware tracker. Through jointly modeling the spatial context and historical target information, our tracker could not only adapt the appearance change but also maintain a relatively stable filter due to the small target variation between inter-frames. Furthermore, we show that the proposed objective formula could be directly solved using the Alternating Direction Method of Multipliers (ADMM) technique with low computational cost. Experiments on the large-scale benchmark demonstrate that the proposed trackers perform favorably against other state-of-the-art methods.