Video synthetic aperture radar (Video SAR) has sparked lots of research attention since it provides the ability of continuously observing and tracking the object of interest. Instead of tracking a target directly, in Video SAR, it is preferred to track its shadow due to the target's instable backscattering characteristic and defocused patterns. However, the current tracking algorithms do not work well since they always suffer from the interference caused by surrounding clutters and cannot locate the target precisely. To address these issues, we propose a robust shadow tracking algorithm for Video SAR in this letter. We equip our tracker with the spatial-temporal (ST) information and saliency-based detection mechanism (SD) against the distractions and background clutters. The proposed optimization formula could be solved efficiently using the alternating direction method of multipliers (ADMM) technique and fully carried in the Fourier domain at a low computational burden. Experiments have demonstrated that the proposed algorithm performs favorably against other state-of-the-art methods.

Multi-scale object detection within Synthetic Aperture Radar (SAR) images has become a research hotspot in SAR image interpretation. Over the past few years, CNN-based detectors have advanced sharply in SAR object detection. However, the state-of-the-art detection methods are continuously limited in Feature Pyramid Network (FPN) designing and detection anchor setting aspects due to feature misalignment and targets’ appearance variation (i.e., scale change, aspect ratio change). To address the mentioned limitations, a scale-aware feature pyramid network (SARFNet) is proposed in this study, which comprises a scale-adaptive feature extraction module and a learnable anchor assignment strategy. To be specific, an enhanced feature pyramid sub-network is developed by introducing a feature alignment module to estimate the pixel offset and contextually align the high-level features. Moreover, a scale-equalizing pyramid convolution is built through 3-D convolution within the feature pyramid to improve inter-scale correlation at different feature levels. Furthermore, a self-learning anchor assignment is set to update hand-crafted anchor assignments to learnable anchor/feature configuration. By using the dynamic anchors, the detector of this study is capable of flexibly matching the target with different appearance changes. According to extensive experiments on public SAR image data sets (SSDD and HRSID), our algorithm is demonstrated to outperform existing boat detectors.

With the development of deep neural networks, many object detection frameworks have shown great success in the fields of smart surveillance, self-driving cars, and facial recognition. However, the data sources are usually videos, and the object detection frameworks are mostly established on still images and only use the spatial information, which means that the feature consistency cannot be ensured because the training procedure loses temporal information. To address these problems, we propose a single, fully-convolutional neural network-based object detection framework that involves temporal information by using Siamese networks. In the training procedure, first, the prediction network combines the multiscale feature map to handle objects of various sizes. Second, we introduce a correlation loss by using the Siamese network, which provides neighboring frame features. This correlation loss represents object co-occurrences across time to aid the consistent feature generation. Since the correlation loss should use the information of the track ID and detection label, our video object detection network has been evaluated on the large-scale ImageNet VID dataset where it achieves a 69.5% mean average precision (mAP).

Ship classification in optical images has been challenged by the complexity of various ships, different imaging conditions, and limited labelled images. Traditional methods focus on extracting handcrafted features for classification, but often fails to design well‐performed features for complex images. Here, the authors propose a ship classification approach with CNN. It is capable of learning discriminative features itself by supervised learning and achieving good classification performance. They build two small datasets of optical ship images for training and validation, and conduct several experiments. The experimental results indicate that their approach is effective for ship classification.

The existing sparse representation-based visual trackers mostly suffer from both being time consuming and having poor robustness problems. To address these issues, a novel tracking method is presented via combining sparse representation and an emerging learning technique, namely extreme learning machine (ELM). Specifically, visual tracking can be divided into two consecutive processes. Firstly, ELM is utilized to find the optimal separate hyperplane between the target observations and background ones. Thus, the trained ELM classification function is able to remove most of the candidate samples related to background contents efficiently, thereby reducing the total computational cost of the following sparse representation. Secondly, to further combine ELM and sparse representation, the resultant confidence values (i.e., probabilities to be a target) of samples on the ELM classification function are used to construct a new manifold learning constraint term of the sparse representation framework, which tends to achieve robuster results. Moreover, the accelerated proximal gradient method is used for deriving the optimal solution (in matrix form) of the constrained sparse tracking model. Additionally, the matrix form solution allows the candidate samples to be calculated in parallel, thereby leading to a higher efficiency. Experiments demonstrate the effectiveness of the proposed tracker.

In recent years, with the development of deep neural networks, object detection has been widely used in many fields such as video surveillance, face recognition, and unmanned aerial vehicles (UAVs). However, small objects detection is still a challenge for the most of existing methods due to its low resolution and limited information. Here, the authors use an effective object detector single shot multi‐box detector (SSD) as base architecture to detect small vehicles shot by UAV platform. First, in order to improve the performance for small objects, an extended‐layer feature method is proposed for introducing more small‐scale information. Second, the shapes of default boxes on specific feature maps are adjusted to balance the performance loss caused by adding feature maps. Experimental results show that this method reached the accuracy of 78.6% on PASCAL VOC object‐detection dataset, which has a 1.8% bonus compared with the baseline. Moreover, in order to show the effectiveness on small vehicles, an additional experiment is conducted on the UAV123 dataset, which gets a 3.1% bonus. The speed of the proposed method has a 39 fps on a NVIDIA GTX Titan X.