No abstract

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.

No abstract

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.

No abstract

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).

The diffusion of 99 Tc in granite was investigated with small-sized diffusion cells, composed of a radioactive source solution cell and a sampling cell. Water in the two cells was kept at the same level. 1 ml aliquots were taken from the sampling cells daily during the first 50 days, then at intervals of several days, and measured via liquid scintillation counting. The experimental results indicate that the diffusion of 99 Tc and 3 H in granite follows the one-dimensional diffusion equation when diffusion time is long enough (> 100 days). The calculated average diffusion coefficient of 99 Tc (1.4 × 10 −12 m 2 /s) is about one half of that of 3 H (3.2 × 10 −12 m 2 /s).

Migration / 99 Tc / Unsaturated Chinese loess / Artificial rainfall / In situ testSummary. The migration of 99 Tc in unsaturated Chinese loess under artificial rainfall condition was investigated in situ. Water suckers were buried at different depths under the bottom of an experimental pit of 2 m × 2 m × 1 m (deep). Quartz containing 3 H and 99 Tc was introduced into the experimental pit to an area of 40 cm × 40 cm and the pit was backfilled to a thickness of 30 cm. An artificial rainfall of 5 mm/h was applied to the experimental pit 4 h a day for 3 months. Moisture water samples were sucked with the help of a vacuum pumping system and the activity of 3 H and 99 Tc in the samples was determined. Breakthrough curves of 3 H and 99 Tc indicated that 99 Tc was slightly retarded. The calculated average apparent distribution coefficient of 99 Tc in the medium was (1.98 ± 0.42) × 10 −2 ml/g.