Object detection, aiming to recognize and locate objects of interest in aerial images, has historically played a significant role in the remote sensing community. Following remarkable improvements in Earth observation technologies, high-resolution remote sensing (HRRS) images with a bird’s eye view perspective have revealed many categories of objects with sufficient variations in appearance and on complex backgrounds that make HRRS object detection an active but challenging task. The selection of positive samples and negative training instances is an essential factor in influencing detectors’ performance. Related studies have found that many low-quality negative samples in the detectors’ training process have caused training instability and low detection accuracy. In this work, a novel sampling-balance-based multistage network (SB-MSN) is presented to adaptively mine high-quality positive and negative instances for training an accurate detector. It has a series of components to ensure the selection and generation of high-quality examples for training an accurate detector, including a multiscale information retention module, an intersection over union balance sampling strategy, a balance L1 loss, and a multistage network. The proposed detector has been evaluated on three representative HRRS data sets. The extensive experimental results show that our detector can solve the problem of low-quality samples and significantly improve the detection performance of the mAP by 1.4% with the NWPU VHR-10 data set, 3.5% with the high-resolution remote sensing detection (HRRSD) data set, and 4.2% with the detection in the optical remote (DIOR) data set. ¹

Morlet continuous wavelet transform (MCWT) has been widely used to process non-stationary electro-encephalogram (EEG) data. Nowadays, the MCWT application for processing EEG data is time-sensitive and data-intensive due to quickly increasing problem domain sizes and advancing experimental techniques. In this paper, we proposed a massively parallel MCWT approach based on GPGPU to address this research challenge. The proposed approach treats MCWT as four main computing sub-procedures and parallelizes them with CUDA correspondingly. We focused on optimizing FFT on GPUs to improve the performance of MCWT. Extensive experiments have been carried out on Fermi and Kepler GPUs and a Fermi GPU cluster. The results indicate that (1) the proposed approach (especially on Kepler GPU) can ensure encouraging runtime performance of processing non-stationary EEG data in contrast to CPU-based MCWT, (2) the performance can further be improved on the GPU cluster but performance bottleneck exists when running multiple GPGPUs on one node, and (3) tuning an appropriate FFT radix is important to the performance of our MCWT.

Current spatial-keyword publish/subscribe systems need to handle spatial-keyword skyline queries over geo-textual streams to continuously obtain good results. The skyline queries in such systems face two main problems: (1) query problems, because the powerful query capability is required for the strict limit of the response time and the large number of items concerned by the users, and (2) scalability issue, because millions of active users are maintained simultaneously with many network-connected machines. Unfortunately, the current approach is towards static data. Thus, this paper first proposes a distributed skyline query processing framework. Then, we optimize the skyline computing by introducing MF-R $^t$ -tree, which is an update-efficient and space-saving indexing structure and a fast approach for processing a continuous spatial-keyword skyline query called $eager^*$ . Finally, a spatial and textual signature-based communication optimization method is proposed to support scalability. The experimental results indicate that (1) MF-R $^t$ -tree can significantly reduce update costs, while maintaining a low storage cost, and a query performance comparable to IL-Quadtree, (2) $eager^*$ can averagely accelerate 79.72 × faster than the method based on BNL, (3) the communication optimization method significantly reduces the communication cost, and (4) the distributed framework can efficiently support large-scale skyline queries.

Current social-network-based and location-based-service applications need to handle continuous spatial approximate keyword queries over geo-textual streaming data of high density. The continuous query is a well-known expensive operation. The optimization of continuous query processing is still an open issue. For geo-textual streaming data, the performance issue is more serious since both location information and textual description need to be matched for each incoming streaming data tuple. The state-of-the-art continuous spatial-keyword query indexing approaches generally lack both support for approximate keyword matching and high-performance processing for geo-textual streaming data. Aiming to tackle this problem, this paper first proposes an indexing approach for efficient supporting of continuous spatial approximate keyword queries by integrating $min-wise$ signatures into an AP-tree, namely AP-tree ${}^{+}$ . AP-tree ${}^{+}$ utilizes the one-permutation $min-wise$ hashing method to achieve a much lower signature maintenance costs compared with the traditional $min-wise$ hashing method because it only employs one hashing function instead of dozens. Towards providing a more efficient indexing approach, this paper has explored the feasibility of parallelizing AP-tree ${}^{+}$ by employing a Graphic Processing Unit (GPU). We mapped the AP-tree ${}^{+}$ data structure into the GPU’s memory with a variety of one-dimensional arrays to form the GPU-aided AP-tree ${}^{+}$ . Furthermore, a $min-wise$ parallel hashing algorithm with a scheme of data parallel and a GPU-CPU data communication method based on a four-stage pipeline way have been used to optimize the performance of the GPU-aided AP-tree ${}^{+}$ . The experimental results indicate that (1) AP-tree ${}^{+}$ can reduce the space cost by about 11% compared with MHR-tree, (2) AP-tree ${}^{+}$ can hold a comparable recall and 5.64× query performance gain compared with MHR-tree while saving 41.66% maintenance cost on average, (3) the GPU-aided AP-tree ${}^{+}$ can attain an average speedup of 5.76× compared to AP-tree ${}^{+}$ , and (4) the GPU-CPU data communication scheme can further improve the query performance of the GPU-aided AP-tree ${}^{+}$ by 39.4%.