An autoencoder is trained to generate the background from the surveillance image by setting the training label as the shuffled input, instead of the input itself in a traditional autoencoder. Then the multi-scale features are extracted by a sparse autoencoder from the surveillance image and the corresponding background to detect foreground.

Crowd flow prediction in high density urban scenes is involved in a wide range of intelligent transportation and smart city applications, and it has become a significant topic in urban computing. In this letter, a CNN-based framework called Pyramidal Spatio-Temporal Network (PSTNet) for crowd flow prediction is proposed. Spatial encoding is employed for spatial representation of external factors, while prior pyramid enhances feature dependence of spatial scale distances and temporal spans, after that, post pyramid is proposed to fuse the heterogeneous spatio-temporal features of multiple scales. Experimental results based on TaxiBJ and MobileBJ demonstrate that proposed PSTNet outperforms the state-of-the-art methods.

Exploring the structural information as prior to facial images is a key issue of face super-resolution (SR). Although deep convolutional neural networks (CNNs) own powerful representation ability, how to accurately use facial structural information remains challenges. In this paper, we proposed a new residual fusion network to utilize the multi-scale structural information for face SR. Different from the existing methods of increasing network depth, the bottleneck attention module is introduced to extract fine facial structural features by exploring correlation from feature maps. Finally, hierarchical scales of structural information is fused for generating a high-resolution (HR) facial image. Experimental results show the proposed network outperforms some existing state-of-the-art CNNs based face SR algorithms.

Multi-FPGA systems have been receiving a lot of attention as a low cost and energy efficient system for Multi-access Edge Computing (MEC). For such purpose, a bare-metal multi-FPGA system called FiC (Flow-in-Cloud) is under development. In this paper, we introduce the FiC multi FPGA cluster which is applied partial reconfiguration (PR) FPGA design flow to support online user defined accelerator replacement while executing FPGA interconnection network and its low-level multiple FPGA management software called remote PR manager. With the remote PR manager, the user can define the FiC FPGA cluster setup by JSON and control the cluster from user application with the cooperation of simple cluster management tool / library called ficmgr on the client host and REST API service provider called ficwww on Raspberry Pi 3 (RPi3) on each node. According to the evaluation results with a prototype FiC FPGA cluster system with 12 nodes, using with online application replacement by PR and on-the-fly FPGA bitstream compression, the time for FPGA bitstream distribution was reduced to 1/17 and the total cluster setup time was reduced by 21∼57% than compared to cluster setup with full configuration FPGA bitstream.

Robustness of complex networks is an essential subject for improving their performance when vertices or links are removed due to potential threats. In recent years, significant advancements have been achieved in this field by many researchers. In this paper we show an overview from a novel statistic perspective. We present a brief review about complex networks at first including 2 primary network models, 12 popular attack strategies and the most convincing network robustness metrics. Then, we focus on the correlations of 12 attack strategies with each other, and the difference of the correlations from one network model to the other. We are also curious about the robustness of networks when vertices are removed according to different attack strategies and the difference of robustness from one network model to the other. Our aim is to observe the correlation mechanism of centralities for distinct network models, and compare the network robustness when different centralities are applied as attacking directors to distinct network models. What inspires us is that maybe we can find a paradigm that combines several high-destructive attack strategies to find the optimal strategy based on the deep learning framework.

Network throughput has become an important issue for big-data analysis on Warehouse-Scale Computing (WSC) systems. It has been reported that randomly-connected inter-switch networks can enlarge the network throughput. For irregular networks, a multi-path routing method called k-shortest path routing is conventionally utilized. However, it cannot efficiently exploit longer-than-shortest paths that would be detour paths to avoid bottlenecks. In this work, a novel routing method called k-optimized path routing to achieve high throughput is proposed for irregular networks. We introduce a heuristic to select detour paths that can avoid bottlenecks in the network to improve the average-case network throughput. Experimental results by network simulation show that the proposed k-optimized path routing can improve the saturation throughput by up to 18.2% compared to the conventional k-shortest path routing. Moreover, it can reduce the computation time required for optimization to 1/2760 at a minimum compared to our previously proposed method.

Recently, the ECG-based diagnosis system based on wearable devices has attracted more and more attention of researchers. Existing studies have achieved high classification accuracy by using deep neural networks (DNNs), but there are still some problems, such as: imprecise heart beat segmentation, inadequate use of medical knowledge, the same treatment of features with different importance. To address these problems, this paper: 1) proposes an adaptive segmenting-reshaping method to acquire abundant useful samples; 2) builds a set of hand-crafted features and deep features on the inner-beat, beat and inter-beat scale by integrating enough medical knowledge. 3) introduced a modified channel attention module (CAM) to augment the significant channels in deep features. Following the Association for Advancement of Medical Instrumentation (AAMI) recommendation, we classified the dataset into four classes and validated our algorithm on the MIT-BIH database. Experiments show that the accuracy of our model reaches 96.94%, a 3.71% increase over that of a state-of-the-art alternative.

Vehicle logo detection technology is one of the research directions in the application of intelligent transportation systems. It is an important extension of detection technology based on license plates and motorcycle types. A vehicle logo is characterized by uniqueness, conspicuousness, and diversity. Therefore, thorough research is important in theory and application. Although there are some related works for object detection, most of them cannot achieve real-time detection for different scenes. Meanwhile, some real-time detection methods of single-stage have performed poorly in the object detection of small sizes. In order to solve the problem that the training samples are scarce, our work in this paper is improved by constructing the data of a vehicle logo (VLD-45-S), multi-stage pre-training, multi-scale prediction, feature fusion between deeper with shallow layer, dimension clustering of the bounding box, and multi-scale detection training. On the basis of keeping speed, this article improves the detection precision of the vehicle logo. The generalization of the detection model and anti-interference capability in real scenes are optimized by data enrichment. Experimental results show that the accuracy and speed of the detection algorithm are improved for the object of small sizes.

This paper presents a large-angle imaging algorithm based on a dynamic scattering model for inverse synthetic aperture radar (ISAR). In this way, more information can be presented in an ISAR image than an ordinary RD image. The proposed model describes the scattering characteristics of ISAR target varying with different observation angles. Based on this model, feature points in each sub-image of the ISAR targets are extracted and matched using the scale-invariant feature transform (SIFT) and random sample consensus (RANSAC) algorithms. Using these feature points, high-precision rotation angles are obtained via joint estimation, which makes it possible to achieve a large angle imaging using the back-projection algorithm. Simulation results verifies the validity of the proposed method.

Faster R-CNN uses a region proposal network which consists of a single scale convolution filter and fully connected networks to localize detected regions. However, using a single scale filter is not enough to detect full regions of characters. In this letter, we propose a simple but effective way, i.e., utilizing variously sized convolution filters, to accurately detect Chinese characters of multiple scales in documents. We experimentally verified that our method improved IoU by 4% and detection rate by 3% than the previous single scale Faster R-CNN method.

High frame rate and ultra-low delay are the most essential requirements for building excellent human-machine-interaction systems. As a state-of-the-art local keypoint detection and feature extraction algorithm, A-KAZE shows high accuracy and robustness. Nonlinear scale space is one of the most important modules in A-KAZE, but it not only has at least one frame delay and but also is not hardware friendly. This paper proposes a hardware oriented nonlinear scale space for high frame rate and ultra-low delay A-KAZE matching system. In the proposed matching system, one part of nonlinear scale space is temporally forward and calculated in the previous frame (proposal #1), so that the processing delay is reduced to be less than 1 ms. To improve the matching accuracy affected by proposal #1, pre-adjustment of nonlinear scale (proposal #2) is proposed. Previous two frames are used to do motion estimation to predict the motion vector between previous frame and current frame. For further improvement of matching accuracy, pixel-level pre-adjustment (proposal #3) is proposed. The pre-adjustment changes from block-level to pixel-level, each pixel is assigned an unique motion vector. Experimental results prove that the proposed matching system shows average matching accuracy higher than 95% which is 5.88% higher than the existing high frame rate and ultra-low delay matching system. As for hardware performance, the proposed matching system processes VGA videos (640×480 pixels/frame) at the speed of 784 frame/second (fps) with a delay of 0.978 ms/frame.

Satellite communications (SATCOM) systems play important roles in wireless communication systems. In the future, they will be required to accommodate rapidly increasing communication requests from various types of users. Therefore, we propose a framework for efficient resource management in large-scale SATCOM systems that integrate multiple satellites. Such systems contain hundreds of thousands of communication satellites, user terminals, and gateway stations; thus, our proposed framework enables simpler and more reliable communication between users and satellites. To manage and control this system efficiently, we formulate an optimization problem that designs the network structure and allocates communication resources for a large-scale SATCOM system. In this mixed integer programming problem, we allow the cost function to be a combination of various factors so that SATCOM operators can design the network according to their individual management strategies. These factors include the total allocated bandwidth to users, the number of satellites and gateway stations to be used, and the number of total satellite handovers. Our numerical simulations show that the proposed management strategy outperforms a conventional strategy in which a user can connect to only one specific satellite determined in advance. Furthermore, we determine the effect of the number of satellites in the system on overall system performance.

To enhance cover song identification accuracy on a large-size music archive, a song-level feature summarization method is proposed by using multi-scale representation. The chroma n-grams are extracted in multiple scales to cope with both global and local tempo changes. We derive index from the extracted n-grams by clustering to reduce storage and computation for DB search. Experiments on the widely used music datasets confirmed that the proposed method achieves the state-of-the-art accuracy while reducing cost for cover song search.

We propose a novel compositing pipeline and a dynamic load balancing technique for volume rendering which utilizes a two-layered group structure to achieve effective and scalable load balancing. The technique enables each process to render data from non-contiguous regions of the volume with minimal impact on the total render time. We demonstrate the effectiveness of the proposed technique by performing a set of experiments on a modern GPU cluster. The experiments show that using the technique results in up to a 35.7% lower worst-case memory usage as compared to a dynamic k-d tree load balancing technique, whilst simultaneously achieving similar or higher render performance. The proposed technique was also able to lower the amount of transferred data during the load balancing stage by up to 72.2%. The technique has the potential to be used in many scenarios where other dynamic load balancing techniques have proved to be inadequate, such as during large-scale visualization.

Although correlation filter-based trackers have demonstrated excellent performance for visual object tracking, there remain several challenges to be addressed. In this work, we propose a novel tracker based on the correlation filter framework. Traditional trackers face difficulty in accurately adapting to changes in the scale of the target when the target moves quickly. To address this, we suggest a scale adaptive scheme based on prediction scales. We also incorporate a speed-based adaptive model update method to further improve overall tracking performance. Experiments with samples from the OTB100 and KITTI datasets demonstrate that our method outperforms existing state-of-the-art tracking algorithms in fast motion scenes.

High Efficiency Video Coding (HEVC) standard is now becoming one of the most widespread video coding standards in the world. As a successor of H.264 standard, it aims to provide a much superior encoding performance. To fulfill this goal, several new notations along with the corresponding computation processes are introduced by this standard. Among those computation processes, the integer motion estimation (IME) is one of bottlenecks due to the complex partitions of the inter prediction units (PU) and the large search window commonly adopted. Many algorithms have been proposed to address this issue and usually put emphasis on a large search window and great computation amount. However, the coding efforts should be related to the scenes. To be more specific, for relatively static videos, a small search window along with a simple search scheme should be adopted to reduce the time cost and power consumption. In view of this, a micro-code-based IME engine is proposed in this paper, which could be applied with search schemes of different complexity. To test the performance, three different search schemes based on this engine are designed and evaluated under HEVC test model (HM) 16.9, achieving a B-D rate increase of 0.55/-0.07/-0.14%. Compared with our previous work, the hardware implementation is optimized to reduce 64.2% of the SRAMs bits and 32.8% of the logic gate count. The final design could support 4K×2K @139/85/37fps videos @500MHz.

In order to solve the influence of scale change on target tracking using the drone, a multi-scale target tracking algorithm is proposed which based on the color feature tracking algorithm. The algorithm realized adaptive scale tracking by training position and scale correlation filters. It can first obtain the target center position of next frame by computing the maximum of the response, where the position correlation filter is learned by the least squares classifier and the dimensionality reduction for color features is analyzed by principal component analysis. The scale correlation filter is obtained by color characteristics at 33 rectangular areas which is set by the scale factor around the central location and is reduced dimensions by orthogonal triangle decomposition. Finally, the location and size of the target are updated by the maximum of the response. By testing 13 challenging video sequences taken by the drone, the results show that the algorithm has adaptability to the changes in the target scale and its robustness along with many other performance indicators are both better than the most state-of-the-art methods in illumination Variation, fast motion, motion blur and other complex situations.

In this paper, we focus on a large-scale ICN (Information-Centric Networking), and reveal the scaling property of ICN. Because of in-network content caching, ICN is a sort of cache networks and expected to be a promising architecture for replacing future Internet. To realize a global-scale (e.g., Internet-scale) ICN, it is crucial to understand the fundamental properties of such large-scale cache networks. However, the scaling property of ICN has not been well understood due to the lack of theoretical foundations and analysis methodologies. For answering research questions regarding the scaling property of ICN, we derive the cache hit probability at each router, the average content delivery delay of each entity, and the average content delivery delay of all entities over a content distribution tree comprised of a single repository (i.e., content provider), multiple routers, and multiple entities (i.e., content consumers). Through several numerical examples, we investigate the effect of the topology and the size of the content distribution tree and the cache size at routers on the average content delivery delay of all entities. Our findings include that the average content delivery delay of ICNs converges to a constant value if the cache size of routers are not small, which implies high scalability of ICNs, and that even when the network size would grow indefinitely, the average content delivery delay is upper-bounded by a constant value if routers in the network are provided with a fair amount of content caches.

The 3D holographic display has long been expected as a future human interface as it does not require users to wear special devices. However, its heavy computation requirement prevents the realization of such displays. A recent study says that objects and holograms with several giga-pixels should be processed in real time for the realization of high resolution and wide view angle. To this problem, first, we have adapted a conventional FFT algorithm to a GPU cluster environment in order to avoid heavy inter-node communications. Then, we have applied several single-node and multi-node optimization and parallelization techniques. The single-node optimizations include a change of the way of object decomposition, reduction of data transfer between the CPU and GPU, kernel integration, stream processing, and utilization of multiple GPUs within a node. The multi-node optimizations include distribution methods of object data from host node to the other nodes. Experimental results show that intra-node optimizations attain 11.52 times speed-up from the original single node code. Further, multi-node optimizations using 8 nodes, 2 GPUs per node, attain an execution time of 4.28 sec for generating a 1.6 giga-pixel hologram from a 3.2 giga-pixel object. It means a 237.92 times speed-up of the sequential processing by CPU and 41.78 times speed-up of multi-threaded execution on multicore-CPU, using a conventional FFT-based algorithm.

This paper presents a high power efficient pulse VCO with tail-filter for the chip-scale atomic clock (CSAC) application. The stringent power and clock stability specifications of next-generation CSAC demand a VCO with ultra-low power consumption and low phase noise. The proposed VCO architecture aims for the high power efficiency, while further reducing the phase noise using tail filtering technique. The VCO has been implemented in a standard 45nm SOI technology for validation. At an oscillation frequency of 5.0GHz, the proposed VCO achieves a phase noise of -120dBc/Hz at 1MHz offset, while consuming 1.35mW. This translates into an FoM of -191dBc/Hz.