Pedestrian detection is a significant task in computer vision. In recent years, it is widely used in applications such as intelligent surveillance systems and automated driving systems. Although it has been exhaustively studied in the last decade, the occlusion handling issue still remains unsolved. One convincing idea is to first detect human body parts, and then utilize the parts information to estimate the pedestrians' existence. Many parts-based pedestrian detection approaches have been proposed based on this idea. However, in most of these approaches, the low-quality parts mining and the clumsy part detector combination is a bottleneck that limits the detection performance. To eliminate the bottleneck, we propose Discriminative Part CNN (DP-CNN). Our approach has two main contributions: (1) We propose a high-quality body parts mining method based on both convolutional layer features and body part subclasses. The mined part clusters are not only discriminative but also representative, and can help to construct powerful pedestrian detectors. (2) We propose a novel method to combine multiple part detectors. We convert the part detectors to a middle layer of a CNN and optimize the whole detection pipeline by fine-tuning that CNN. In experiments, it shows astonishing effectiveness of optimization and robustness of occlusion handling.
Yuchun MA Xin LI Yu WANG Xianlong HONG
In 3D IC design, thermal issue is a critical challenge. To eliminate hotspots, physical layouts are always adjusted by some incremental changes, such as shifting or duplicating hot blocks. In this paper, we distinguish the thermal-aware incremental changes in three different categories: migrating computation, growing unit and moving hotspot blocks. However, these modifications may degrade the packing area as well as interconnect distribution greatly. In this paper, mixed integer linear programming (MILP) models are devised according to these different incremental changes so that multiple objectives can be optimized simultaneously. Furthermore, to avoid random incremental modification, which may be inefficient and need long runtime to converge, here potential gain is modeled for each candidate incremental change. Based on the potential gain, a novel thermal optimization flow to intelligently choose the best incremental operation is presented. Experimental results show that migrating computation, growing unit and moving hotspot can reduce max on-chip temperature by 7%, 13% and 15% respectively on MCNC/GSRC benchmarks. Still, experimental results also show that the thermal optimization flow can reduce max on-chip temperature by 14% to the initial packings generated by an existing 3D floorplanning tool CBA, and achieve better area and total wirelength improvement than individual operations do. The results with the initial packings from CBA_T (Thermal-aware CBA floorplanner) show that 13.5% temperature reduction can be obtained by our incremental optimization flow.
Guanwen ZHANG Jien KATO Yu WANG Kenji MASE
In this paper, we propose a patch-wise learning based approach to deal with the multiple-shot people re-identification task. In the proposed approach, re-identification is formulated as a patch-wise set-to-set matching problem, with each patch set being matched using a specifically learned Mahalanobis distance metric. The proposed approach has two advantages: (1) a patch-wise representation that moderates the ambiguousness of a non-rigid matching problem (of human body) to an approximate rigid one (of body parts); (2) a patch-wise learning algorithm that enables more constraints to be included in the learning process and results in distance metrics of high quality. We evaluate the proposed approach on popular benchmark datasets and confirm its competitive performance compared to the state-of-the-art methods.
Zheng-qiang WANG Chen-chen WEN Zi-fu FAN Xiao-yu WAN
In this letter, we consider the power allocation scheme with rate proportional fairness to maximize energy efficiency in the downlink the non-orthogonal multiple access (NOMA) systems. The optimization problem of energy efficiency is a non-convex optimization problem, and the fractional programming is used to transform the original problem into a series of optimization sub-problems. A two-layer iterative algorithm is proposed to solve these sub-problems, in which power allocation with the fixed energy efficiency is achieved in the inner layer, and the optimal energy efficiency of the system is obtained by the bisection method in the outer layer. Simulation results show the effectiveness of the proposed algorithm.
Zheng-qiang WANG Xiao-yu WAN Zi-fu FAN
This letter studies the price-based power control algorithm for the spectrum sharing cognitive radio networks. The primary user (PU) profits from the secondary users (SUs) by pricing the interference power made by them. The SUs cooperate with each other to maximize their sum revenue with the signal-to-interference plus noise ratio (SINR) balancing condition. The interaction between the PU and the SUs is modeled as a Stackelberg game. Closed-form expressions of the optimal price for the PU and power allocation for the SUs are given. Simulation results show the proposed algorithm improves the revenue of both the PU and fairness of the SUs compared with the uniform pricing algorithm.
Li TAN Haoyu WANG Xiaofeng LIAN Jiaqi SHI Minji WANG
As the nodes of AWSN (Aerial Wireless Sensor Networks) fly around, the network topology changes frequently with high energy consumption and high cluster head mortality, and some sensor nodes may fly away from the original cluster and interrupt network communication. To ensure the normal communication of the network, this paper proposes an improved LEACH-M protocol for aerial wireless sensor networks. The protocol is improved based on the traditional LEACH-M protocol and MCR protocol. A Cluster head selection method based on maximum energy and an efficient solution for outlier nodes is proposed to ensure that cluster heads can be replaced prior to their death and ensure outlier nodes re-home quickly and efficiently. The experiments show that, compared with the LEACH-M protocol and MCR protocol, the improved LEACH-M protocol performance is significantly optimized, increasing network data transmission efficiency, improving energy utilization, and extending network lifetime.
Chia-Yu WANG Chia-Hsin TSAI Sheng-Chung WANG Chih-Yu WEN Robert Chen-Hao CHANG Chih-Peng FAN
In this paper, the effective Long Range (LoRa) based wireless sensor network is designed and implemented to provide the remote data sensing functions for the planned smart agricultural recycling rapid processing factory. The proposed wireless sensor network transmits the sensing data from various sensors, which measure the values of moisture, viscosity, pH, and electrical conductivity of agricultural organic wastes for the production and circulation of organic fertilizers. In the proposed wireless sensor network design, the LoRa transceiver module is used to provide data transmission functions at the sensor node, and the embedded platform by Raspberry Pi module is applied to support the gateway function. To design the cloud data server, the MySQL methodology is applied for the database management system with Apache software. The proposed wireless sensor network for data communication between the sensor node and the gateway supports a simple one-way data transmission scheme and three half-duplex two-way data communication schemes. By experiments, for the one-way data transmission scheme under the condition of sending one packet data every five seconds, the packet data loss rate approaches 0% when 1000 packet data is transmitted. For the proposed two-way data communication schemes, under the condition of sending one packet data every thirty seconds, the average packet data loss rates without and with the data-received confirmation at the gateway side can be 3.7% and 0%, respectively.
The aim of this paper is to propose effective attentional regions for fine-grained visual recognition. Based on the Spatial Transformers' capability of spatial manipulation within networks, we propose an extension model, the Attention-Guided Spatial Transformer Networks (AG-STNs). This model can guide the Spatial Transformers with hard-coded attentional regions at first. Then such guidance can be turned off, and the network model will adjust the region learning in terms of the location and scale. Such adjustment is conditioned to the classification loss so that it is actually optimized for better recognition results. With this model, we are able to successfully capture detailed attentional information. Also, the AG-STNs are able to capture attentional information in multiple levels, and different levels of attentional information are complementary to each other in our experiments. A fusion of them brings better results.
Pengyu WANG Hongqing ZHU Ning CHEN
A novel superpixel segmentation approach driven by uniform mixture model with spatially constrained (UMMS) is proposed. Under this algorithm, each observation, i.e. pixel is first represented as a five-dimensional vector which consists of colour in CLELAB space and position information. And then, we define a new uniform distribution through adding pixel position, so that this distribution can describe each pixel in input image. Applied weighted 1-Norm to difference between pixels and mean to control the compactness of superpixel. In addition, an effective parameter estimation scheme is introduced to reduce computational complexity. Specifically, the invariant prior probability and parameter range restrict the locality of superpixels, and the robust mean optimization technique ensures the accuracy of superpixel boundaries. Finally, each defined uniform distribution is associated with a superpixel and the proposed UMMS successfully implements superpixel segmentation. The experiments on BSDS500 dataset verify that UMMS outperforms most of the state-of-the-art approaches in terms of segmentation accuracy, regularity, and rapidity.
Zhengqiang WANG Wenrui XIAO Xiaoyu WAN Zifu FAN
Price-based power control problem is investigated in the spectrum sharing cognitive radio networks (CRNs) by Stackelberg game. Using backward induction, the revenue function of the primary user (PU) is expressed as a non-convex function of the transmit power of the secondary users (SUs). To solve the non-convex problem of the PU, a branch and bound based price-based power control algorithm is proposed. The proposed algorithm can be used to provide performance benchmarks for any other low complexity sub-optimal price-based power control algorithms based on Stackelberg game in CRNs.
Local spatio-temporal features are popular in the human action recognition task. In practice, they are usually coupled with a feature encoding approach, which helps to obtain the video-level vector representations that can be used in learning and recognition. In this paper, we present an efficient local feature encoding approach, which is called Approximate Sparse Coding (ASC). ASC computes the sparse codes for a large collection of prototype local feature descriptors in the off-line learning phase using Sparse Coding (SC) and look up the nearest prototype's precomputed sparse code for each to-be-encoded local feature in the encoding phase using Approximate Nearest Neighbour (ANN) search. It shares the low dimensionality of SC and the high speed of ANN, which are both desired properties for a local feature encoding approach. ASC has been excessively evaluated on the KTH dataset and the HMDB51 dataset. We confirmed that it is able to encode large quantity of local video features into discriminative low dimensional representations efficiently.
Dichao LIU Yu WANG Kenji MASE Jien KATO
Fine-grained image classification is a difficult problem, and previous studies mainly overcome this problem by locating multiple discriminative regions in different scales and then aggregating complementary information explored from the located regions. However, locating discriminative regions introduces heavy overhead and is not suitable for real-world application. In this paper, we propose the recursive multi-scale channel-spatial attention module (RMCSAM) for addressing this problem. Following the experience of previous research on fine-grained image classification, RMCSAM explores multi-scale attentional information. However, the attentional information is explored by recursively refining the deep feature maps of a convolutional neural network (CNN) to better correspond to multi-scale channel-wise and spatial-wise attention, instead of localizing attention regions. In this way, RMCSAM provides a lightweight module that can be inserted into standard CNNs. Experimental results show that RMCSAM can improve the classification accuracy and attention capturing ability over baselines. Also, RMCSAM performs better than other state-of-the-art attention modules in fine-grained image classification, and is complementary to some state-of-the-art approaches for fine-grained image classification. Code is available at https://github.com/Dichao-Liu/Recursive-Multi-Scale-Channel-Spatial-Attention-Module.
Kanghui ZHAO Tao LU Yanduo ZHANG Yu WANG Yuanzhi WANG
In recent years, compared with the traditional face super-resolution (SR) algorithm, the face SR based on deep neural network has shown strong performance. Among these methods, attention mechanism has been widely used in face SR because of its strong feature expression ability. However, the existing attention-based face SR methods can not fully mine the missing pixel information of low-resolution (LR) face images (structural prior). And they only consider a single attention mechanism to take advantage of the structure of the face. The use of multi-attention could help to enhance feature representation. In order to solve this problem, we first propose a new pixel attention mechanism, which can recover the structural details of lost pixels. Then, we design an attention fusion module to better integrate the different characteristics of triple attention. Experimental results on FFHQ data sets show that this method is superior to the existing face SR methods based on deep neural network.
Xiao-yu WAN Xiao-na YANG Zheng-qiang WANG Zi-fu FAN
This paper investigates energy-efficient resource allocation problem for the wireless power transfer (WPT) enabled multi-user massive multiple-input multiple-output (MIMO) systems. In the considered systems, the sensor nodes (SNs) are firstly powered by WPT from the power beacon (PB) with a large scale of antennas. Then, the SNs use the harvested energy to transmit the data to the base station (BS) with multiple antennas. The problem of optimizing the energy efficiency objective is formulated with the consideration of maximum transmission power of the PB and the quality of service (QoS) of the SNs. By adopting fractional programming, the energy-efficient optimization problem is firstly converted into a subtractive form. Then, a joint power and time allocation algorithm based on the block coordinate descent and Dinkelbach method is proposed to maximize energy efficiency. Finally, simulation results show the proposed algorithm achieves a good compromise between the spectrum efficiency and total power consumption.
Jianmei ZHANG Pengyu WANG Feiyang GONG Hongqing ZHU Ning CHEN
Finding the correspondence between two images of the same object or scene is an active research field in computer vision. This paper develops a rapid and effective Content-based Superpixel Image matching and Stitching (CSIS) scheme, which utilizes the content of superpixel through multi-features fusion technique. Unlike popular keypoint-based matching method, our approach proposes a superpixel internal feature-based scheme to implement image matching. In the beginning, we make use of a novel superpixel generation algorithm based on content-based feature representation, named Content-based Superpixel Segmentation (CSS) algorithm. Superpixels are generated in terms of a new distance metric using color, spatial, and gradient feature information. It is developed to balance the compactness and the boundary adherence of resulted superpixels. Then, we calculate the entropy of each superpixel for separating some superpixels with significant characteristics. Next, for each selected superpixel, its multi-features descriptor is generated by extracting and fusing local features of the selected superpixel itself. Finally, we compare the matching features of candidate superpixels and their own neighborhoods to estimate the correspondence between two images. We evaluated superpixel matching and image stitching on complex and deformable surfaces using our superpixel region descriptors, and the results show that new method is effective in matching accuracy and execution speed.
Chao HUANG Jianling SUN Xinyu WANG Di WU
In this paper, we propose an inconsistency resolution method based on a new concept, insecure backtracking role mapping. By analyzing the role graph, we prove that the root cause of security inconsistency in distributed interoperation is the existence of insecure backtracking role mapping. We propose a novel and efficient algorithm to detect the inconsistency via finding all of the insecure backtracking role mappings. Our detection algorithm will not only report the existence of inconsistency, but also generate the inconsistency information for the resolution. We reduce the inconsistency resolution problem to the known Minimum-Cut problem, and based on the results generated by our detection algorithm we propose an inconsistency resolution algorithm which could guarantee the security of distributed interoperation. We demonstrate the effectiveness of our approach through simulated tests and a case study.
Xiao-yu WAN Rui-fei CHANG Zheng-qiang WANG Zi-fu FAN
This paper investigates the sum rate (SR) maximization problem for downlink cooperative non-orthogonal multiple access (C-NOMA) systems with hardware impairments (HIs). The source node communicates with users via a half-duplex amplified-and-forward (HD-AF) relay with HIs. First, we derive the SR expression of the systems under HIs. Then, SR maximization problem is formulated under maximum power of the source, relay, and the minimum rate constraint of each user. As the original SR maximization problem is a non-convex problem, it is difficult to find the optimal resource allocation directly by tractional convex optimization method. We use variable substitution method to convert the non-convex SR maximization problem to an equivalent convex optimization problem. Finally, a joint power and rate allocation based on interior point method is proposed to maximize the SR of the systems. Simulation results show that the algorithm can improve the SR of the C-NOMA compared with the cooperative orthogonal multiple access (C-OMA) scheme.
Xinyu WANG Jianling SUN Xiaohu YANG Chao HUANG Di WU
This paper proposes a security violation detection method for RBAC based interoperation to meet the requirements of secure interoperation among distributed systems. We use role mappings between RBAC systems to implement trans-system access control, analyze security violation of interoperation with role mappings, and formalize definitions of secure interoperation. A minimum detection method according to the feature of RBAC system in distributed environment is introduced in detail. This method reduces complexity by decreasing the amount of roles involved in detection. Finally, we analyze security violation further based on the minimum detection method to help administrators eliminate security violation.
Ruilin ZHANG Xingyu WANG Hirofumi SHINOHARA
In this paper, we describe a post-processing technique having high extraction efficiency (ExE) for de-biasing and de-correlating a random bitstream generated by true random number generators (TRNGs). This research is based on the N-bit von Neumann (VN_N) post-processing method. It improves the ExE of the original von Neumann method close to the Shannon entropy bound by a large N value. However, as the N value increases, the mapping table complexity increases exponentially (2N), which makes VN_N unsuitable for low-power TRNGs. To overcome this problem, at the algorithm level, we propose a waiting strategy to achieve high ExE with a small N value. At the architectural level, a Hamming weight mapping-based hierarchical structure is used to reconstruct the large mapping table using smaller tables. The hierarchical structure also decreases the correlation factor in the raw bitstream. To develop a technique with high ExE and low cost, we designed and fabricated an 8-bit von Neumann with waiting strategy (VN_8W) in a 130-nm CMOS. The maximum ExE of VN_8W is 62.21%, which is 2.49 times larger than the ExE of the original von Neumann. NIST SP 800-22 randomness test results proved the de-biasing and de-correlation abilities of VN_8W. As compared with the state-of-the-art optimized 7-element iterated von Neumann, VN_8W achieved more than 20% energy reduction with higher ExE. At 0.45V and 1MHz, VN_8W achieved the minimum energy of 0.18pJ/bit, which was suitable for sub-pJ low energy TRNGs.
Hong LUO Yu WANG Rong LUO Huazhong YANG Yuan XIE
Negative bias temperature instability (NBTI) has become a critical reliability phenomena in advanced CMOS technology. In this paper, we propose an analytical temperature-aware dynamic NBTI model, which can be used in two circuit operation cases: executing tasks with different temperatures, and switching between active and standby mode. A PMOS Vth degradation model and a digital circuits' temporal performance degradation estimation method are developed based on our NBTI model. The simulation results show that: 1) the execution of a low temperature task can decrease ΔVth due to NBTI by 24.5%; 2) switching to standby mode can decrease ΔVth by 52.3%; 3) for ISCAS85 benchmark circuits, the delay degradation can decrease significantly if the circuit execute low temperature task or switch to standby mode; 4) we have also observed the execution time's ratio of different tasks and the ratio of active to standby time both have a considerable impact on NBTI effect.