- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2018
- Conditional Random Fields (CRF)
- Convolutional Neural Network (CNN)
- Fine Classification
- Airborne hyperspectral
- green tide
- Elegant End-to-End Fully Convolutional Network (E3FCN)
- deep learning
- remote sensing
- Moderate Resolution Imaging Spectroradiometer (MODIS)
- Optoelectronic Information Science and Engineering
- Ocean University of China
- Wuhan University
- Central South University
- Hubei University
-
[Lecture Notes in Computational Vision and Biomechanics] Computer Aided Intervention and Diagnostics in Clinical and Medical Images Volume 31 || Deep Neural Architecture for Localization and Tracking of Surgical Tools in Cataract Surgery
摘要： Over the last couple of decades, the quality of surgical interventions has improved owing to the use of computer vision and robotic assistance. One such application of computer vision, namely, detection of surgical tools in videos is gaining attention of the medical image processing community. The main motivation for detection, localization, and annotation of surgical tools is to develop applications for surgical workflow analysis. Such an analysis can aid in report generation, real-time decision support, etc. Cataract surgery is one of the common surgical procedure where surgeons do have direct visual access to the surgical site. Extremely small tools are used for this procedure and the surgeons observe the surgical site through a surgical microscope. In such cases, detecting the presence of tools can act an additional aid to the surgeon as well as other surgical staffs. We propose a framework consisting of a Convolutional Neural Network (CNN) which learns to distinguish and detect the presence of various surgical tools by learning robust features from the frames of a surgical video. Various deep neural architectures are hence evaluated for the task of detecting tools. The baseline models used for the purpose are pretrained on Imagenet dataset and they render upto 50% prediction accuracy. All the experiments have been validated on the dataset released as part of the Cataracts Grand Challenge. A framework for localization and detection of tools has also been proposed, which is capable of extracting visual features from glimpses of an image, by adaptively selecting and processing only the selected regions at high resolution.
关键词： Multiple tool detection,Cataract surgery,CNN,Glimpse network,Deep neural architectures,Class imbalance
更新于2025-09-23 15:23:52
-
BiMO <sub/><i>x</i> </sub> Semiconductors as Catalysts for Photocatalytic Decomposition of N <sub/>2</sub> O: A Combination of Experimental and DFT+U Study
摘要： This paper designs an analog circuit for k -winners-take-all (k WTA) operations. The circuit is stable and ?nite-time convergent. The stable state of the circuit is equivalent to the optimal solution of the k WTA. Simulation results via SPICE substantiate the e?ciency of the design.
关键词： Recurrent neural network,k -winners-take-all,Analog circuit design
更新于2025-09-23 15:23:52
-
Imaging analysis of chlorophyll fluorescence induction for monitoring plant water and nitrogen treatments
摘要： The objective of this study was to check whether different water and nitrogen treatments and, even the water-nitrogen coupling effect of plants could be correctly differentiated via chlorophyll a fluorescence image. We developed a classification method using the imaging analysis of chlorophyll a fluorescence induction based on Artificial Neural Network. The measurements were carried out on scheffera octophylla (Lour.) Harms, and the images were recorded at 690 nm with a high-resolution imaging device consisting of LEDs for an excitation at 460 nm and an Electron-Multiplying CCD camera. The effect of three different water and three different nitrogen treatments on the fluorescence parameters were obtained by hundreds of time-resolved fluorescence images. We used a Radial Basis Function neural network to model and test the sample data. The results showed that the different water and nitrogen statuses of plants were identified by the chlorophyll a fluorescence images and showed a high recognition accuracy. Compared with nitrogen, water had more of an influence on chlorophyll a fluorescence and was easier to identify. However, because the water and nitrogen restrict and promote each other, studying the coupling effect of water and nitrogen is necessary. Nine levels of water-nitrogen coupling plants were tested and classified. We discovered that a significant decrease on the classified accuracy was observed for the high nitrogen and low nitrogen treatments, while under a medium N-supply, the recognition rate was high. The method in this paper allowed plants to be classified under different water and nitrogen treatments, and has the potential to monitor the water and nitrogen coupling effect of plants in situ.
关键词： Artificial Neural Network,Classification,Recognition,Chlorophyll a Fluorescence
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS) - Kathmandu, Nepal (2018.10.25-2018.10.27)] 2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS) - Li-Fi Technology: Bridging The Radio Frequency Communication Gap
摘要： Communication in the modern day era is predominantly dependent on Information and Communication Technology (ICT). The rise in cybercrime, digital espionage and other cyber-related disturbances is one of great concerns to cyberspace users, both corporate and individual. Radio Frequency technologies and solutions been adopted for in-building, and outdoor wireless coverage solutions for the supply-chains market, including turnkey solutions for optimized communications, are been faced with security issues. This paper suggests a secure network communications route (Li-Fi Technology) alternative for users of radio frequency identification (RFID) technologies and solutions. A communication path that is resilient and resistant to disruptions by mitigating sophisticated network communication attacks such as spoofing and TCP/IP attacks (Man-In-the-middle attacks, Denial of Service attacks). This paper proposes the use of Li-Fi network for a safe and secure cyberspace communication exchange path.
关键词： LED,Wi-Fi,Li-Fi,RFID,Network,Attacks,Communication
更新于2025-09-23 15:23:52
-
Dynamic Wireless Power Transfer for Cost-Effective Wireless Sensor Networks using Frequency-Scanned Beaming
摘要： A simple adaptive 1D frequency-s scanning method is proposed for radiative Wireless Power Transfer (RWPT) systems in low-power Wireless Sensor Networks (WSN). As a proof of concept, a directive leaky-wave antenna that scans 1 W output RF power in the angular range from ±10° at 2.4 GHz to ±37° at 2.5 GHz, is used to power a WSN covering an area of 1.2 m x 1.2 m. It is shown that, using a frequency-scanned antenna, a wider area than using a non-scanned directive antenna can be powered without additional expensive equipment. The WPT protocol is described, showing that any sensor in the WSN can select the optimum transmission channel in the 2.4 GHz band, based on Received Signal Strength Indicator (RSSI) measurements, as the coordinator performs a scheduled frequency hopping phase. This maximizes the WPT beaming efficiency and thus the transferred DC power. The optimum channel selection can be performed periodically, which makes the system robust against channel state changes.
关键词： radiative wireless power transfer,Adaptive beaming,frequency-scanned antennas,wireless sensor network
更新于2025-09-23 15:23:52
-
Unsupervised Learning Based Fast Beamforming Design for Downlink MIMO
摘要： In the downlink transmission scenario, power allocation and beamforming design at the transmitter are essential when using multiple antenna arrays. This paper considers a multiple input-multiple output broadcast channel to maximize the weighted sum-rate under the total power constraint. The classical weighted minimum mean-square error (WMMSE) algorithm can obtain suboptimal solutions but involves high computational complexity. To reduce this complexity, we propose a fast beamforming design method using unsupervised learning, which trains the deep neural network (DNN) offline and provides real-time service online only with simple neural network operations. The training process is based on an end-to-end method without labeled samples avoiding the complicated process of obtaining labels. Moreover, we use the 'APoZ'-based pruning algorithm to compress the network volume, which further reduces the computational complexity and volume of the DNN, making it more suitable for low computation-capacity devices. Finally, experimental results demonstrate that the proposed method improves computational speed significantly with performance close to the WMMSE algorithm.
关键词： beamforming,unsupervised learning,deep learning,network pruning,MIMO
更新于2025-09-23 15:23:52
-
Multi-label chest X-ray image classification via category-wise residual attention learning
摘要： This paper considers the problem of multi-label thorax disease classification on chest X-ray images. Identifying one or more pathologies from a chest X-ray image is often hindered by the pathologies unrelated to the targets. In this paper, we address the above problem by proposing a category-wise residual attention learning (CRAL) framework. CRAL predicts the presence of multiple pathologies in a class-specific attentive view. It aims to suppress the obstacles of irrelevant classes by endowing small weights to the corresponding feature representation. Meanwhile, the relevant features would be strengthened by assigning larger weights. Specifically, the proposed framework consists of two modules: feature embedding module and attention learning module. The feature embedding module learns high-level features with a convolutional neural network (CNN) while the attention learning module focuses on exploring the assignment scheme of different categories. The attention module can be flexibly integrated into any feature embedding networks with end-to-end training. The comprehensive experiments are conducted on the Chest X-ray14 dataset. CRAL yields the average AUC score of 0.816 which is a new state of the art.
关键词： Image classification,Chest X-ray,Convolutional neural network,Residual attention
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE 12th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) - Hanoi (2018.9.12-2018.9.14)] 2018 IEEE 12th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) - Designing Compact Convolutional Neural Network for Embedded Stereo Vision Systems
摘要： Autonomous systems are used in a wide range of domains from indoor utensils to autonomous robot surgeries and self-driving cars. Stereo vision cameras probably are the most flexible sensing way in these systems since they can extract depth, luminance, color, and shape information. However, stereo vision based applications suffer from huge image sizes and computational complexity leading system to higher power consumption. To tackle these challenges, in the first step, GIMME2 stereo vision system [1] is employed. GIMME2 is a high-throughput and cost efficient FPGA-based stereo vision embedded system. In the next step, we present a framework for designing an optimized Deep Convolutional Neural Network (DCNN) for time constraint applications and/or limited resource budget platforms. Our framework tries to automatically generate a highly robust DCNN architecture for image data receiving from stereo vision cameras. Our proposed framework takes advantage of a multi-objective evolutionary optimization approach to design a near-optimal network architecture for both the accuracy and network size objectives. Unlike recent works aiming to generate a highly accurate network, we also considered the network size parameters to build a highly compact architecture. After designing a robust network, our proposed framework maps generated network on a multi/many core heterogeneous System-on-Chip (SoC). In addition, we have integrated our framework to the GIMME2 processing pipeline such that it can also estimate the distance of detected objects. The generated network by our framework offers up to 24x compression rate while losing only 5% accuracy compare to the best result on the CIFAR-10 dataset.
关键词： Deep Convolutional Neural Network,Stereo Vision Systems,Neural Processing Unit,Neural Network Architecture Search
更新于2025-09-23 15:22:29
-
Scale Adaptive Proposal Network for Object Detection in Remote Sensing Images
摘要： Object detection in aerial images is widely applied in many applications. In recent years, faster region convolutional neural network shows a great improvement on object detecting in natural images. Considering the size and distribution characteristic of object in remote sensing images, the region proposal network (RPN) should be changed before being adopted. In this letter, a scale adaptive proposal network (SAPNet) is proposed to improve the accuracy of multiobject detection in remote sensing images. The SAPNet consists of multilayer RPNs which are designed to generate multiscale object proposals, and a ?nal detection subnetwork in which fusion feature layer has been applied for better multiobject detection. Comparative experimental results show that the proposed SAPNet signi?cantly improves the accuracy of multiobject detection.
关键词： region proposal network (RPN),multiobject detection,remote sensing images,Convolution neural network (CNN)
更新于2025-09-23 15:22:29
-
Class Agnostic Image Common Object Detection
摘要： Learning similarity of two images is an important problem in computer vision and has many potential applications. Most of previous works focus on generating image similarities in three aspects: global feature distance computing, local feature matching and image concepts comparison. However, the task of directly detecting class agnostic common objects from two images has not been studied before, which goes one step further to capture image similarities at region level. In this paper, we propose an end-to-end Image Common Object Detection Network (CODN) to detect class agnostic common objects from two images. The proposed method consists of two main modules: locating module and matching module. The locating module generates candidate proposals of each two images. The matching module learns the similarities of the candidate proposal pairs from two images, and re?nes the bounding boxes of the candidate proposals. The learning procedure of CODN is implemented in an integrated way and a multi-task loss is designed to guarantee both region localization and common object matching. Experiments are conducted on PASCAL VOC 2007 and COCO 2014 datasets. Experimental results validate the effectiveness of the proposed method.
关键词： Common object detection,relation network,siamese network
更新于2025-09-23 15:22:29