The deeplearning object detection algorithm has been widely applied in the field of synthetic aperture radar (SAR). By utilizing deep convolutional neural networks (CNNs) and other techniques, these algorithms can ef...
详细信息
The deeplearning object detection algorithm has been widely applied in the field of synthetic aperture radar (SAR). By utilizing deep convolutional neural networks (CNNs) and other techniques, these algorithms can effectively identify and locate targets in SAR images, thereby improving the accuracy and efficiency of detection. In recent years, achieving real-time monitoring of regions has become a pressing need, leading to the direct completion of real-time SAR image target detection on airborne or satellite-borne real-timeprocessing platforms. However, current GPU-based real-timeprocessing platforms struggle to meet the power consumption requirements of airborne or satellite applications. To address this issue, a low-power, low-latency deeplearning SAR object detection algorithm accelerator was designed in this study to enable real-time target detection on airborne and satellite SAR platforms. This accelerator proposes a Process Engine (PE) suitable for multidimensional convolution parallel computing, making full use of Field-Programmable Gate Array (FPGA) computing resources to reduce convolution computing time. Furthermore, a unique memory arrangement design based on this PE aims to enhance memory read/write efficiency while applying dataflow patterns suitable for FPGA computing to the accelerator to reduce computation latency. Our experimental results demonstrate that deploying the SAR object detection algorithm based on Yolov5s on this accelerator design, mounted on a Virtex 7 690t chip, consumes only 7 watts of dynamic power, achieving the capability to detect 52.19 512 x 512-sized SAR images per second.
Twitter spam needs to be detected and arrested quickly. The paper examines methods for classification of spam in terms of determination of important features, comparative performance of classification models, and impr...
详细信息
Twitter spam needs to be detected and arrested quickly. The paper examines methods for classification of spam in terms of determination of important features, comparative performance of classification models, and improvement in time performance for classification. It presents a conceptualization of several novel rich, deep, and na & iuml;ve features. The extraction processes for rich and deep features increase the time complexity of spam classification. To address this, the proposed model selectively segregates and combines features to enable near real-timeprocessing. This supersedes the time performance of standard machine learning and deeplearning models, with no compromise on the quality of classification.
In this paper, an urban object detection system via unmanned aerial vehicles (UAVs) is developed to collect real-time traffic information, which can be further utilized in many applications such as traffic monitoring ...
详细信息
In this paper, an urban object detection system via unmanned aerial vehicles (UAVs) is developed to collect real-time traffic information, which can be further utilized in many applications such as traffic monitoring and urban traffic management. The system includes an object detection algorithm, deeplearning model training, and deployment on a real UAV. For the object detection algorithm, the Mobilenet-SSD model is applied owing to its lightweight and efficiency, which make it suitable for real-time applications on an onboard microprocessor. For model training, federated learning (FL) is used to protect privacy and increase efficiency with parallel computing. Last, the FL-trained object detection model is deployed on a real UAV for real-time performance testing. The experimental results show that the object detection algorithm can reach a speed of 18 frames per second with good detection performance, which shows the real-time computation ability of a resource-limited edge device and also validates the effectiveness of the developed system.
Gas-solid fluidized beds are widely applied as chemical reactors, and the fluidization quality in the bed is closely related to bubble behavior. Digital imageprocessing is a commonly used non-invasive method for bubb...
详细信息
Gas-solid fluidized beds are widely applied as chemical reactors, and the fluidization quality in the bed is closely related to bubble behavior. Digital imageprocessing is a commonly used non-invasive method for bubble behavior analysis, but it is usually constrained by experimental conditions such as lighting, making identification of bubble and emulsion phases still challenging. Herein, deeplearning is applied in this study to optimize traditional digital imageprocessing techniques. By evaluating different deeplearning models (FCN, deepLab V3, U-Net), rapid and accurate identification and segmentation of bubble images can be achieved, and the U-Net model performs best, achieving an identification accuracy of 99.05 %. Further application of U-Net to analyze bubble behavior demonstrates that deeplearning methods enable efficient and accurate identification of bubbles and real-time analysis of bubble behavior, highlighting the significant potential application of deeplearning in the field of complex hydrodynamics in fluidized beds.
Applying affective computing techniques to recognize fear and combining them with portable signal monitors makes it possible to create real-time detection systems that could act as bodyguards when users are in danger....
详细信息
Applying affective computing techniques to recognize fear and combining them with portable signal monitors makes it possible to create real-time detection systems that could act as bodyguards when users are in danger. With this aim, this paper presents a fear recognition method based on physiological signals obtained from wearable devices. The procedure involves creating two-dimensional feature maps from the raw signals, using data augmentation and feature selection algorithms, followed by deeplearning-based classification models, taking inspiration from those used in imageprocessing. This proposal has been validated with two different datasets, achieving, in WEMAC, WESAD 3-classes, and WESAD 2-classes, F1-score results of 78.13%, 88.07%, and 99.60%, respectively, and 79.90%, 89.12%, and 99.60% in accuracy. Furthermore, the paper demonstrates the feasibility of implementing the proposed method on the Coral Edge TPU device, prepared to make inferences on the edge.
Abstract: In order to improve the intellective level of water resources management, a real-time water level recognition method based on deep-learning algorithms and image-processing techniques is proposed in this pape...
详细信息
ISBN:
(纸本)9781450395687
Abstract: In order to improve the intellective level of water resources management, a real-time water level recognition method based on deep-learning algorithms and image-processing techniques is proposed in this paper. The recognition process is composed of four steps. Firstly, for the purpose of digit detection, YOLO-v3 model is deployed for extracting numbers from the water gauges. Then, the cropped number images are fed into the LSTM + CTC model as training samples so that digits can be recognized. In the third step, Hough transform are adopted to correct the tilt of water gauge in terms of the vertical edge feature. Morphological operation, associated with horizontal projection would position upper and lower edge of water gauge to recognize the scale lines correctly. Water level could be determined correspondingly. Model application shows that the recognition model has satisfying accuracy and efficiency, with potential being applied in practice.
India is home to 10% of all traffic deaths worldwide and has the second-largest road network in the world. Moreover, in smart cities, traffic congestion, pollutants, and noise pollution have increased due to a constan...
详细信息
With the rapid growth and development of cities, Intelligent Traffic Management and Control (ITMC) is becoming a fundamental component to address the challenges of modern urban traffic management, where a wide range o...
详细信息
With the rapid growth and development of cities, Intelligent Traffic Management and Control (ITMC) is becoming a fundamental component to address the challenges of modern urban traffic management, where a wide range of daily problems need to be addressed in a prompt and expedited manner. Issues such as unpredictable traffic dynamics, resource constraints, and abnormal events pose difficulties to city managers. ITMC aims to increase the efficiency of traffic management by minimizing the odds of traffic problems, by providing real-time traffic state forecasts to better schedule the intersection signal controls. Reliable implementations of ITMC improve the safety of inhabitants and the quality of life, leading to economic growth. In recent years, researchers have proposed different solutions to address specific problems concerning traffic management, ranging from image-processing and deep-learning techniques to forecasting the traffic state and deriving policies to control intersection signals. This review article studies the primary public datasets helpful in developing models to address the identified problems, complemented with a deep analysis of the works related to traffic state forecast and intersection-signal-control models. Our analysis found that deep-learning-based approaches for short-term traffic state forecast and multi-intersection signal control showed reasonable results, but lacked robustness for unusual scenarios, particularly during oversaturated situations, which can be resolved by explicitly addressing these cases, potentially leading to significant improvements of the systems overall. However, there is arguably a long path until these models can be used safely and effectively in real-world scenarios.
Road separations, intersections, and crosswalks, which are important components of highways, are seen as significant areas for autonomous vehicles and advanced driver assistance systems because traffic accident occurr...
详细信息
Road separations, intersections, and crosswalks, which are important components of highways, are seen as significant areas for autonomous vehicles and advanced driver assistance systems because traffic accident occurrence rate is considerably high in these areas. In this study, an imageprocessing method and a deeplearning based approach on realimages has been proposed in order to provide instant information for drivers and autonomous vehicles, or to develop warning systems as part of advanced driver assistance systems to prevent or minimize traffic accidents. The information is obtained from the classification of images belonging to the separations, intersections and crosswalks on the road using a new model and VggNet, AlexNet, LeNet based on Convolutional Neural Network(CNN). We have obtained high classification accuracy with our model based on CNN. The result of the study performed on different datasets showed that the proposed method is usable for driver assistance systems and an effective structure that can be used in many areas such as warning both vehicles and drivers. (C) 2019 Elsevier B.V. All rights reserved.
Although deeplearning techniques have made significant advances in the field of images, existing methods still face challenges in processing complex, noisy images. In view of the limitation that most denoising models...
详细信息
Although deeplearning techniques have made significant advances in the field of images, existing methods still face challenges in processing complex, noisy images. In view of the limitation that most denoising models only focus on extracting single scale features, a new denoising network structure is proposed in this paper. Firstly, the channel attention mechanism and convolutional neural network are combined to construct a realimage denoising model, and then the parallel multi-scale convolutional neural network is constructed by combining the adaptive dense connected residual block and parallel multi-scale feature extraction module. The results showed that the designed model can reach the stable state only after 121 and 86 iterations on the training set and the test set, and the denoising accuracy of the model is as high as 0.96. In addition, the research model has high computational efficiency and short denoising time when processing noisy images, and the processingtime of an image is as low as 0.09s. Therefore, the proposed denoising structure has good denoising performance under different noise levels and types, and this study also provides a new idea for the application of deeplearning in image denoising and other imageprocessing tasks.
暂无评论