The development of innovative solutions to reduce hydrogeological risk is one of the most important research topics of recent years. The paper proposes a technique for river flood detection based on imageprocessing f...
详细信息
The development of innovative solutions to reduce hydrogeological risk is one of the most important research topics of recent years. The paper proposes a technique for river flood detection based on imageprocessing for sub-blocks. The tests carried out with the proposed method have shown that the system is able to estimate the flooding event with good precision and with very short timeframes. The research activity was carried out within the CORA (COntrollo del Rischio Ambientale, Environmental Risk Control) project financed by the Calabria Region (Italy).
Foreground extraction from an image, even by using the reference background is still a challenging problem due to the temporal variations that might occur for the test image, such as background illumination changes an...
详细信息
ISBN:
(数字)9781728153506
ISBN:
(纸本)9781728153513
Foreground extraction from an image, even by using the reference background is still a challenging problem due to the temporal variations that might occur for the test image, such as background illumination changes and object movements. In this paper, a novel structure has been presented to address this problem using a modified version of ICA algorithm which leverages the Hilbert-Schmidt Independence Criterion (HSIC) instead of the common objective functions. Moreover, the unmixing matrix elements of ICA are extracted through a Particle Swarm (PSO) evolutionary algorithm in a much faster way. The experimental results clearly show the outperformance of the proposed structure over the original works being cited among the references, using Wallflower dataset.
The Brazilian National Department of Transport Infrastructure (DNIT) maintains the National Traffic Counting Plan (PNCT). The main goal of PNCT is to evaluate the current flow of traffic on federal highways aiming to ...
详细信息
ISBN:
(数字)9781728192741
ISBN:
(纸本)9781728192758
The Brazilian National Department of Transport Infrastructure (DNIT) maintains the National Traffic Counting Plan (PNCT). The main goal of PNCT is to evaluate the current flow of traffic on federal highways aiming to define public policies. However, DNIT still performs the quantitative classificatory surveys not automated or with invasive equipment. It is crucial for conducting traffic studies to search for more modern solutions to accomplish a higher number of automated non-invasive, and low-cost classificatory surveys. This paper proposes a system that uses YOLOv3 for object detection and the Deep SORT for multiple objects tracking algorithms. From the results over real-world videos collected in Brazilian roads, we obtained a precision above 90 % in the global vehicle count. We also show that our proposal outperformed other previously proposed tools with 99.15% precision in public datasets. We believe this paper's proposal allows the development of a traffic analysis tool to be used for the automation of the volumetric traffic surveys, enabling to improve the DNIT agility and generating economy for the public coffers.
Simple Linear Iterative Clustering (SLIC) is one of the most excellent superpixel segmentation algorithms with the most comprehensive performance and is widely used in various scenes of production and living. As a pre...
详细信息
Modified Gram Schmidt (MGS) is one of the well-known forms of QR decomposition (QRD) algorithms. It has been used in many signal and imageprocessing applications to solve least square problem, linear equations or to ...
详细信息
Modified Gram Schmidt (MGS) is one of the well-known forms of QR decomposition (QRD) algorithms. It has been used in many signal and imageprocessing applications to solve least square problem, linear equations or to invert matrices. Nevertheless, QRD is considered a computationally expensive operation, and its sequential implementation doesn't meet the requirements of many real time applications. In this paper, we propose an optimized MGS algorithm version based on software pipelining and loop unrolling techniques. The suggested MGS version is parallel and well suited for VLIW architectures. The implementation is done under TI C6678 VLIW DSP and the obtained results show great improvements against the standard MGS and the optimized vendor QRD implementations.
Neuroscientists are collecting Electron Microscopy (EM) datasets at increasingly faster rates. This modality offers an unprecedented map of brain structure at the resolution of individual neurons and their synaptic co...
详细信息
ISBN:
(数字)9781728143002
ISBN:
(纸本)9781728143019
Neuroscientists are collecting Electron Microscopy (EM) datasets at increasingly faster rates. This modality offers an unprecedented map of brain structure at the resolution of individual neurons and their synaptic connections. Despite sophisticated imageprocessingalgorithms such as Flood Filling Networks, these huge datasets often require large amounts of hand-labeled data for algorithm training, followed by significant human proofreading. Many of these challenges are common across neuroscience modalities (and in other domains), but we use EM as a use case because the scale of this data emphasizes the opportunity and impact of rapidly transferring methods to new datasets. We investigate transfer learning for these work-flows, exploring transfer to different regions within a dataset, between datasets from different species, and for datasets collected with different image acquisition techniques. For EM data, we investigate the impact of algorithm performance at different workflow stages. Finally, we assess the impact of candidate transfer learning strategies in environments with no training labels. This work provides a library of algorithms, pipelines, and baselines on established datasets. We enable rapid assessment and improvements to processing pipelines, and an opportunity to quickly and effectively analyze new datasets for the neuroscience community.
The paper exploits the video camera available on-board vehicles for public transport, such as trains, coaches, ferryboats, and so on, to implement advanced services for the passengers. The idea is implementing not onl...
详细信息
ISBN:
(数字)9781510618527
ISBN:
(纸本)9781510618527
The paper exploits the video camera available on-board vehicles for public transport, such as trains, coaches, ferryboats, and so on, to implement advanced services for the passengers. The idea is implementing not only surveillance systems, but also passenger services such as: people counting, smoke and/or fire alarm, automatic climate control, e-ticketing. For each wagon, an embedded acquisition and processing unit is used, which is composed by a video multiplexer, and by an image/video signal processor that implements in real-time algorithms for advanced services such as: smoke detection, to give an early alarm in case of a fire, or people detection for people counting, or fatigue detection for the driver. The alarm is then transmitted to the train information system, to be displayed for passengers or the crew staff.
Using digital imageprocessing and machine learning technology to realize the automatic recognition of plant leaf diseases is of great significance to the prevention and control of crop diseases. In this paper, powder...
详细信息
ISBN:
(数字)9781728161068
ISBN:
(纸本)9781728161075
Using digital imageprocessing and machine learning technology to realize the automatic recognition of plant leaf diseases is of great significance to the prevention and control of crop diseases. In this paper, powdery mildew, bacterial leaf spot, black spot and downy mildew of sunflower leaves were studied. The image samples were denoised by morphological weight adaptive image denoising method. K-means + + clustering algorithm and watershed algorithm are used to segment the image of sunflower leaf disease. 19 feature values of color feature and texture feature are extracted from the diseased areas, and a random forest algorithm is constructed to identify the diseased areas. The overall recognition rate can reach 95%.
Advanced Process Controls (APCs) are already widely and deeply established especially for industrial plants with high but complex optimization possibilities like chemical batch processes. The most famous representer i...
详细信息
ISBN:
(纸本)9781538682371
Advanced Process Controls (APCs) are already widely and deeply established especially for industrial plants with high but complex optimization possibilities like chemical batch processes. The most famous representer is the Model Predictive Controller (MPC). Unlike traditional controllers, an explicit process model is used to predict the future reaction of the system, given the control input and the past states. In order to find optimal control input, this prediction is used to find a sufficient solution for a dynamic optimization problem. Due to the complex algorithms needed to find a global minimum of the constrained quadratic problem using online optimization with real-time capabilities, a suitable performance of the underlying hardware is required. FPGA implementations are especially interesting due to the application specific data flow parallelization character of MPC tasks. In this research we focus on the algorithm development and reconfigurable hardware implementation of a generic MPC using High-Level-Synthesis (HLS).
In the modern era, computers are used to automate most of the operations used to be done by humans. This leads to higher performance and low cost of operations. The field of traffic management is not an exception. In ...
详细信息
ISBN:
(数字)9781728110066
ISBN:
(纸本)9781728110073
In the modern era, computers are used to automate most of the operations used to be done by humans. This leads to higher performance and low cost of operations. The field of traffic management is not an exception. In this paper, we propose an automatic license plate recognition system which can extract the license plate number of the vehicles using machine learning models and imageprocessingalgorithms. License plate recognition systems pass through three successive stages and differ in the techniques used to achieve the output. In this paper, Locating the license plate in a given image is the first stage. It is achieved using Faster Region-Based Convolutional Neural Network, which is capable of identifying regions with objects based on regions proposal network. It is also capable of classifying the detected objects. Second stage is the segmentation of the plate using imageprocessingalgorithms and final stage is to recognize the segmented digits using convolutional neural network model. Results reveal that the presented system successfully detects and recognizes the vehicle number plate on real images, achieving an overall accuracy of 93% with a total of 100 images.
暂无评论