Fig 5 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
Source publication
The speed of information processing is of particular importance for image recognition tasks in remote sensing. The large amount of satellite data regarding the planet’s space and the possibility of their regular updating make the relevance of the results of their research dependent on processing technologies. In its turn the effectiveness of the ap...
Context in source publication
Context 1
... model was taken as a basis (see Fig. 5) [23]. The architecture consists of a sequence of nonlinear processing layers (encoders) and a corresponding set of decoders followed by a pixel classifier. Typically, each encoder consists of one or more convolutional layers with batch normalization and ReLU nonlinearity, followed by non-overlapping Max-pooling and Sub-sampling. One ...
Citations
... Yet, accelerating applications at the CPU level is still respectable compared to what is required in terms of computing. Therefore, many research fields were benefited from GPU acceleration techniques [10,14,22,39,40,44]. ...
Image processing by segmentation technique is an important phase in medical imaging such as MRI. Its objective is to analyze the different tissues in human body. In research area, Fuzzy set is one of the most successful techniques that guarantees a robust classification. Spatial FCM (SFCM); one of the fuzzy c-means variants; considers spatial information to deal with the noisy images. To reduce this iterative algorithm’s execution time, a hard SIMD architecture has been planted named the Graphical Processing Unit (GPU). In this work, a great contribution has been done to diagnose, confront and implement three different parallel implementations on GPU. A parallel implementations’ extensive study of SFCM entitled PSFCM using 3 × 3 window is presented, and the experiments illustrate a significant decrease in terms of running time of this algorithm known by its high complexity. The experimental results indicate that the parallel version’s execution time is about 9.46 times faster than the sequential implementation on image segmentation. This gain in terms of speed-up is achieved on the Nvidia GeForce GT 740 m GPU.
... Consequently, performing satellite image processing with convolutional neural networks has gained popularity among researchers. Image classification with satellite images enables remote sensing data processing so it has become a broad research area [25]. Classification algorithms are commonly utilized with satellite imagery for land classification [26], image scene classification [27], vehicle detection [21], and tree species classification [28]. ...
Monitoring construction activities is an important task for efficiency in construction site operations thus the topic received a fair amount of attention in the literature. Optimizing construction site operations by monitoring and detecting various tasks is dependent on the size of the construction field, which determines the tools that can be used for the job. A monitoring task can be performed with high efficiency through image classification algorithms by training the algorithms to detect construction machinery. If the area of monitoring is larger, such as the task of detecting construction related operations in a large infrastructural construction, using drone images might become inefficient. We aimed to take a first step towards a cost-efficient monitoring system specifically for construction activities that cover large territories. Consequently, satellite image classification has been performed for construction machinery detection in this study. We utilized different versions of well-established convolutional neural network architectures as backbone for the transfer learning method and their performances are evaluated. Finally, the best performing models are determined as DenseNet161 and ResNet101 with 0.919 and 0.903 test accuracies, respectively. DenseNet161 model was discussed in terms of its accuracy and efficiency in a case study to detect illegal aggregate mining activity through the basin of Thamirabarani River.
... Recently, the performances of CNNs have been significantly improved [19][20][21][22][23][24][25]. When using this type of neural network in combination with powerful graphics-processing units [26], the CNN is the key technology behind new developments in driverless driving and facial recognition. However, as the authors of [27] note, convolutional neural networks work very slowly with high-resolution images and on devices with weak processors. ...
The sustainable functioning of the transport system requires solving the problems of identifying and classifying road users in order to predict the likelihood of accidents and prevent abnormal or emergency situations. The emergence of unmanned vehicles on urban highways significantly increases the risks of such events. To improve road safety, intelligent transport systems, embedded computer vision systems, video surveillance systems, and photo radar systems are used. The main problem is the recognition and classification of objects and critical events in difficult weather conditions. For example, water drops, snow, dust, and dirt on camera lenses make images less accurate in object identification, license plate recognition, vehicle trajectory detection, etc. Part of the image is overlapped, distorted, or blurred. The article proposes a way to improve the accuracy of object identification by using the Canny operator to exclude the damaged areas of the image from consideration by capturing the clear parts of objects and ignoring the blurry ones. Only those parts of the image where this operator has detected the boundaries of the objects are subjected to further processing. To classify images by the remaining whole parts, we propose using a combined approach that includes the histogram-oriented gradient (HOG) method, a bag-of-visual-words (BoVW), and a back propagation neural network (BPNN). For the binary classification of the images of the damaged objects, this method showed a significant advantage over the classical method of convolutional neural networks (CNNs) (79 and 65% accuracies, respectively). The article also presents the results of a multiclass classification of the recognition objects on the basis of the damaged images, with an accuracy spread of 71 to 86%.
... Liu et al., 2014). Previously, the utilization GPU functions included satellite imageries classification (Sharma et al., 2020), real-time radiometric correction (Fang et al., 2014), soil parameter inversion (Yin et al., 2020), noise removal (Granata et al., 2020) and hyperspectral image classification (Yusuf & Alawneh, 2018). Some of these applications are being optimised using NVIDIA's application programming interface (API), Compute Unified Device Architecture (CUDA) (Fang et al., 2014;Sharma et al., 2020;Yin et al., 2020) and OpenCL (Granata et al., 2020), an open-source API used for NVIDIA or AMD manufactured GPU. ...
... Previously, the utilization GPU functions included satellite imageries classification (Sharma et al., 2020), real-time radiometric correction (Fang et al., 2014), soil parameter inversion (Yin et al., 2020), noise removal (Granata et al., 2020) and hyperspectral image classification (Yusuf & Alawneh, 2018). Some of these applications are being optimised using NVIDIA's application programming interface (API), Compute Unified Device Architecture (CUDA) (Fang et al., 2014;Sharma et al., 2020;Yin et al., 2020) and OpenCL (Granata et al., 2020), an open-source API used for NVIDIA or AMD manufactured GPU. These studies displayed satellite image processing able to demonstrate a good flexibility to GPU computational elements. ...
... Using GPU to accelerate satellite image processing has a huge influence on the remote sensing industry. Sharma et al., (2020) investigated the feasibility of employing GPU to accelerate batch processing of spatial raster data. They concluded that the GPU is capable of drawing conclusions about its applicability in solving various problems related to geoinformation and its efficiency processes by using neutral network training for segmenting images of 10 classes that included ground, non-ground, and manmade features of 1601 images. ...
The expansion of data collection from remote sensing and other geographic data sources, as well as from other technology such as cloud, sensors, mobile, and social media, have made mapping and analysis more complex. Some geospatial applications continue to rely on conventional geospatial processing, where limitation on computation capabilities often lacking to attain significant data interpretation. In recent years, GPU processing has improved far more GIS applications than using CPU alone. As a result, numerous researchers have begun utilising GPUs for scientific, geometric, and database computations in addition to graphics hardware use. This paper summarizes parallel processing concept and architecture, the development of GPU geoprocessing for big geodata ranging from remote sensing and 3D modelling to smart cities studies. This paper also addresses the GPU future trends advancement opportunities with other technologies, machine learning, deep learning, and cloud-based computing.
Vision-based hardware driver assistance systems are the most important systems in the world because of their low cost and ability to provide information on driving environments. Improving safety and reducing accidents are the two main objectives of these systems. For this, in this paper a new Vision-based Hardware Advanced Driver Assistance System (VH-ADAS) based machine learning incorporating the hybridization of Support Vector Machine (SVM)-Histogram of Oriented Gradient (HOG) classifier and Particle Swarm Optimization (PSO) technique is proposed for traffic scenes from both video and captured images. First, the proposed system uses a feature extraction method based on the HOG. Then, the Particle Swarm Optimization technique is used for selection and so to optimize the features. The SVM method is applied to obtain fast detection and high accuracy. Finally, a hardware synthesizable architecture of the complete system was developed and then co-simulation validity was succeeded using the Matlab-Vivado System Generator (VSG) and a Field Programmable Gate Array (FPGA). The results show that the proposed new system supports real-time detection in both images and video. Also, they show that the proposed vehicle detection method is competitive in terms of parallel run time with only 1.483 ms and in terms of accuracy rate with only 97.84%.
An effective solution to the city’s transport problems is associated with a set of infrastructural measures that can compensate for the expansion of the road network. Paid parking in cities is a proven solution that has been used for several decades in various countries around the world. Now the cities of Russia are coming close to this approach. A simplified planning algorithm for paid urban parking spaces is considered in the article using the example of the city of Volgograd. The algorithm is presented in the form of a sequence of actions for the study of quantitative and qualitative indicators of the use of parking space in the central part of the city, as well as actions for drawing up conceptual proposals for the organization of parking space. Particular attention is paid to the block for collecting initial data on the parameters of the road network and information on the parameters of the use of parking spaces in order to form technically sound proposals for the creation of zones of paid parking spaces.
Over the past half century, mankind is increasingly faced with the problems of rational use of the Earth’s territories and its resources without negative impact on the environment and the person himself. The organization of human life activity requires solving the issues of urban planning and the correct distribution of zones for the construction of industrial facilities, recreation, waste disposal zones, communications, routes, etc. Balanced planning is based on monitoring the current state of infrastructure and territory. This article proposes a methodology for integrated monitoring of the development of urban and suburban areas. It is proposed to use Earth remote sensing data as a basis for the study. The issues of collection, integration and intelligent processing of satellite images are considered. The definition and segmentation of objects in images to create digital maps is performed based on machine learning algorithms.
