Search

High-resolution satellite imagery provides the information about the planet's surface whose automated labelling helps in various practical applications. Segmentation of building footprint from remote sensing images is a challenging task. This paper proposes a novel architecture bi-channel bi-spatial (B2-CS) LinkNet for implementing the semantic segmentation of building footprint. The proposed network uses two parallel semantic segmentation architectures (LinkNet) of RGB and HSV channels with dual spatial and channel attention schemes. By enhancing the features specifically in various channels and positions, result of the segmentation scheme improves. The proposed model outperforms other models with different characteristics like scales, spatial resolution, and object shapes while the analysis was done in two state-of-art datasets: INRIA aerial image labelling dataset and Massachusetts buildings dataset. Accuracy of the proposed work is 97.92% for both datasets which is better than many of the existing methods. [ABSTRACT FROM AUTHOR]

Typically, the delivery of information in vehicular ad hoc networks (VANETs) is regarded as a demanding one because of high mobility and invariable topological difference. One major concern in VANET framework is the occurrence of simulated intersection at which the packet reception probability become complicated for predicting and the model turn out to be complex highly. So as to overcome this dispute, a new framework is introduced which in turn prevents the intersection among the transmission path. Initially, the system model is initialized and the availability of channel is estimated. Based on the strength and size of data to be transmitted, the availability of channel is computed. After that, the best forwarding zone computation is made for minimizing the redundant data packets flow. To check the priority of packet and occurrence of packet collision, tree construction based data strength transmission is employed at last, the prevention of intersection or collision between the transmission channel is checked by means of correlation matrix based intersection prevention approach by monitoring the neighbor node. Then, the data packets were forwarded in an efficient manner without any intersection between the frames. The performance analysis is estimated in terms of network lifetime, packet delivery ratio, packet collision; inter node collision, throughput, and end-to-end delay. [ABSTRACT FROM AUTHOR]

In Vehicular ad-hoc networks (VANETs), resource allocation has become one of the primary tasks. Thus, a system should be well-designed so that information could be transmitted reliably and efficiently. As vehicular communication has several characteristics, efficient resource allocation scheme for D2D communications is highly required in VANET. The network topology changes rapidly as the vehicles are moving fast on the road and this makes it harder to communicate among the vehicles by predicting the best available channel. So as to overcome these issues, the proposed technique is offered in which the channel availability is predicted based on the novel mechanism like contention latency prediction using interframe spaces like Short interframe space, Distributed Coordination Function interframe space, Pointed Coordination Function and scattering based greedy weight matrix method. The implementation of this greedy mechanism in turn enhances the prediction probability of best channels that are available. Thus, the best available channel offered using greedy weight matrix scheme thereby estimates the decision probability at which the collision for available channel is computed. Thus, from this the best available channel is provided to the requested user. At last, the performance analysis is made in terms of packet delivery ratio, throughput, delay, reliability, and rate of message loss and is compared with existing techniques to prove the effectiveness of proposed strategy. [ABSTRACT FROM AUTHOR]

Wireless capsule endoscopy is the commonly employed modality in the treatment of gastrointestinal tract pathologies. However, the time taken for interpretation of these images is very high due to the large volume of images generated. Automated detection of disorders with these images can facilitate faster clinical interventions. In this paper, we propose an automated system based on Gaussian mixture model superpixels for bleeding detection and segmentation of candidate regions. The proposed system is realized with a classic binary support vector machine classifier trained with seven features including color and texture attributes extracted from the Gaussian mixture model superpixels of the WCE images. On detection of bleeding images, bleeding regions are segmented from them, by incrementally grouping the superpixels based on deltaE color differences. Tested with standard datasets, this system exhibits best performance compared to the state-of-the-art approaches with respect to classification accuracy, feature selection, computational time, and segmentation accuracy. The proposed system achieves 99.88% accuracy, 99.83% sensitivity, and 100% specificity signifying the effectiveness of the proposed system in bleeding detection with very few classification errors. [ABSTRACT FROM AUTHOR]

Land cover classification is a vital application area in the satellite image processing domain. Texture is a useful feature in land cover classification. In this paper, we propose a distributed texture-based land cover classification algorithm using Hidden Markov Model (HMM). Here, HMM is used for texture-based classification of remotely sensed images. Furthermore, to enhance the performance, data-intensive remotely sensed image is segmented and distributed into parallel sessions. Experiments were conducted on IRS P6 LISS-IV data, and the results were evaluated based on the confusion matrix, classification accuracy, and Kappa statistics. These results indicate that the proposed algorithm achieves a classification accuracy of 88.75%. [ABSTRACT FROM AUTHOR]