Description:
Automatic 3D extraction of building roofs from remotely sensed data is important for many applications including city modeling. This paper proposes a new method for automatic 3D roof extraction through an effective integration of LIDAR (Light Detection And Ranging) data and multispectral orthoimagery. Using the ground height from a DEM (Digital Elevation Model), the raw LIDAR points are separated into two groups. The first group contains the ground points that are exploited to constitute a `ground mask'. The second group contains the non-ground points which are segmented using an innovative image line guided segmentation technique to extract the roof planes. The image lines extracted from the grey-scale version of the orthoimage are classified into several classes such as `ground', `tree', `roof edge' and `roof ridge' using the ground mask and colour and texture information from the orthoimagery. During roof plane extraction the lines from the later two classes are used to fit roof planes to the neighbouring non-ground LIDAR points. Finally, a new rule-based procedure is applied to remove planes constructed on trees. Experimental results show that the proposed method successfully removes vegetation and offers high extraction rates.
Description:
Automatic 3D extraction of building roofs from remotely sensed data is important for many applications including city modeling. This paper proposes a new method for automatic 3D roof extraction through an effective integration of LIDAR (Light Detection And Ranging) data and multispectral orthoimagery. Using the ground height from a DEM (Digital Elevation Model), the raw LIDAR points are separated into two groups. The first group contains the ground points that are exploited to constitute a `ground mask'. The second group contains the non-ground points which are segmented using an innovative image line guided segmentation technique to extract the roof planes. The image lines extracted from the grey-scale version of the orthoimage are classified into several classes such as `ground', `tree', `roof edge' and `roof ridge' using the ground mask and colour and texture information from the orthoimagery. During roof plane extraction the lines from the later two classes are used to fit roof planes to the neighbouring non-ground LIDAR points. Finally, a new rule-based procedure is applied to remove planes constructed on trees. Experimental results show that the proposed method successfully removes vegetation and offers high extraction rates.
Description:
The use of Multimedia Wireless Sensor Networks (MWSNs) is becoming common nowadays with a rapid growth in communication facilities. Similar to any other WSNs, these networks face various challenges while providing security, trust and privacy for user data. Provisioning of the aforementioned services become an uphill task especially while dealing with real-time streaming data. These networks operates with resource-constrained sensor nodes for days, months and even years depending on the nature of an application. The resource-constrained nature of these networks makes it difficult for the nodes to tackle real-time data in mission-critical applications such as military surveillance, forest fire monitoring, health-care and industrial automation. For a secured MWSN, the transmission and processing of streaming data needs to be explored deeply. The conventional data authentication schemes are not suitable for MWSNs due to the limitations imposed on sensor nodes in terms of battery power, computation, available bandwidth and storage. In this paper, we propose a novel quality-driven clustering-based technique for authenticating streaming data in MWSNs. Nodes with maximum energy are selected as Cluster Heads (CHs). The CHs collect data from member nodes and forward it to the Base Station (BS), thus preventing member nodes with low energy from dying soon and increasing life span of the underlying network. The proposed approach not only authenticates the streaming data but also maintains the quality of transmitted data. The proposed data authentication scheme coupled with an Error Concealment technique provides an energy-efficient and distortion-free real-time data streaming. The proposed scheme is compared with an unsupervised resources scenario. The simulation results demonstrate better network lifetime along with 21.34 dB gain in Peak Signal-to-Noise Ratio (PSNR) of received video data streams.