• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.2
• /
• pp.76-76
• /
• 2013

The current hierarchical model of galaxy formation predicts that galaxy halos contain merger relics in the form of long stellar streams. In order to find stellar substructures in galaxy, we focused our investigation on the stellar spatial density around globular clusters and on the quantitative properties of the evolved sequences in the color-magnitude diagrams (CMDs). First, we investigated the spatial configuration of stars around five metal-poor globular clusters in halo region (M15, M30, M53, NGC 5053, and NGC 5466) and one metal-poor globular cluster in bulge region (NGC 6626). Our findings indicate that all of these globular clusters show strong evidence of extratidal features in the form of extended tidal tails around the clusters. The orientations of the extratidal features show the signatures of tidal tails tracing the clusters' orbits and the effects of dynamical interactions with the galaxy. These features were also confirmed by the radial surface density profiles and azimuthal number density profiles. Our results suggest that these six globular clusters are potentially associated with the satellite galaxies merged into the Milky Way. Second, we derived the morphological parameters of the red giant branch (RGB) from the near-infrared CMDs of 12 metal-poor globular clusters in the Galactic bulge. The photometric RGB shape indices such as colors at fixed magnitudes, magnitudes at fixed colors, and the RGB slope were measured for each cluster. The magnitudes of the RGB bump and tip were also estimated. The derived RGB parameters were used to examine the overall behavior of the RGB morphology as a function of cluster metallicity. The behavior of the RGB shape parameters was also compared with the previous observational calibration relation and theoretical predictions of the Yonsei-Yale isochrones. Our results of studies for stellar spatial distribution around globular clusters and the morphological properties of RGB stars in globular clusters could add further observational evidence of merging scenario of galaxy formation.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.453-456
• /
• 2003

Compared with other features of the image, color features are less sensitive to noise and background complication. Besides, this adding to object segmentation has more accuracy of image retrieval. This paper presents object segmentation and HAQ(Histogram Analysis and Quantization) algorithm approach to extract features(the object information and the characteristic colors) of an image. The empirical results shows that this method presents exactly spatial and color information of an image as image retrieval's feature.

• Korean Journal of Computational Design and Engineering
• /
• v.4 no.1
• /
• pp.43-51
• /
• 1999

Producing the relevant information (features) from the CAD models of CAM, called feature recognition or extraction, is the essential stage for the integration of CAD and CAM. Most feature recognition methods, however, have problems in the recognition of intersecting features because they do not handle the intersection geometry properly. In this paper, we propose a machining feature recognition algorithm, which has a solid model consisting of orthogonal primitives as input. The algorithm calculates candidate features and constitutes the Intersection Geometry Matrix which is necessary to represent the spatial relation of candidate features. Finally, it recognizes machining features from the proposed candidate features dividing and growing systems using half space and Boolean operation. The algorithm has the following characteristics: Though the geometry of part is complex due to the intersections of design primitives, it can recognize the necessary machining features. In addition, it creates the Maximal Feature Volumes independent of the machining sequences at the feature recognition stage so that it can easily accommodate the change of decision criteria of machining orders.

• Korean Journal of Cognitive Science
• /
• v.10 no.3
• /
• pp.1-15
• /
• 1999

Based on known physiological and psychophysical results, a neural network model for visual selection, called FeaureGate is proposed. The model consists of a hierarchy of spatial maps. and the flow of information from each level of the hierarchy to the next is controlled by attentional gates. The gates are jointly controlled by a bottom-up system favoring locations with unique features. and a top-down mechanism favoring locations with features designated as target features. The present study focuses on the top-down mechanism of the FeatureGate model that produces results similar to Moran and Desimone's (1985), which many current models have failed to explain, The FeatureGate model allows a consistent interpretation of many different experimental results in visual attention. including parallel feature searches and serial conjunction searches. attentional gradients triggered by cuing, feature-driven spatial selection, split a attention, inhibition of distractor locations, and flanking inhibition. This framework can be extended to produce a model of shape recognition using upper-level units that respond to configurations of features.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.09b
• /
• pp.1132-1133
• /
• 2005

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.95-95
• /
• 1996

• Proceedings of the KGS Conference
• /
• 2005.05a
• /
• pp.37-39
• /
• 2005

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.1
• /
• pp.131-139
• /
• 2006

Statistical analyses for spatial data are important features for various types of fields. Spatial data are taken at specific locations or within specific regions and their relative positions are recorded. Lattice data are synoptic observation covering an entire spatial region, like cancer rates corresponding to each county in a state. The main purpose of this paper is to detect hotspots for the region with significantly high or low rates. Kulldorff(1997) detected hotspots based on circular spatial scan statistics. We propose a new method to find any shapes of hotspots by use of echelon analysis with spatial scan statistics.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.656-658
• /
• 2003

Recently, loosely-coupled systems are widely used for distributed computing environment. We develop a web GIS server who conforms to the international standards developed by the Open GIS Consortium (OGC), such as web feature service (WFS) implementation specification, Geography Markup Language (GML) implementation specification, and the simple features specification for OLE/COM. The web GIS server provides interoperable access of spatial data among data formats in the distributed environment.