• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.12
• /
• pp.1081-1088
• /
• 2013

Hyperspectral cameras acquire reflectance values at many different wavelength bands. Dimensions tend to increase because spectral information is stored in each pixel. Several attempts have been made to reduce dimensional problems such as the feature selection using Adaboost and dimension reduction using the Simulated Annealing technique. We propose a novel material detection method that consists of four steps: feature band selection, feature extraction, SVM (Support Vector Machine) learning, and target and specific region detection. It is a combination of the band ratio method and Simulated Annealing algorithm based on detection rate. The experimental results validate the effectiveness of the proposed feature selection and band ratio method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.9
• /
• pp.1878-1883
• /
• 2012

Generally, in the underwater target recognition, feature vectors are extracted from the target signal utilizing spatial information according to target shape/material characteristics. And, various signal processing techniques have been studied to extract feature vectors which is less sensitive to the location of the receiver. In this paper, we analyzed the characteristics of synthesized underwater objects using canonical correlation analysis method which is relatively less sensitive to the location of receiver. Canonical correlation analysis is applied to two consecutive backscattered sonar returns at different aspect angles to analyze the correlation characteristics in multi-aspect environment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.358-361
• /
• 2021

In order to improve the accuracy of small target detection more effectively, this paper proposes an improved single shot detector (SSD) target detection and recognition method based on cspdarknet53, which introduces lightweight ECA attention mechanism and Feature Pyramid Network (FPN). First, the original SSD backbone network is replaced with cspdarknet53 to enhance the learning ability of the network. Then, a lightweight ECA attention mechanism is added to the basic convolution block to optimize the network. Finally, FPN is used to gradually fuse the multi-scale feature maps used for detection in the SSD from the deep to the shallow layers of the network to improve the positioning accuracy and classification accuracy of the network. Experiments show that the proposed target detection algorithm has better detection accuracy, and it improves the detection accuracy especially for small targets.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.11 no.1
• /
• pp.75-84
• /
• 2008

A new automatic small target detection and tracking algorithm for the real-time IR surveillance system is presented. The automatic target detection and tracking algorithm of the real-time systems, requires low complexity and robust tracking performance in the cluttered environment. Linear-array and parallel-scan IR systems usually suffer from severe scan noise caused by the detector non-uniformity. After the spatial filtering and thresholding, this scan noise still remains as high amplitude clutter which degrades the target detection rate and tracking performance. In this paper, we propose a new feature which consists of area and validity information of a measurement. By adopting this feature to the measurements selection and track confirmation, we can increase the target detection rate and reduce both the track loss rate and false track rate. From the experimental results, we can validate the feasibility of the proposed method in the noisy IR images.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.39-47
• /
• 2012

The opinion of user on a certain product is expressed in positive/negative sentiments for specific features of it. In some cases, they are expressed for a holistic part of homogeneous specific features, or expressed for product itself. Therefore, in the area of opinion mining, name of opinion features to be extracted are specific feature names, holonyms for theses specific features, and product names. However, when the opinion target is described with product name or holonym, sometimes it may not match feature name of opinion sentence to true opinion target intended by the reviewer. In this paper, we present a method to extract opinion targets from opinion sentences. Most importantly, we propose a method to extract true target from the feature names mismatched to a intended target. First, we extract candidate opinion pairs using dependency relation between words, and then select feature names frequently mismatched to opinion target. Each selected opinion feature name is replaced to a specific feature intended by the reviewer. Finally, in order to extract relevant opinion features from the whole candidate opinion pairs including modified opinion feature names, candidate opinion pairs are rearranged by the order of user's interest.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.10
• /
• pp.5095-5111
• /
• 2016

The Probability Hypothesis Density (PHD) filter is a suboptimal approximation and tractable alternative to the multi-target Bayesian filter based on random finite sets. However, the PHD filter fails to track newborn targets when the target birth intensity is unknown prior to tracking. In this paper, a dual detection-guided newborn target intensity PHD algorithm is developed to solve the problem, where two schemes, namely, a newborn target intensity estimation scheme and improved measurement-driven scheme, are proposed. First, the newborn target intensity estimation scheme, consisting of the Dirichlet distribution with the negative exponent parameter and target velocity feature, is used to recursively estimate the target birth intensity. Then, an improved measurement-driven scheme is introduced to reduce the errors of the estimated number of targets and computational load. Simulation results demonstrate that the proposed algorithm can achieve good performance in terms of target states, target number and computational load when the newborn target intensity is not predefined in multi-target tracking systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.9C
• /
• pp.546-554
• /
• 2011

Near targets in the infrared (IR) images have the steady feature for inner region and the transient feature for the boundary region. Based on these features, this paper proposes a new method to extract the fine target shape of near targets in the IR images. First, we detect the boundary region of the candidate targets using the local variance weighted information entropy (WIE) of the original images. And then, a coarse target region can be estimated based on the labeling of the boundary region. For the coarse target region, we use the opening filter with an adaptive structure element to extract the fine target shape. The decision of the adaptive structure element size is optimized for the width information of target boundary by calculating the average WIE in the enlarged windows. The experimental results show that a proposed method has better extraction performance than the previous threshold algorithms.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.4
• /
• pp.370-380
• /
• 2002

This paper proposes an ATR (Automatic Target Recognition) algorithm for identifying non-occluded and occluded military vehicles in natural FLIR (Forward Looking InfraRed) images. After segmenting a target, a radial function is defined from the target boundary to extract global shape features. Also, to extract local shape features of upper region of a target, a distance function is defined from boundary points and a line between two extreme points. From two functions and target contour, four global and four local shape features are proposed. They are much more invariant to translation, rotation and scale transform than traditional feature sets. In the experiments, we show that the proposed feature set is superior to the traditional feature sets with respect to the similarity-transform invariance and recognition performance.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.72-81
• /
• 2022

Visual Object Tracking is known as the most fundamental problem in the field of computer vision. Object tracking localize the region of target object with bounding box in the video. In this paper, a custom CNN is created to extract object feature that has strong and various information. This network was constructed as a Siamese network for use as a feature extractor. The input images are passed convolution block composed of a bottleneck layers, and features are emphasized. The feature map of the target object and the search area, extracted from the Siamese network, was input as a local proposal network. Estimate the object area using the feature map. The performance of the tracking algorithm was evaluated using the OTB2013 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.611 in Success Plot and 0.831 in Precision Plot were achieved.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.