• The Journal of Korean Institute of Information Technology
• /
• v.17 no.12
• /
• pp.81-92
• /
• 2019

Weeds are a major object which is very harmful to crops. To remove the weeds effectively, we have to classify them accurately and use herbicides. As computing technology has developed, image-based machine learning methods have been studied in this field, specially convolutional neural network(CNN) based models have shown good performance in public image dataset. However, CNN with numerous training parameters and high computational amount. Thus, it works under high hardware condition of expensive GPUs in real application. To solve these problems, in this paper, a hierarchical architecture based deep-learning model is proposed. The experimental results show that the proposed model successfully classify 21 species of the exotic weeds. That is, the model achieve 97.2612% accuracy with a small number of parameters. Our proposed model with a few parameters is expected to be applicable to actual application of network based classification services.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1302-1308
• /
• 2019

This paper presents an approach for classifying image made by acquired position data from a 2D Lidar sensor with a convolutional neural network (CNN). Lidar sensor has been widely used for unmanned devices owing to advantages in term of data accuracy, robustness against geometry distortion and light variations. A CNN algorithm consists of one or more convolutional and pooling layers and has shown a satisfactory performance for image classification. In this paper, different types of CNN architectures based on training methods, Gradient Descent(GD) and Levenberg-arquardt(LM), are implemented. The LM method has two types based on the frequency of approximating Hessian matrix, one of the factors to update training parameters. Simulation results of the LM algorithms show better classification performance of the image data than that of the GD algorithm. In addition, the LM algorithm with more frequent Hessian matrix approximation shows a smaller error than the other type of LM algorithm.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.1
• /
• pp.73-81
• /
• 2010

In recent years, there have been diverse researches and utilizations of creating geo-spatial information with high resolution satellite images. However thematic maps made with middle or low resolution satellite images have low location accuracy and precision of thematic information. This study set out to propose a method of making a precision thematic map with high resolution satellite images by examining the conversion from the conventional method based on middle or low resolution satellite images to the automatic method based on high resolution satellite images of GSD 1m or lower, extracting thematic information of middle or large scale of 1/5,000 or lower, and analyzing its accuracy. Seven classification classes were categorized according to the object-oriented classification in order to automatically extract thematic information with high resolution satellite images. And the classification results were compared and analyzed with the old middle scale land cover map and 1/1000 digital map.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.59-66
• /
• 2016

This paper presents an empirical evaluation on dimensionality reduction strategies by which dissimilarity-based classifications (DBC) can be implemented efficiently. In DBC, classification is not based on feature measurements of individual objects (a set of attributes), but rather on a suitable dissimilarity measure among the individual objects (pair-wise object comparisons). One problem of DBC is the high dimensionality of the dissimilarity space when a lots of objects are treated. To address this issue, two kinds of solutions have been proposed in the literature: prototype selection (PS)-based methods and dimension reduction (DR)-based methods. In this paper, instead of utilizing the PS-based or DR-based methods, a way of performing DBC in Eigen spaces (ES) is considered and empirically compared. In ES-based DBC, classifications are performed as follows: first, a set of principal eigenvectors is extracted from the training data set using a principal component analysis; second, an Eigen space is expanded using a subset of the extracted and selected Eigen vectors; third, after measuring distances among the projected objects in the Eigen space using $l_p$-norms as the dissimilarity, classification is performed. The experimental results, which are obtained using the nearest neighbor rule with artificial and real-life benchmark data sets, demonstrate that when the dimensionality of the Eigen spaces has been selected appropriately, compared to the PS-based and DR-based methods, the performance of the ES-based DBC can be improved in terms of the classification accuracy.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.2
• /
• pp.71-78
• /
• 2021

In order to classify a target image in a cluster of images, the difference in brightness between the object and the background is mainly concerned, which is not easy to classify if the shape of the object is blurred and the sharpness is low. However, there are a few studies attempted to solve these problems, and there is still the problem of not properly distinguishing between wrong pattern and right pattern images when applied to actual data analysis. In this paper, we propose an algorithm that classifies 3D films into sharp and blurry using the width of the pixel values histogram. This algorithm determines the width of the right and wrong images based on the width of the pixel distributions. The larger the width histogram, the sharp the image, while the shorter the width histogram the blurry the image. Experiments show that the proposed algorithm reflects that the characteristics of these histograms allows classification of all wrong images and right images. To determine the reliability and validity of the proposed algorithm, we compare the results with the other obtained from preprocessed 3D films. We then trained the 3D films using few-shot learning algorithm for accurate classification. The experiments verify that the proposed algorithm can perform higher without complicated computations.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.5
• /
• pp.37-43
• /
• 2006

The target of this study is development of web based mold discrimination system by matching vision information with CAD database. The use of 2D vision image makes possible speedy mold discrimination from many databases. The image processing such as preprocessing, cleaning is done for obtaining vivid image with object information. The web-based system is a program which runs to exchange messages between a server and a client by making of ActiveX control and the result of mold discrimination is shown on web-browser. For effective feature classification and extraction, signature method is used to make sensible information from 2D data. As a result, the possibility of proposed system is shown as matching feature information from vision image with CAD database samples.

• Journal of Multimedia Information System
• /
• v.1 no.2
• /
• pp.119-126
• /
• 2014

We propose a bicycle detection system riding on people based on modified projected local binary pattern(PLBP) for vision based intelligent vehicles. Projection method has robustness for rotation invariant and reducing dimensionality for original image. The features of Local binary pattern(LBP) are fast to compute and simple to implement for object recognition and texture classification area. Moreover, We use uniform pattern to remove the noise. This paper suggests that modified LBP method and projection vector having different weighting values according to the local shape and area in the image. Also our system maintains the simplicity of evaluation of traditional formulation while being more discriminative. Our experimental results show that a bicycle and motorcycle riding on people detection system based on proposed PLBP features achieve higher detection accuracy rate than traditional features.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.12
• /
• pp.3197-3218
• /
• 2012

Compared with traditional itinerary planning, intention-oriented itinerary recommendations can provide more flexible activity planning without requiring the user's predetermined destinations and is especially helpful for those in unfamiliar environments. The rank and classification of points of interest (POI) from location-based social networks (LBSN) are used to indicate different user intentions. The mining of vehicles' physical trajectories can provide exact civil traffic information for path planning. This paper proposes a POI category-based itinerary recommendation framework combining physical trajectories with LBSN. Specifically, a Voronoi graph-based GPS trajectory analysis method is utilized to build traffic information networks, and an ant colony algorithm for multi-object optimization is implemented to locate the most appropriate itineraries. We conduct experiments on datasets from the Foursquare and GeoLife projects. A test of users' satisfaction with the recommended items is also performed. Our results show that the satisfaction level reaches an average of 80%.

• ETRI Journal
• /
• v.39 no.4
• /
• pp.502-513
• /
• 2017

For video understanding, namely analyzing who did what in a video, actions along with objects are primary elements. Most studies on actions have handled recognition problems for a well-trimmed video and focused on enhancing their classification performance. However, action detection, including localization as well as recognition, is required because, in general, actions intersect in time and space. In addition, most studies have not considered extensibility for a newly added action that has been previously trained. Therefore, proposed in this paper is an extensible hierarchical method for detecting generic actions, which combine object movements and spatial relations between two objects, and inherited actions, which are determined by the related objects through an ontology and rule based methodology. The hierarchical design of the method enables it to detect any interactive actions based on the spatial relations between two objects. The method using object information achieves an F-measure of 90.27%. Moreover, this paper describes the extensibility of the method for a new action contained in a video from a video domain that is different from the dataset used.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.1
• /
• pp.87-99
• /
• 1999

A shop floor control system(SFCS) performs the production activities required to fill orders. In order to effectively control these activities, the autonomous agent-based heterarchical shop floor control architecture is adopted where a supervisor does not exist. In this paper, we define functional perspective of the heterarchical shop floor control using planning, scheduling, and execution modules. In particular, we focus on an execution module that can coordinate the planning and scheduling modules and a general execution module that easily can be modified to execute the other equipment. The execution module can be defined informally as a module that downloads and performs a set of scheduled tasks. The execution module is also responsible for identifying and resolving various errors whether they come from hardware or software. The purpose of this research is to identify all the execution activities and solving techniques under the assumptions of the heterarchical control architecture. And we model the execution module in object-oriented modelling technique for generalization. The execution module modeled in object-oriented concept can be adopted to the other execution module easily. This paper also proposes a classification scheme for execution activities of the heterarchical control architecture. Petri-nets are used as a unified framework for modeling and controlling execution activities. For solving the nonexistence of a supervisor, a negotiation-based solution technique is utilized.