• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.2
• /
• pp.429-435
• /
• 2010

Three dimensional (3-D) object detection and pose estimation from a single view query image has been an important issue in various fields such as medical applications, robot vision, and manufacturing automation. However, most of the existing methods are not appropriate in a real time environment since object detection and pose estimation requires extensive information and computation. In this paper, we present a fast 3-D object detection and pose estimation scheme based on surrounding camera view-changed images of objects. Our scheme has two parts. First, we detect images similar to the query image from the database based on the shape feature, and calculate candidate poses. Second, we perform accurate pose estimation for the candidate poses using the scale invariant feature transform (SIFT) method. We earned out extensive experiments on our prototype system and achieved excellent performance, and we report some of the results.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.7
• /
• pp.59-69
• /
• 1993

In this paper, a new matching strategy for 3-D object recognition, based on the Surface Normal Images (SNIs), is proposed. The matching strategy using the similarity decision function [9,10] lost the efficiency and the reliability of matching, because all features of models within model base must be compared with the scene object features, and the weights of the attributes of features is given by heuristic manner. However, the proposed matching strategy can solve these problems by using a new approach. In the approach, by searching the model base, a model object whose features are fully matched with the features of sceme object is selected. In this paper, the model base is constructed for the total 26 objects, and systhetic and real range images are used in the test of the system operation. Experimental result is performed to show the possibility that this strategy can be effectively used for the SNI based recognition.

• Proceedings of the Korea Database Society Conference
• /
• 1998.09a
• /
• pp.406-420
• /
• 1998

Users want to browse various stoups of nested attribute values of an object. On the other hand, in case of the presentation of a multimedia object, the form-based presentation is superior to the graph-based presentation. Therefore we propose o form-based presentation transformation scheme that allows users to reorganize the presentation layout to ft the limited screen and to show the values of all the needed attributes. For the representation of the presentation scenario of an object a presentation information class and the presentation transformation operations are defined. We show how these operations transform the default presentation into the wanted presentation by navigating through a multimedia object with the COMIB (COMposite Icon Browser).

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2680-2692
• /
• 1999

Software quality is classified by quality of process and product. In experience of Quality Management, it is known that quality level of product as it depends on goodness and badness of process and organization. As a result, improvement of software process has been important subject. According as this trends, ISO 12207 is publicated as standard of software life cycle process by ISO. For UML based object oriented development process, it is necessary that we should research detailed definition of activity and task of ISO 12207 process which is added, deleted or tailored in according to organization and project characteristics. In this thesis, by according with ISO 12207 software life cycle process, UML based object oriented development process is proposed. This process is composed of 7 steps and 19 activities including development phase, activity and product to improve quality of reliability. Usefulness of object oriented process for improvement of software quality is proved at three ways, which are comparative analysis of process characteristics, SPICE process evaluation and SPICE rick analysis.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.345-354
• /
• 2021

Recently, deep learning-based image recognition systems have been adopted to various surveillance environments, but most of them are still picture-type object recognition methods, which are insufficient for the long term temporal analysis and high-dimensional situation management. Therefore, we propose a method recognizing the specific dangerous situation generated by human in real-time, and utilizing deep learning-based object analysis techniques. The proposed method uses deep learning-based object detection and tracking algorithms in order to recognize the situations such as 'trespassing', 'loitering', and so on. In addition, human's joint pose data are extracted and analyzed for the emergent awareness function such as 'falling down' to notify not only in the security but also in the emergency environmental utilizations.

• Current Optics and Photonics
• /
• v.6 no.5
• /
• pp.463-472
• /
• 2022

At certain wavelengths, single-pixel imaging is considered to be a solution that can achieve high quality imaging and also reduce costs. However, achieving imaging of complex scenes is an overhead-intensive process for single-pixel imaging systems, so low efficiency and high consumption are the biggest obstacles to their practical application. Improving efficiency to reduce overhead is the solution to this problem. Salient object detection is usually used as a pre-processing step in computer vision tasks, mimicking human functions in complex natural scenes, to reduce overhead and improve efficiency by focusing on regions with a large amount of information. Therefore, in this paper, we explore the implementation of salient object detection based on single-pixel imaging after a single pixel, and propose a scheme to reconstruct images based on Fourier bases and use U²Net models for salient object detection.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.65-71
• /
• 2024

An indirect visual SLAM takes raw image data and exploits geometric information such as key-points and line edges. Due to various environmental changes, SLAM performance may decrease. The main problem is caused by dynamic objects especially in highly crowded environments. In this paper, we propose a robust feature-based visual SLAM, building on ORB-SLAM, via multi-channel dynamic objects estimation. An optical flow and deep learning-based object detection algorithm each estimate different types of dynamic object information. Proposed method incorporates two dynamic object information and creates multi-channel dynamic masks. In this method, information on actually moving dynamic objects and potential dynamic objects can be obtained. Finally, dynamic objects included in the masks are removed in feature extraction part. As a results, proposed method can obtain more precise camera poses. The superiority of our ORB-SLAM was verified to compared with conventional ORB-SLAM by the experiment using KITTI odometry dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2067-2081
• /
• 2024

Recently, image analysis research has been actively conducted due to the accumulation of big image data and the development of deep learning. Image analytics research has different characteristics from other data such as data size, real-time, image quality diversity, structural complexity, and security issues. In addition, a large amount of data is required to effectively analyze images with deep-learning models. However, in many fields, the data that can be collected is limited, so there is a need for meta learning based image analysis technology that can effectively train models with a small amount of data. This paper presents a comprehensive survey of meta-learning-based object-tracking techniques. This approach comprehensively explores object tracking methods and research that can achieve high performance in data-limited situations, including key challenges and future directions. It provides useful information for researchers in the field and can provide insights into future research directions.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.1
• /
• pp.1-14
• /
• 2017

A land cover map provides basic information to help understand the current state of a region, but its utilization in the ecological research field has deteriorated due to limited temporal and spatial resolutions. The purpose of this study was to investigate the possibility of using a land cover map with data based on high resolution images acquired by UAV. Using the UAV, 10.5 cm orthoimages were obtained from the $2.5km^2$ study area, and land cover maps were obtained from object-based and pixel-based classification for comparison and analysis. From accuracy verification, classification accuracy was shown to be high, with a Kappa of 0.77 for the pixel-based classification and a Kappa of 0.82 for the object-based classification. The overall area ratios were similar, and good classification results were found in grasslands and wetlands. The optimal image segmentation weights for object-based classification were Scale=150, Shape=0.5, Compactness=0.5, and Color=1. Scale was the most influential factor in the weight selection process. Compared with the pixel-based classification, the object-based classification provides results that are easy to read because there is a clear boundary between objects. Compared with the land cover map from the Ministry of Environment (subdivision), it was effective for natural areas (forests, grasslands, wetlands, etc.) but not developed areas (roads, buildings, etc.). The application of an object-based classification method for land cover using UAV images can contribute to the field of ecological research with its advantages of rapidly updated data, good accuracy, and economical efficiency.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.