• 한국정보통신학회논문지
• /
• 제13권8호
• /
• pp.1601-1607
• /
• 2009

비전 시스템은 카메라를 통하여 획득한 이미지 정보를 캡쳐 후, 이를 분석하여 물체를 인식하는 것으로서, 차종 분류를 포함 한 다양한 산업현장에서 사용하고 있다. 이런 필요성으로 인하여 차종 분류를 위한 많은 연구가 이루어지고 있으나 복잡한 계산과정으로 인하여 처리 시간이 많이 소요되는 단점이 있다. 본 논문에서는 임베디드 시스템을 기반으로 하는 Vision Box를 설계하고 이를 사용한 차종인식 시스템을 제안하였다. 제안한 Vision Box의 성능을 자동차의 차종분류를 통한 사전 테스트 결과 최적 화된 환경 조건에서는 100%의 차종별 인식률을 보였으며, 조명 및 회전의 작은 변화에 따른 테스트에서 차종인식은 가능하였으나, 패턴점수가 낮아졌다. 제안한 Vision Box 시스템을 산업 현장에 적용한 결과 처리시간, 인식률 등에서 산업체의 요구 조건을 만족 할 수 있음을 확인할 수 일었다.

• 제어로봇시스템학회논문지
• /
• 제15권5호
• /
• pp.496-504
• /
• 2009

This paper presents a recognition performance of VOR (Vestibular-Ocular Reflex) based vision tracking system for mobile robot. The VOR is a reflex eye movement which, during head movements, produces an eye movement in the direction opposite to the head movement, thus maintaining the image of interested objects placed on the center of retina. We applied this physiological concept to the vision tracking system for high recognition performance in mobile environments. The proposed method was implemented in a vision tracking system consisting of a motion sensor module and an actuation module with vision sensor. We tested the developed system on an x/y stage and a rate table for linear motion and angular motion, respectively. The experimental results show that the recognition rates of the VOR-based method are three times more than non-VOR conventional vision system, which is mainly due to the fact that VOR-based vision tracking system has the line of sight of vision system to be fixed to the object, eventually reducing the blurring effect of images under the dynamic environment. It suggests that the VOR concept proposed in this paper can be applied efficiently to the vision tracking system for mobile robot.

• 한국정보통신학회논문지
• /
• 제11권1호
• /
• pp.191-197
• /
• 2007

본 연구의 목적은 카메라를 통하여 획득한 이미지 정보를 캡쳐 후, 이를 분석하여 물체의 동작을 인식하는 Vision Box를 설계하는데 목적이 있다. 본 연구는 고객 즉, 사용자의 요구조건을 최대한 반영하여 구현하고자 하였다. 구현하고자 하는 Vision Box 시스템은 특별한 외부의 부가적인 센서를 사용하지 않고 카메라를 통하여 들어오는 화상 정보만을 분석하여 물체를 식별할 수 있도록 하였다. 그리고 PLC와의 통신과 원격지에서 Vision Box를 제어 할 수 있는 방법도 지원할 수 있도록 하였다. 본 연구에서 제안한 Vision Box의 성능을 자동차의 차종분류를 통한 성능분석 결과 최적화 된 환경조건에서는 100%의 차종별 인식률을 보였으며, 조명 및 잡음과 회전의 작은 변화에 따른 테스트에서 차종인식은 가능하였으나, 패턴점수가 낮아졌다. 따라서 제안한 Vision Box 시스템이 다양한 산업분야에 적용될 수 있을 것이라 생각된다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2379-2384
• /
• 2005

We propose a novel method for object recognition using the smart tag system with a stereo vision on a pan-tilt mechanism. We developed a smart tag which included IRED device. The smart tag is attached onto the object. We also developed a stereo vision system which pans and tilts for the object image to be the centered on each whole image view. A Stereo vision system on the pan-tilt mechanism can map the position of IRED to the robot coordinate system by using pan-tilt angles. And then, to map the size and pose of the object for the robot to coordinate the system, we used a simple model-based vision algorithm. To increase the possibility of tag-based object recognition, we implemented our approach by using as easy and simple techniques as possible.

• 한국공작기계학회논문집
• /
• 제16권6호
• /
• pp.110-116
• /
• 2007

This paper presents a new technique to implement the real-time recognition for shapes and model number of parts based on an active vision approach. The main focus of this paper is to apply a technique of 3D object recognition for non-contacting inspection of the shape and the external form state of precision parts based on the pattern recognition. In the field of computer vision, there have been many kinds of object recognition approaches. And most of these approaches focus on a method of recognition using a given input image (passive vision). It is, however, hard to recognize an object from model objects that have similar aspects each other. Recently, it has been perceived that an active vision is one of hopeful approaches to realize a robust object recognition system. The performance is illustrated by experiment for several parts and models.

• 한국컴퓨터정보학회논문지
• /
• 제24권6호
• /
• pp.67-72
• /
• 2019

This paper proposes a computer vision-based banknote recognition system intended to assist the blind. This system is robust and fast in recognizing banknotes on videos recorded with a smartphone on real-life scenarios. To reduce the computation time and enable a robust recognition in cluttered environments, this study segments the banknote candidate area from the background utilizing a technique called Pixel-Based Adaptive Segmenter (PBAS). The Speeded-Up Robust Features (SURF) interest point detector is used, and SURF feature vectors are computed only when sufficient interest points are found. The proposed algorithm achieves a recognition accuracy of 98%, a 100% true recognition rate and a 0% false recognition rate. Although Korean banknotes are used as a working example, the proposed system can be applied to recognize other countries' banknotes.

• 센서학회지
• /
• 제30권2호
• /
• pp.76-81
• /
• 2021

In this study, we propose a machine vision system with a high object recognition rate. By utilizing a multiple-exposure image sensing technique, the proposed deep learning-based machine vision system can cover a wide light intensity range without further learning processes on the various light intensity range. If the proposed machine vision system fails to recognize object features, the system operates in a multiple-exposure sensing mode and detects the target object that is blocked in the near dark or bright region. Furthermore, short- and long-exposure images from the multiple-exposure sensing mode are synthesized to obtain accurate object feature information. That results in the generation of a wide dynamic range of image information. Even with the object recognition resources for the deep learning process with a light intensity range of only 23 dB, the prototype machine vision system with the multiple-exposure imaging method demonstrated an object recognition performance with a light intensity range of up to 96 dB.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2003년도 추계학술대회
• /
• pp.420-425
• /
• 2003

Generally, reverse engineering means getting CAD data from unidentified shape using vision or 3D laser scanner system. In this paper, we studied unidentified model by machine vision based reverse engineering system to get information about in-processing model. Recently, vision technology is widely used in current factories, because it could inspect the in-process object easily, quickly, accurately. The following tasks were mainly investigated and implemented. We obtained more precise data by corning camera's distortion, compensating slit-beam error and revising acquired image. Much more, we made similar curves or surface with B-spline approximation for precision. Until now, there have been many case study of shape recognition. But it was uncompatible to apply to the field, because it had taken too many processing time and has frequent recognition failure. This paper propose recognition algorithm that prevent such errors and give applications to the field.

• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.1282-1282
• /
• 2024

Given the widespread use of intelligent surveillance cameras at construction sites, recent studies have introduced vision-based deep learning approaches. These studies have focused on enhancing the performance of vision-based excavator activity recognition to automatically monitor productivity metrics such as activity time and work cycle. However, acquiring a large amount of training data, i.e., videos captured from actual construction sites, is necessary for developing a vision-based excavator activity recognition model. Yet, complexities of dynamic working environments and security concerns at construction sites pose limitations on obtaining such videos from various surveillance camera locations. Consequently, this leads to performance degradation in excavator activity recognition models, reducing the accuracy and efficiency of heavy equipment productivity analysis. To address these limitations, this study aimed to conduct sensitivity analysis of excavator activity recognition performance based on surveillance camera location, utilizing synthetic videos generated from a game-engine-based virtual environment (Unreal Engine). Various scenarios for surveillance camera placement were devised, considering horizontal distance (20m, 30m, and 50m), vertical height (3m, 6m, and 10m), and horizontal angle (0° for front view, 90° for side view, and 180° for backside view). Performance analysis employed a 3D ResNet-18 model with transfer learning, yielding approximately 90.6% accuracy. Main findings revealed that horizontal distance significantly impacted model performance. Overall accuracy decreased with increasing distance (76.8% for 20m, 60.6% for 30m, and 35.3% for 50m). Particularly, videos with a 20m horizontal distance (close distance) exhibited accuracy above 80% in most scenarios. Moreover, accuracy trends in scenarios varied with vertical height and horizontal angle. At 0° (front view), accuracy mostly decreased with increasing height, while accuracy increased at 90° (side view) with increasing height. In addition, limited feature extraction for excavator activity recognition was found at 180° (backside view) due to occlusion of the excavator's bucket and arm. Based on these results, future studies should focus on enhancing the performance of vision-based recognition models by determining optimal surveillance camera locations at construction sites, utilizing deep learning algorithms for video super resolution, and establishing large training datasets using synthetic videos generated from game-engine-based virtual environments.

• 한국컴퓨터정보학회논문지
• /
• 제24권6호
• /
• pp.21-28
• /
• 2019

Recent years with the development of artificial intelligence and the success of the deep model, they have been deployed in all fields of computer vision. Action recognition, as an important branch of human perception and computer vision system research, has attracted more and more attention. Action recognition is a challenging task due to the special complexity of human movement, the same movement may exist between multiple individuals. The human action exists as a continuous image frame in the video, so action recognition requires more computational power than processing static images. And the simple use of the CNN network cannot achieve the desired results. Recently, the attention model has achieved good results in computer vision and natural language processing. In particular, for video action classification, after adding the attention model, it is more effective to focus on motion features and improve performance. It intuitively explains which part the model attends to when making a particular decision, which is very helpful in real applications. In this paper, we proposed a 3D dense convolutional network based on attention mechanism(ADD-Net), recognition of human motion behavior in the video.