• Smart Structures and Systems
• /
• 제24권5호
• /
• pp.617-630
• /
• 2019

Currently most of the vision-based structural identification research focus either on structural input (vehicle location) estimation or on structural output (structural displacement and strain responses) estimation. The structural condition assessment at global level just with the vision-based structural output cannot give a normalized response irrespective of the type and/or load configurations of the vehicles. Combining the vision-based structural input and the structural output from non-contact sensors overcomes the disadvantage given above, while reducing cost, time, labor force including cable wiring work. In conventional traffic monitoring, sometimes traffic closure is essential for bridge structures, which may cause other severe problems such as traffic jams and accidents. In this study, a completely non-contact structural identification system is proposed, and the system mainly targets the identification of bridge unit influence line (UIL) under operational traffic. Both the structural input (vehicle location information) and output (displacement responses) are obtained by only using cameras and computer vision techniques. Multiple cameras are synchronized by audio signal pattern recognition. The proposed system is verified with a laboratory experiment on a scaled bridge model under a small moving truck load and a field application on a footbridge on campus under a moving golf cart load. The UILs are successfully identified in both bridge cases. The pedestrian loads are also estimated with the extracted UIL and the predicted weights of pedestrians are observed to be in acceptable ranges.

• 제어로봇시스템학회논문지
• /
• 제21권2호
• /
• pp.121-129
• /
• 2015

This paper presents a multiple vehicle recognition algorithm based on radar and vision sensor fusion for lane change assistance. To determine whether the lane change is possible, it is necessary to recognize not only a primary vehicle which is located in-lane, but also other adjacent vehicles in the left and/or right lanes. With the given sensor configuration, two challenging problems are considered. One is that the guardrail detected by the front radar might be recognized as a left or right vehicle due to its genetic characteristics. This problem can be solved by a guardrail recognition algorithm based on motion and shape attributes. The other problem is that the recognition of rear vehicles in the left or right lanes might be wrong, especially on curved roads due to the low accuracy of the lateral position measured by rear radars, as well as due to a lack of knowledge of road curvature in the backward direction. In order to solve this problem, it is proposed that the road curvature measured by the front vision sensor is used to derive the road curvature toward the rear direction. Finally, the proposed algorithm for multiple vehicle recognition is validated via field test data on real roads.

• 한국정보통신학회논문지
• /
• 제23권11호
• /
• pp.1384-1390
• /
• 2019

본 논문은 머신비전기반 자동검사를 위한 대상객체의 인식방향성 개선 연구로서, 영상카메라에 의한 자동 비전검사의 과정에서 제한성이 따르는 대상 객체의 인식방향성을 개선하는 방법을 제안한다. 이를 통하여 머신비전 자동검사에서 시험대상물의 위치와 방향에 상관없이 검사대상의 영상을 검출할 수 있게 함으로써 별도 검사지그의 필요성을 배제하고 검사과정의 자동화 레벨을 향상시킨다. 본 연구에서는 검사대상으로서 와이어 하네스 제조과정에서 실제 적용할 수 있는 기술과 방법을 개발하여 실제 시스템으로 구현한 결과를 제시한다. 시스템구현 결과는 공인기관의 평가를 통하여, 정밀도, 검출인식도, 재현률 및 위치조정 성공률에서 모두 성공적인 측정결과를 얻었고, 당초 설정하였던 10종류의 컬러구별 능력, 1초 이내 검사시간, 4개 자동모드 설정 등에서도 목표달성을 확인하였다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 가을 학술발표논문집 Vol.34 No.2 (C)
• /
• pp.263-266
• /
• 2007

We introduce a vision-based hand gesture recognition fer understanding musical time and patterns without extra special devices. We suggest a simple and reliable vision-based hand gesture recognition having two features First, the motion-direction code is proposed, which is a quantized code for motion directions. Second, the conducting feature point (CFP) where the point of sudden motion changes is also proposed. The proposed hand gesture recognition system extracts the human hand region by segmenting the depth information generated by stereo matching of image sequences. And then, it follows the motion of the center of the gravity(COG) of the extracted hand region and generates the gesture features such as CFP and the direction-code finally, we obtain the current timing pattern of beat and tempo of the playing music. The experimental results on the test data set show that the musical time pattern and tempo recognition rate is over 86.42% for the motion histogram matching, and 79.75% fer the CFP tracking only.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.6-8
• /
• 2007

In this paper, We propose reasoning system for object recognition and space classification using not only visual features but also contextual information. It is necessary to perceive object and classify space in real environments for mobile robot. especially vision based. Several visual features such as texture, SIFT. color are used for object recognition. Because of sensor uncertainty and object occlusion. there are many difficulties in vision-based perception. To show the validities of our reasoning system. experimental results will be illustrated. where object and space are inferred by bi -directional rules even with partial and uncertain information. And the system is combined with top-down and bottom-up approach.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2006년도 추계학술발표대회
• /
• pp.19-22
• /
• 2006

In this paper we present a vision based place recognition method which uses Bayesian method with feed back of image retrieval. Both Bayesian method and image retrieval method are based on interest features that are invariant to many image transformations. The interest features are detected using Harris-Laplacian detector and then descriptors are generated from the image patches centered at the features' position in the same manner of SIFT. The Bayesian method contains two stages: learning and recognition. The image retrieval result is fed back to the Bayesian recognition to achieve robust and confidence. The experimental results show the effectiveness of our method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1759-1772
• /
• 2023

Chinese named entity recognition (NER) is a challenging work that seeks to find, recognize and classify various types of information elements in unstructured text. Due to the Chinese text has no natural boundary like the spaces in the English text, Chinese named entity identification is much more difficult. At present, most deep learning based NER models are developed using a bidirectional long short-term memory network (BiLSTM), yet the performance still has some space to improve. To further improve their performance in Chinese NER tasks, we propose a new NER model, IDCNN-BiLSTM-Highway, which is a combination of the BiLSTM, the iterated dilated convolutional neural network (IDCNN) and the highway network. In our model, IDCNN is used to achieve multiscale context aggregation from a long sequence of words. Highway network is used to effectively connect different layers of networks, allowing information to pass through network layers smoothly without attenuation. Finally, the global optimum tag result is obtained by introducing conditional random field (CRF). The experimental results show that compared with other popular deep learning-based NER models, our model shows superior performance on two Chinese NER data sets: Resume and Yidu-S4k, The F1-scores are 94.98 and 77.59, respectively.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.877-885
• /
• 2022

Vision-based activity recognition has been widely attempted at construction sites to estimate productivity and enhance workers' health and safety. Previous studies have focused on extracting an individual worker's postural information from sequential image frames for activity recognition. However, various trades of workers perform different tasks with similar postural patterns, which degrades the performance of activity recognition based on postural information. To this end, this research exploited a concept of human-object interaction, the interaction between a worker and their surrounding objects, considering the fact that trade workers interact with a specific object (e.g., working tools or construction materials) relevant to their trades. This research developed an approach to understand the context from sequential image frames based on four features: posture, object, spatial features, and temporal feature. Both posture and object features were used to analyze the interaction between the worker and the target object, and the other two features were used to detect movements from the entire region of image frames in both temporal and spatial domains. The developed approach used convolutional neural networks (CNN) for feature extractors and activity classifiers and long short-term memory (LSTM) was also used as an activity classifier. The developed approach provided an average accuracy of 85.96% for classifying 12 target construction tasks performed by two trades of workers, which was higher than two benchmark models. This experimental result indicated that integrating a concept of the human-object interaction offers great benefits in activity recognition when various trade workers coexist in a scene.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2012년도 추계학술대회 논문집
• /
• pp.213-214
• /
• 2012

• 한국멀티미디어학회논문지
• /
• 제8권6호
• /
• pp.768-775
• /
• 2005

For sign languages are main communication means among hearing-impaired people, there are communication difficulties between speaking-oriented people and sign-language-oriented people. Automated sign-language recognition may resolve these communication problems. In sign languages, finger spelling is used to spell names and words that are not listed in the dictionary. There have been research activities for gesture and posture recognition using glove-based devices. However, these devices are often expensive, cumbersome, and inadequate for recognizing elaborate finger spelling. Use of colored patches or gloves also cause uneasiness. In this paper, a vision-based finger spelling recognition system is introduced. In our method, captured hand region images were separated from the background using a skin detection algorithm assuming that there are no skin-colored objects in the background. Then, hand postures were recognized using a two-dimensional grid analysis method. Our recognition system is not sensitive to the size or the rotation of the input posture images. By optimizing the weights of the posture features using a genetic algorithm, our system achieved high accuracy that matches other systems using devices or colored gloves. We applied our posture recognition system for detecting Korean Sign Language, achieving better than $93\%$ accuracy.