• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1493-1503
• /
• 2018

We propose an object recognition system and experiential game contents using Kinect to maximize object recognition rate by utilizing underwater robots. we implement an ice hockey game based on object-aware interactive contents to validate the excellence of the proposed system. The object recognition system, which is a preprocessor module, is composed based on Kinect and OpenCV. Network sockets are utilized for object recognition communications between C/S. The problem of existing research, degradation of object recognition at long distance, is solved by combining the system development method suggested in the study. As a result of the performance evaluation, the underwater robot object recognized all target objects (90.49%) with 80% of accuracy from a 2m distance, revealing 42.46% of F-Measure. From a 2.5m distance, it recognized 82.87% of the target objects with 60.5% of accuracy, showing 34.96% of F-Measure. Finally, it recognized 98.50% of target objects with 59.4% of accuracy from a 3m distance, showing 37.04% of F-measure.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.535-540
• /
• 2009

Recently, autonomous robots which can achieve the complex tasks have been required with the advance of robotics. Advanced robot vision for recognition is necessary for the realization of such robots. In this paper, we propose a method to recognize an object in the actual environment. We assume that a 3D-object model used in our proposal method is the voxel data. Its inside is full up and its surface has color information. We also define the word "recognition" as the estimation of a target object's condition. This condition means the posture and the position of a target object in the actual environment. The proposal method consists of three steps. In Step 1, we extract features from the 3D-object model. In Step 2, we estimate the position of the target object. At last, we estimate the posture of the target object in Step 3. And we experiment in the actual environment. We also confirm the performance of our proposal method from results.

• 반도체디스플레이기술학회지
• /
• 제17권2호
• /
• pp.67-70
• /
• 2018

Object detection and tracking is an exciting and interesting research area in the field of computer vision, and its technologies have been widely used in various application systems such as surveillance, military, and augmented reality. This paper proposes and implements a novel and more robust object recognition and tracking system to localize and track multiple objects from input images, which estimates target state using the likelihoods obtained from multiple CNNs. As the experimental result, the proposed algorithm is effective to handle multi-modal target appearances and other exceptions.

• 한국산학기술학회논문지
• /
• 제22권2호
• /
• pp.20-25
• /
• 2021

본 논문은 Deep-learning 기반의 검출모델을 이용하여 연속적으로 입력되는 비디오 이미지 내의 해당 대상체를 의미별로 분류해야하는 문제에 대한 구현방법에 관한 논문이다. 기존의 대상체 검출모델은 Deep-learning 기반의 검출모델로서 유사한 대상체 분류를 위해서는 방대한 DATA의 수집과 기계학습과정을 통해서 가능했다. 대상체 검출모델의 구조개선을 통한 유사물체의 인식 및 분류를 위하여 기존의 검출모델을 이용한 분류 문제를 분석하고 처리구조를 변경하여 개선된 비전처리 모듈개발을 통해 이를 기존 인식모델에 접목함으로써 대상체에 대한 인식모델을 구현하였으며, 대상체의 분류를 위하여 검출모델의 구조변경을 통해 고유성과 유사성을 정의하고 이를 검출모델에 적용하였다. 실제 축구경기 영상을 이용하여 대상체의 특징점을 분류의 기준으로 설정하여 실시간으로 분류문제를 해결하여 인식모델의 활용성 검증을 통해 산업에서의 활용도를 확인하였다. 기존의 검출모델과 새롭게 구성한 인식모델을 활용하여 실시간 이미지를 색상과 강도의 구분이 용이한 HSV의 칼라공간으로 변환하는 비전기술을 이용하여 기존모델과 비교 검증하였고, 조도 및 노이즈 환경에서도 높은 검출률을 확보할 수 있는 실시간 환경의 인식모델 최적화를 위한 선행연구를 수행하였다.

• 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.

• 로봇학회논문지
• /
• 제14권1호
• /
• pp.1-7
• /
• 2019

Recently, smart factories have attracted much attention as a result of the 4th Industrial Revolution. Existing factory automation technologies are generally designed for simple repetition without using vision sensors. Even small object assemblies are still dependent on manual work. To satisfy the needs for replacing the existing system with new technology such as bin picking and visual servoing, precision and real-time application should be core. Therefore in our work we focused on the core elements by using deep learning algorithm to detect and classify the target object for real-time and analyzing the object features. We chose YOLO CNN which is capable of real-time working and combining the two tasks as mentioned above though there are lots of good deep learning algorithms such as Mask R-CNN and Fast R-CNN. Then through the line and inside features extracted from target object, we can obtain final outline and estimate object posture.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.767-771
• /
• 2003

In this study, stereo vision system is applied to a mobile manipulator for effective tasks. The robot can recognize a target and compute the position of the target using a stereo vision system. While a monocular vision system needs properties such as geometric shape of a target, a stereo vision system enables the robot to find the position of a target without additional information. Many algorithms have been studied and developed for an object recognition. However, most of these approaches have a disadvantage of the complexity of computations and they are inadequate for real-time visual servoing. However, color information is useful for simple recognition in real-time visual servoing. In this paper, we refer to about object recognition using colors, stereo matching method, recovery of 3D space and the visual servoing.

• 제어로봇시스템학회논문지
• /
• 제11권5호
• /
• pp.411-417
• /
• 2005

In this study, stereo vision system is applied to a mobile manipulator for effective tasks. The robot can recognize a target and compute the potion of the target using a stereo vision system. While a monocular vision system needs properties such as geometric shape of a target, a stereo vision system enables the robot to find the position of a target without additional information. Many algorithms have been studied and developed for an object recognition. However, most of these approaches have a disadvantage of the complexity of computations and they are inadequate for real-time visual servoing. Color information is useful for simple recognition in real-time visual servoing. This paper addresses object recognition using colors, stereo matching method to reduce its calculation time, recovery of 3D space and the visual servoing.

• 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.

• Ocean Systems Engineering
• /
• 제10권4호
• /
• pp.435-449
• /
• 2020

This paper proposes a method to estimate the underwater target object's yaw angle using a sonar image. A simulator modeling imaging mechanism of a sonar sensor and a generative adversarial network for style transfer generates realistic template images of the target object by predicting shapes according to the viewing angles. Then, the target object's yaw angle can be estimated by comparing the template images and a shape taken in real sonar images. We verified the proposed method by conducting water tank experiments. The proposed method was also applied to AUV in field experiments. The proposed method, which provides bearing information between underwater objects and the sonar sensor, can be applied to algorithms such as underwater localization or multi-view-based underwater object recognition.