This research is a case study of underwater object tracking based on real-time recurrent regression networks (Re3). Re3 has the concept of generic object tracking. Because of these characteristics, it is very effective to apply this model to unclear underwater sonar images. The model also an pursues object tracking method, thus it solves the problem of calculating load that may be limited when object detection models are used, unlike the tracking models. The model is also highly intuitive, so it has excellent continuity of tracking even if the object being tracked temporarily becomes partially occluded or faded. There are 4 types of the dataset using multi-beam sonar images: including (a) dummy object floated at the testbed; (b) dummy object settled at the bottom of the sea; (c) tire object settled at the bottom of the testbed; (d) multi-objects settled at the bottom of the testbed. For this study, the experiments were conducted to obtain underwater sonar images from the sea and underwater testbed, and the validity of using noisy underwater sonar images was tested to be able to track objects robustly.

In this paper, we introduce the methodology that utilizes deep learning-based front-end to enhance underwater feature matching. Both optical camera and sonar are widely applicable sensors in underwater research, however, each sensor has its own weaknesses, such as light condition and turbidity for the optic camera, and noise for sonar. To overcome the problems, we proposed the opti-acoustic transformation method. Since feature detection in sonar image is challenging, we converted the sonar image to an optic style image. Maintaining the main contents in the sonar image, CNN-based style transfer method changed the style of the image that facilitates feature detection. Finally, we verified our result using cosine similarity comparison and feature matching against the original optic image.

본 연구에서는 플라이애시가 다량치환된 모르타르에 알칼리 활성화를 통한 강도증진을 양생온도 및 양생방법 변화에 따라 비교 분석하였다. 연구 결과로 플라이애시를 60 % 과다치환한 경우 소생재 도포 후 40℃의 온도로 48시간 기중양생을 실시한다면 OPC의 28일 압축강도에 근접하게 발휘되는 것이 얻어졌다.

본 연구에서는 외기온 영하조건에서 노출시간 변화별 콘크리트의 초기동해 피해를 입는 온도이력을 확인하고, 실험연구결과 –10℃인 외기조건에서 200 mm 두께의 슬래브는 18시간까지는 외기온에 노출되어도 콘크리트의 수화열에 의해 초기동해 피해가 발생하지 않는 것을 알 수 있었다.

In this paper, we present auto-annotation tool and synthetic dataset using 3D CAD model for deep learning based object detection. To be used as training data for deep learning methods, class, segmentation, bounding-box, contour, and pose annotations of the object are needed. We propose an automated annotation tool and synthetic image generation. Our resulting synthetic dataset reflects occlusion between objects and applicable for both underwater and in-air environments. To verify our synthetic dataset, we use MASK R-CNN as a state-of-the-art method among object detection model using deep learning. For experiment, we make the experimental environment reflecting the actual underwater environment. We show that object detection model trained via our dataset show significantly accurate results and robustness for the underwater environment. Lastly, we verify that our synthetic dataset is suitable for deep learning model for the underwater environments.

This study was conducted to compensate for the decrease in intensity due to the decrease in temperature and proposed temperature correction strength T28, using the Fractional function model.

This study was conducted to propose a strength correction factor to compensate the strength delay at designed age caused by the temperature drop in low temperature condition. Strength correction factors due to temperature drop T28 were provided using the constant function model.

In the ground environment, mobile robot research uses sensors such as GPS and optical cameras to localize surrounding landmarks and to estimate the position of the robot. However, an underwater environment restricts the use of sensors such as optical cameras and GPS. Also, unlike the ground environment, it is difficult to make a continuous observation of landmarks for location estimation. So, in underwater research, artificial markers are installed to generate a strong and lasting landmark. When artificial markers are acquired with an underwater sonar sensor, different types of noise are caused in the underwater sonar image. This noise is one of the factors that reduces object detection performance. This paper aims to improve object detection performance through distortion and rotation augmentation of training data. Object detection is detected using a Faster R-CNN.

In this study, the temperature correction strength (Tn) was conducted to propose (Tn) according to the management age of structural concrete that is separated from the average curing temperature of 4°C to 17°C in cold conditions. After reviewing the strength difference of the concrete using fly ash as a combined material at W/C 50%, the temperature correction strength (Tn) is proposed. The temperature correction strength was proposed to compensate for differences with standard curing conditions due to decrease in curing temperature from 28th, 42nd, 56th and 91st of the models interpreted as equivalent age methods.

This study is a basic study to CGS, which originates from the IGCC, as fine aggregate for concrete. The study measured density, water absorption ratio, solid volume percentage for grain shape, fineness modulus, grading curve of physical properties of fine aggregate. As a result, the density and solid volume percentage for grain sheet were found to be satisfactory in the aggregate for content (KS F 2527).Water evaluation ratio, fitness modulus, and grinding curve did not meet KS standards. Therefore, it is deemed necessary to adjust the grain size through sieving in case of fineness modulus and grinding curve.

This study was conducted to improve the economy, quality, and load of Soil paving concrete by using waste materials such as Oystery and Dolomitic to solve strength reduction and durability reduction caused by hardening agents in Korea. According to the results of the study, for the curing expenses, the Fine part agreement (FC) and the Furnace slag power lower (BS) are 5:5, It was possible to verify that the best results were obtained in terms of the quality of cement mortar when the natural organic lime and dolomitic lime were mixed at a ratio of 5:5.

National statistics of solid waste indicate that, although the amount of combustible wastes from household sectors is decreasing, the amount of waste that is buried in landfills increases each year. And the increasing rate of combustible wastes from industrial sectors is higher than the decreasing rate of combustible wastes from household sectors. Combustible waste, once screened, can be used as a potential energy resource contributing to resource circulation. Therefore, the objective of this study was to predict the amount of waste materials to be recovered and recycled by landfill mining and reclamation (LFMR), based on material flow analysis for four existing landfills. In this study, the landfills analyzed by material flow analysis were classified into types 1 to 4 by considering the status of the landfill and incineration situation. In order to perform material flow analysis, volume increase rate and bulk density were applied to the methodology employed in previous studies. In addition, material flow analysis software ‘STAN 2.0’ was used for the analysis. As a result of analyzing the average value of four landfills, the landfilled waste was classified as 93.9 m3 (73.7%) of combustible waste, 9.2 m3 (7.3%) of incombustible waste, and 24.3 m3 (19.1%) of soil matter. So, 73.7% can be incinerated or recovered by energy, 7.3% can be recycled as materials and reclaimed, and 19.1% can be recycled as landfill cover materials based on weight. The results of the material flow analysis carried out in this study are expected to be used to predict the amount of waste materials landfilled to be recovered by the material flow analysis during landfill mining processes.

This study focuses on autonomous exploration based on map expansion for an underwater robot equipped with acoustic sonars. Map expansion is applicable to large-area mapping, but it may affect localization accuracy. Thus, as the key contribution of this paper, we propose a method for underwater autonomous exploration wherein the robot determines the trade-off between map expansion ratio and position accuracy, selects which of the two has higher priority, and then moves to a mission step. An occupancy grid map is synthesized by utilizing the measurements of an acoustic range sonar that determines the probability of occupancy. This information is then used to determine a path to the frontier, which becomes the new search point. During area searching and map building, the robot revisits artificial landmarks to improve its position accuracy as based on imaging sonar-based recognition and EKF-SLAM if the position accuracy is above the predetermined threshold. Additionally, real-time experiments were conducted by using an underwater robot, yShark, to validate the proposed method, and the analysis of the results is discussed herein.

In this study, the correlation between the durometer and the proctor penetration resistance tester, which is considered to be efficient in determining the setting time in a simple portability for soil and concrete utilizing organic lime (H) and Goto lime (G), is used. The results of the study show a high correlation between the portable hardness meter, the durometer and the proctor penetration resistance test period. Therefore, it is expected that the durometer will be useful for the measurement of setting time and the time limit.

In this study, the correlation with a proctor penetration resistance tester is analyzed for the purpose of judging the setting time of concrete by the convenient portability of the durometer which is a rubber hardness meter.The result of this study showed a high correlation between the value of the tilt of the durometer and the measured value of the proctor penetration resistance tester.

This study is a basic review of the use of CGS generated in IGCC as a fine aggregate for concrete, and a basic feature of cement mortar was considered. The analysis shows that CGS and CS mix ratio is best when the CGS is mixed at about 0~50 % On the basis of workability and strength improvement effects. This is expected to contribute to the strength, workability, and quality improvement of concrete given the optimal mixing of CGS.

In this study, concrete slab with insulation and non-insulated formwork was used to monitor and control its strength using a wireless sensor network with equivalent age method. As a result, the temperature and compressive strength of the structures were monitored without any problems, which revealed a good management tool.

In this study examined the strength of wall concrete using insulated molds and non-insulated forms by monitoring the strength of the structure using a wireless sensor network by maturity method. It was confirmed that the temperature and compressive strength of the structures are monitored in real time, along with effective strength control.

Acoustic based localization is essential to operate autonomous robotic systems in underwater environment where the use of sensorial data is limited. This paper proposes a localization method using artificial underwater acoustic sources. The proposed method acquires directional angles of acoustic sources using time difference of arrivals of two hydrophones. For this purpose, a probabilistic approach is used for accurate estimation of the time delay. Then, Gaussian sum filter based SLAM technique is used to localize both acoustic sources and underwater vehicle. It is performed by using bearing of acoustic sources as measurement and inertial sensors as prediction model. The proposed method can handle directional ambiguity of time difference based source localization by generating Gaussian models corresponding to possible locations of both front and back sides. Through these processes, the proposed method can provide reliable localization method for underwater vehicles without any prior information of source locations. The performance of the proposed method is verified by experimental results conducted in a real sea environment.

Localization of underwater vehicle is essential to use underwater robotic systems for various applications effectively. For this purpose, this paper presents a method of two-dimensional SLAM for underwater vehicles equipped with two hydrophones. The proposed method uses directional angles for underwater acoustic sources. A target signal transmitted from acoustic source is extracted using band-pass filters. Then, directional angles are estimated based on Bayesian process with generalized cross-correlation. The acquired angles are used as measurements for EKF-SLAM to estimate both vehicle location and locations of acoustic sources. Through these processes, the proposed method provides reliable estimation for two dimensional locations of underwater vehicles. Experimental results demonstrate the performance of the proposed method in a real sea environment.