• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.65 no.4
• /
• pp.255-263
• /
• 2020

In this study, we evaluated the salinity tolerance of five forage rice cultivars (Mogwoo, Mogyang, Miwoo, Jowoo, and Yeongwoo) with respect to germination, seedling growth, productivity, and feed values in a reclaimed paddy field in Muan, Korea. We found that the cultivars Mogwoo, Miwoo, Jowoo, and Yeongwoo showed normal germination and seedling growth, even at saline concentrations of between 0.1% and 0.5%, whereas in contrast, there were significant reductions in the germination and seedling growth of Mokyang with an increase in salt concentration. Among the five cultivars assessed, the seedling growth of Mogwoo and Yeongwoo was relatively higher at different salt concentrations in hydroponic and sand cultivation. Furthermore, cultivation of the five cultivars in the reclaimed paddy field with an initial salt concentration of 0.3% revealed that Yeongwoo was relatively superior in terms of yield and feed value. In conclusion, the germination and early growth of Yeongwoo were relatively good at high salt concentrations, and the yield and forage value of this cultivar in a reclaimed paddy field were also relatively superior to those of the other assessed varieties.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.4
• /
• pp.957-957
• /
• 2017

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.40 no.3
• /
• pp.138-148
• /
• 2020

This study was carried out to find out the changes in the growth characteristics and feed value of the three different whole-crop silage rice cultivars of whole-crop silage rice such as Jonong, Yeongwoo and Mogwoo to develop an efficient double cropping system. This study showed that there were significant differences biomass and feed values among cultivars but no clear difference among transplanting dates. Dry weight and height were in order of Mogwoo, Yeongwoo, Jonong (p<0.05). Dry weight and feed value of Jonong showed no significant difference after 21 days after heading (DAH), it was expected to be harvested before DAH 30 days. Yeongwoo showed a lower dry weight than Mogwoo, but heading date was earlier than Mogwoo, so one can expect a higher feed value than Mogwoo. Mogwoo had lower crude protein and total digestible nutrient than the other two cultivars but relative feed value in stem was higher than that of the other cultivars, but had higher dry weight than other cultivars so it was considered to take an advantage as a silage rice. Therefore, the results of this study suggest that the selection of whole-crop silage rice on the cropping system be made comprehensively by considering the heading characteristics of the cultivars and the feed value.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.220-220
• /
• 2017

Soybean (Glycine max (L.) Merill) is a very outstanding material crop with high protein and oil contents. We conducted this study to evaluate forage value and usability of soybean varieties as livestock forage. Three soybeans cultivars, OT93-26, Geomjeongsaeol, and Pungwon, were evaluated for forage use in this study, and Kwangpyeongok and Yeongwoo were used as check forage corn and rice, respectively. The whole soybean plants were harvested at the R5 (beginning seed development)- and R6 (full seed)-reproductive stages for analyzing forage usability and quality. Days to harvesting of the R5 stage-OT93-26 was the shortest among the tested crops while that of Yeongwoo was 122 days. The fresh and dry matter yields of all 3 soybeans were greater at R6 stage than at R5. Crude protein of the soybean cultivars harvested had a higher compared to the rice and corn regardless of the harvesting stage. Contents of crude fiber, neutral detergent fiber and acid detergent fiber of Yeongwoo had the lowest whereas Pungwon harvested at R5 were the highest. Among the soybeans, digestible dry matter, dry matter intake, and relative feed value of R6-harvested Geomjeongsaeol and Pungwon were high more compared to those at the R5-harvested, but in case of OT93-26 those at R6 stage were inversely measured rather than those at R5 stage. In conclusion, soybean can be used as s forage with high nutritive value for livestock. Moreover, Geomjeongsaeol can be applied to develop new forage soybean varieties with high nutritive value, and R6 stage is the optimum harvesting stage in yield and quality of the tested soybeans more than R5.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.67 no.4
• /
• pp.326-334
• /
• 2022

This study was carried out to investigate the optimal nitrogen concentration level suitable for forage rice growth by hydroponic cultivation in the salinity concentration of 0.1~0.3% which is similar to that of Muan reclaimed paddy field, and based on this results, to estimate optimal nitrogen fertilization level by field experiment in Muan reclaimed paddy for maximum forage production by cultivation of Yeongwoo rice. As a result of the growth response to the salt and nitrogen concentrations in the hydroponic cultivation experiment, the growth amount increased as the nitrogen concentration increased in the range of 0~24 me/L in the absence of salt stress. However, at a salt concentration of 0.1~0.3%, the growth amount was the highest at a nitrogen concentration of 12 me/L, and at higher nitrogen concentrations of that, the rice growth decreased as the nitrogen concentration increased. Therefore, nitrogen concentration of 12 me/L was judged to be an appropriate concentration for forage rice growth at salt concentration of 0.1~0.3%, and a nitrogen fertilization amount level corresponding to a nitrogen concentration of 12 me/L was actually applied to the Muan reclaimed paddy field for forage rice cultivation during two years. The amount of nitrogen fertilizer was tested with three treatments, which are 18 kg/10a considered appropriate, and 1.5 times and 2 times of the appropriate amount, and the planting density was tested with 2 treatments of 15 hills/m² and 26 hills/m². As a result of the reclaimed paddy field experiment, the yield was the highest when nitrogen fertilizer was applied at 18 kg/10a in the planting density of both treatments. Looking at the yield according to planting density, the high planting density plot yielded higher than the low planting density plot. In other words, when the planting density was 26 hills/m² and the nitrogen fertilization amount was 18 kg/10, the highest dry matter yield of 1,763 kg/10a was obtained. From the results of hydroponics and reclaimed field experiments, we could conclude that the productivity of forage rice decreased more as the nitrogen concentration increased when the nitrogen concentration was higher than the optimal level under salt stress.

• Journal of KIISE
• /
• v.43 no.2
• /
• pp.186-195
• /
• 2016

This paper proposes a vehicle license plate detection method in real road environments using 8 bit-MCT features and a landmark-based Adaboost method. The proposed method allows identification of the potential license plate region, and generates a saliency map that presents the license plate's location probability based on the Adaboost classification score. The candidate regions whose scores are higher than the given threshold are chosen from the saliency map. Each candidate region is adjusted by the local image variance and verified by the SVM and the histograms of the 8bit-MCT features. The proposed method achieves a detection accuracy of 85% from various road images in Korea and Europe.

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.203-212
• /
• 2015

This paper proposes a traffic sign recognition method in real road environments. The video stream in driving environments has two different characteristics compared to a general object video stream. First, the number of traffic sign types is limited and their shapes are mostly simple. Second, the camera cannot take clear pictures in the road scenes since there are many illumination changes and weather conditions are continuously changing. In this paper, we improve a modified census transform(MCT) to extract features effectively from the road scenes that have many illumination changes. The extracted features are collected by histograms and are transformed by the dense descriptors into very high dimensional vectors. Then, the high dimensional descriptors are encoded into a low dimensional feature vector by Fisher-vector coding and Gaussian Mixture Model. The proposed method shows illumination invariant detection and recognition, and the performance is sufficient to detect and recognize traffic signs in real-time with high accuracy.

• Korean Journal of Cognitive Science
• /
• v.25 no.1
• /
• pp.51-71
• /
• 2014

This paper presents an image enhancement method in real road traffic scenes. The images captured by the camera on the car cannot keep the color constancy as illumination or weather changes. In the real environment, these problems are more worse at back light conditions and at night that make more difficult to the applications of the vision-based intelligent vehicles. Using the existing image enhancement methods without considering the position and intensity of the light source and their geometric relations the image quality can even be deteriorated. Thus, this paper presents a fast and effective method for image enhancement resembling human cognitive system which consists of 1) image preprocessing, 2) color-contrast evaluation, 3) alpha blending of over/under estimated image and preprocessed image. An input image is first preprocessed by gamma correction, and then enhanced by an Automatic Color Enhancement(ACE) method. Finally, the preprocessed image and the ACE image are blended to improve image visibility. The proposed method shows drastically enhanced results visually, and improves the performance in traffic sign detection of the vision based intelligent vehicle applications.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.3
• /
• pp.483-492
• /
• 2017

Precipitation is one of key components in hydrological modeling and water balance studies. A comprehensive, optimized and sustainable water balance monitoring requires the availability of accurate precipitation data. The amount of precipitation measured in a gauge is less than the actual precipitation reaching the ground. The objective of this study is to determine the wind-induced under-catch of solid precipitation and develop a continuous adjustment function for measurements of all types of winter precipitation (from rain to dry snow), which can be used for operational measurements based on data available at standard automatic weather stations. This study provides Bayesian analysis for the systematic structure of catch ratio in precipitation measurement.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.349-358
• /
• 2021

Recently, a method of finding the attention area or localization area for an object of an image using CAM (Class Activation Map)[1] has been variously carried out as a study of WSOL (Weakly Supervised Object Localization). The attention area extraction from the object heat map using CAM has a disadvantage in that it cannot find the entire area of the object by focusing mainly on the part where the features are most concentrated in the object. To improve this, using CAM and Selective Search[6] together, we first expand the attention area in the heat map, and a Gaussian smoothing is applied to the extended area to generate retraining data. Finally we train the data to expand the attention area of the objects. The proposed method requires retraining only once, and the search time to find an localization area is greatly reduced since the selective search is not needed in this stage. Through the experiment, the attention area was expanded from the existing CAM heat maps, and in the calculation of IOU (Intersection of Union) with the ground truth for the bounding box of the expanded attention area, about 58% was improved compared to the existing CAM.