• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.249-254
• /
• 2006

Aerial photo process with digital camera has some benefits. It is fast and simple by digital way in comparison with aerial photo based on film. Also it works with GPS/INS device to do direct geo-referencing, In this study, AT result from using direct exterior factors, exterior factors extracting from GPS/INS data and digital map and GCP is produced. In base on it, ortho images are produced and compared with surveying data.

• Journal of Korean Society for Geospatial Information Science
• /
• v.2 no.2 s.4
• /
• pp.131-142
• /
• 1994

Generally, there are two methods which generates the base map of Geo-Spatial Information System(GSIS). one is the digitizing of existing map, and the other is the analytical plotting method editing data acquired by sensors using computers. But the analytical plotting method and method of the digitizing of existing map is technically complex and has the disadvantages in the costs and time. The subject region of study(the Kwangyang province), was photographed by aircraft, and photographing scale was 1/6,000. Then this area was divided into two specific regions, the residential area, and the agricultural area. In this study, we developed the algorithm that generated base map of database in GSIS from the aerial photo. This algorithm is as followed. First, the digital aerial photos were generated using these aerial photos. Second, these digital aerial photos were enhanced by implementing the histogram equalization. Third, the objects of the enhanced images were extracted by implementing thresholding and edged detection techiques of image segmentation. Finally, these images could be used to updated the base map of database in GSIS. The result obtained from this study showed that method used by this study were more efficient than existing method in costs and time.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.51-57
• /
• 2018

The purpose of this study is to find a valid link between color and tourism experience. We analyzed color that extracted by Aerial photo by IRI Image Scale to find color image. As an indicator of the experience of tourism, a review of the Tripadvisor was selected and analyzed through text mining. Results using text mining results and IRI image scales were generally inconsistent. To identify problems with aerial photo, the results of the analysis using the representative photographs provided by the Tripadvisor in the same way were the same as before. This indicate that details are key of tourism than the image of the overall background. This study presents new research directions by combining color analysis studies with text mining.

• Water for future
• /
• v.7 no.2
• /
• pp.34-46
• /
• 1974

This paper provides a new geomorphological approach for survey of potential flood damages and for preparation of cartographically accurate flood maps. floods are possibly the worst disasters we have recorded in he past and may expect in the future. Interpretation of aerial photographs of river basin enables us to determine the nature of floods by investigating the maximum extent of inundated areas in the past. Most of the typical dangerous spots, highly susceptible for flood disasters can be systematically identified by analyzin lithologic, structural, and geomorphic cycle.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.217-222
• /
• 2006

In this study, we performed three dimensional(3-D) modeling and simulation of terrain surfaces by using large scale aerial photographs. The objectives of this study are to use landscape analysis including 3-D database of built environments. The test area is selected around Olympic stadium located in Susung-gu, Daegu. A 1:5,000 scale of ortho-photo map is generated by photogrammetric procedures from 1:20,000 scale of aerial photographs, Digital Elevation Model (DEM) is also extracted from stereo aerial photographs or digital maps. The heights of buildings are determined using GPS control survey and aerial photographs in the test area, DEMs are extracted from the digital map. And then the two are combined three-dimensional changes of landscape views of buildings with terrain are simulated.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.23 no.3
• /
• pp.303-312
• /
• 2005

Digital map, DEM and orthophoto were produced by using PC based digital photogrammetric system and aerial photo images that were obtained with scale of 1/5,000 and scanning density of 1200dpi and 600dpi, and the accuracies of these outputs were evaluated by various methods. Non-skilled operator produced digital map with PC based digital photogrammetric system and aerial photo images scanned by 1200dpi. The results showed that it was impossible to insert contour lines, but the rest elements could be drawn with the accuracy of 1/1,000. In automatic generation of DEM, scanning density of aerial photo and grid interval of DEM didn't affect the accuracy of DEM. In production of orthophoto, we could know that the larger grid interval of DEM, the lower accuracy of orthophoto, but scanning density of original image had more effect on quality of orthophoto. By the way, accuracy comparison between orthophoto and digital map with same check points showed that orthophoto was more accurate than digital map, and orthophoto could be used in more diverse areas. Hereafter in civilian part, aerial photo image and PC based digital photogrammetric system could make practical application of data correction and update in GIS.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.375-377
• /
• 2003

In this study, we employ the control patches, which have been created in previous photogrammetric projects, serving for the candidates of the control points that are likely to be found in the newly taken photos by utilizing image matching technique. Among others, the successful implementation of the above idea lies in the underlying factors: (1). Predicting the control patches and projecting them onto new photos; (2). Alignment of control patches with respect to the new photos; (3). Generating the equivalent ground elements of control patches versus the new photos for the purpose of correlation; (4). Developing effective matching methods and matching strategy; (5). Refining the exterior orientation parameters. What may show significance in this work comparing to traditional aerial-triangulation chain is that whenever at least three matched control patches succeed in a single photo, it follows that single photo orientation is applicable. The experiments suggest the potential efficiency of automatic control point measurement from control patch database and photo orientation by the proposed workflow.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.14 no.1
• /
• pp.89-95
• /
• 1996

As an attempt to apply GPS technique to aerial photogrammetry, an effort is exerted to replace the ground control points that were necessary in the traditional aerial photogrammetry with the aerial control by measuring the position of the camera exposure. In this study, various situations are simulated to test the conditions that affect the positioning of the points in aerial photogrammetry for the use of GPS data. From the result of the simulations, the necessary conditions and the applicable values to produce a 1:1, 000 topographical map were suggested. In the case of a photo block consists of 104 photos, we found a minimum of six ground control points make acceptable accuracy under the condition of below $10\mu{m}$ image positional error and with the ground observations.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.1
• /
• pp.143-148
• /
• 2008

This Study is about driving simulation after road design by 3D-GIS in digital elevation model from digital aerial photogrammetry. For designing roads efficiently it's very important to consider geographical features before design when analyze the view. Nevertheless, existing studies is mainly restricted in the mountainous, despite of using digital map or aerial photogrammetry and the study which used aerial photo in the area where the road designing is made really is not get executed. Therefore, this study will do 3D-road design and driving simulation by appling really road design data to topography, on the basis of digital elevation generated from aerial photogrammetry.

• Korean Journal of Remote Sensing
• /
• v.37 no.4
• /
• pp.747-761
• /
• 2021

With the increasing application of UAVs in intelligent transportation systems, vehicle detection for aerial images has become an essential engineering technology and has academic research significance. In this paper, a vehicle detection method for aerial images based on the YOLOv4 deep learning algorithm is presented. At present, the most known datasets are VOC (The PASCAL Visual Object Classes Challenge), ImageNet, and COCO (Microsoft Common Objects in Context), which comply with the vehicle detection from UAV. An integrated dataset not only reflects its quantity and photo quality but also its diversity which affects the detection accuracy. The method integrates three public aerial image datasets VAID, UAVD, DOTA suitable for YOLOv4. The training model presents good test results especially for small objects, rotating objects, as well as compact and dense objects, and meets the real-time detection requirements. For future work, we will integrate one more aerial image dataset acquired by our lab to increase the number and diversity of training samples, at the same time, while meeting the real-time requirements.