• Title/Summary/Keyword: 영상인력

Search Result 308, Processing Time 0.027 seconds

A Study on the Game Violence Detection System Using Cloud Vision API (Cloud Vision API를 활용한 게임물 폭력성 감지 시스템에 관한 연구)

  • Jo, Hojeong;Moon, Mikyeong
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2022.07a
    • /
    • pp.509-510
    • /
    • 2022
  • 한 해 100만건 이상의 모바일 게임이 출시되고 있으며, 게임 수가 많은 만큼 게임물 등급 관리에 있어서 객관적이고 투명한 업무처리는 필수적이다. 그러나 현재 사업자 자체 등급분류는 오직 게임 개발사가 제출한 서류에 의존하며, 사후 모니터링을 통해 제재하는 실정이다. 이에 따라, 사전에 폭력성 유뮤를 식별할 수 있는 기술이 필요하다. 본 논문에서는 Cloud Vision API를 활용하여 프레임 수를 설정하고 해당 프레임에 대한 폭력성 정도를 수치로 출력하여 해당 영상에 문제 유무를 사전에 식별할 수 있도록 돕는 시스템에 대해 기술한다. 이 시스템을 통해 게임물관리위원회 인력과 예산 한계로 인해 계속 불거지고 있는 연 100만 건에 달하는 등급분류 처리의 정확성과 사후 모니터링에 효과가 있을 것이다.

  • PDF

AI Self-driving CCTV System for Smartening Crime Prevention Facilities (방범 설비의 스마트화를 위한 인공지능 자율주행 CCTV 시스템)

  • Yeon-Kyu Kwak;Ye-Jin Kim;Jin-Woo Woo;Dong-Gyu Jung;Sang-Oh Yoo
    • Annual Conference of KIPS
    • /
    • 2023.11a
    • /
    • pp.840-841
    • /
    • 2023
  • 본 논문에서는 치안 공백 문제 해결을 위해 인공지능 CCTV를 소개한다. 자율주행 RC카의 센서 및 영상 처리로 행인의 이상 행동을 자동 탐지하고 이를 통합 관제 애플리케이션과 웹사이트로 확인 및 제어하는 시스템을 개발하였다. 이 시스템은 부족한 인력을 지원하고 CCTV 사각지대를 최소화하며, 이를 통해 공공 안전에 이바지함으로써 시민들이 안전하게 살 수 있는 사회가 구축되기를 기대한다.

A Study on Development of Systems to Enforce the interfering Cars on the Ramp (끼어들기 단속시스템 개발 연구)

  • Lee, Ho-Won;Hyun, Cheol-Seung;Joo, Doo-Hwan;Jeong, Jun-Ha;Lee, Choul-Ki
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.11 no.5
    • /
    • pp.7-14
    • /
    • 2012
  • We frequently confront with cars interfering into our lane on the ramp. We suffered from serious traffic congestion due to the interfering cars. But the police enforcement has not done actively because it's hard to enforce. In this study, we have evaluated the systems to enforce cutting-in cars through the field test. Generally, the image processing method depends on the weather. To overcome this limitation we proposed a new algorithm combined with section detection method. In the filed test we concluded the results as follows. Whereas the violation detection rate of the general image processing was 58.2%, a new algorithm proposed by this study was 74.5%. And, an error rate enforcing vehicles that do not violate was 0.0%. Also, we can use the existing facilities, such as street light because of compact and lightweight systems which are integrated camera with controller. Therefore, we concluded that it is possible to enforce the interfering Cars using vehicle enforcement systems.

Detection Method of Human Face, Facial Components and Rotation Angle Using Color Value and Partial Template (컬러정보와 부분 템플릿을 이용한 얼굴영역, 요소 및 회전각 검출)

  • Lee, Mi-Ae;Park, Ki-Soo
    • The KIPS Transactions:PartB
    • /
    • v.10B no.4
    • /
    • pp.465-472
    • /
    • 2003
  • For an effective pre-treatment process of a face input image, it is necessary to detect each of face components, calculate the face area, and estimate the rotary angle of the face. A proposed method of this study can estimate an robust result under such renditions as some different levels of illumination, variable fate sizes, fate rotation angels, and background color similar to skin color of the face. The first step of the proposed method detects the estimated face area that can be calculated by both adapted skin color Information of the band-wide HSV color coordinate converted from RGB coordinate, and skin color Information using histogram. Using the results of the former processes, we can detect a lip area within an estimated face area. After estimating a rotary angle slope of the lip area along the X axis, the method determines the face shape based on face information. After detecting eyes in face area by matching a partial template which is made with both eyes, we can estimate Y axis rotary angle by calculating the eye´s locations in three dimensional space in the reference of the face area. As a result of the experiment on various face images, the effectuality of proposed algorithm was verified.

The Technical Solution for Various Array Methods in Resistivity Survey (전기비저항 탐사의 다양한 배열 방법에 대한 해석 기법)

  • Park, Chung-Hwa
    • The Journal of Engineering Geology
    • /
    • v.17 no.1 s.50
    • /
    • pp.49-55
    • /
    • 2007
  • Various away methods are required in the electrical resistivity survey in order to find anomalous zone reliably. Array methods are classified as several groups. Among these group, a curved survey along the fixed elevation is designed to increase the mobility of men and survey equipments at the rough terrain. Another method is performed at the survey using inclined, curved, and horizontal boreholes. A survey can also be conducted in an arbitrary location by measurements of potentials for a multi sources. The complex data acquired using various away methods are represented by a correct images reconstructed from the 3D inversion. The element division is applied to the region in which the boreholes are curved and inclined because of a spatial discrepancies between the coordinate of each electrode and the nodal point in a model. The resistivity images are obtained from a good agreement for the anomalous zones in open slope and in survey using an inclined borehole.

Optimization of the Cloth Simulation Pipeline in Production of 3D Computer Animation (3D 컴퓨터 애니메이션 제작에서 Cloth Simulation 을 위한 제작파이프라인의 최적화)

  • Kwak, Dong-Min;Choi, Chul-Yong;Kim, Ki-Hong;Lee, Dong-Hoon
    • The Journal of the Korea Contents Association
    • /
    • v.9 no.8
    • /
    • pp.198-207
    • /
    • 2009
  • Recently, it was possible to represent the realistic clothes in the cloth simulation along with growth of 3D computer animation such as visual contents. In addition, because of the development of H/W(Hardware) and S/W(Software), the accessibility and participation are growing. However, in order to make the image of high quality of 3D animation, the optimized production pipeline was need. In this paper, in order to overcome the limitation of exiting 3D computer animation production pipeline, we propose the optimized production pipeline of the cloth simulation. Our production pipeline makes the optimization arrangement in consideration of the mobility in order to supplement the related structure limit toward each part of the existing pipeline. Moreover, by utilizing the dummy cloth the association nature with the animation part is solved and a performance is improved. The proposal pipeline actually introduced to the animation production. And then we can improve the performance production time and production manpower consumption. Consequently, our pipeline is guaranteed an optimized work by emphasizing a connection in the direct image production.

A Bone Age Assessment Method Based on Normalized Shape Model (정규화된 형상 모델을 이용한 뼈 나이 측정 방법)

  • Yoo, Ju-Woan;Lee, Jong-Min;Kim, Whoi-Yul
    • Journal of Korea Multimedia Society
    • /
    • v.12 no.3
    • /
    • pp.383-396
    • /
    • 2009
  • Bone age assessment has been widely used in pediatrics to identify endocrine problems of children. Since the number of trained doctors is far less than the demands, there has been numerous requests for automatic estimation of bone age. Therefore, in this paper, we propose an automatic bone age assessment method that utilizes pattern classification techniques. The proposed method consists of three modules; a finger segmentation module, a normalized shape model generation module and a bone age estimation module. The finger segmentation module segments fingers and epiphyseal regions by means of various image processing algorithms. The shape model abstraction module employ ASM to improves the accuracy of feature extraction for bone age estimation. In addition, SVM is used for estimation of bone age. Features for the estimation include the length of bone and the ratios of bone length. We evaluated the performance of the proposed method through statistical analysis by comparing the bone age assessment results by clinical experts and the proposed automatic method. Through the experimental results, the mean error of the assessment was 0.679 year, which was better than the average error acceptable in clinical practice.

  • PDF

Temperture Monitoring of Chejoo island using satellite Image (인공위성 영상을 이용한 제주도 주변 해역의 온도 모니터링)

  • Kang, Joon-Mook;Yun, Hee-Chon;Lee, Sung-Soon
    • Journal of Korean Society for Geospatial Information Science
    • /
    • v.10 no.1 s.19
    • /
    • pp.101-108
    • /
    • 2002
  • The studies using satellite data have been progressed in many area. Especially, Landsat data have been widely used due to its wide coverage. To establish a plan for preserving fishing and environment preservation, measurement of sea temperature is important. The measurement of the sea temperature was made on the ship. However, the measurement on the ship could not provide sufficient information due to the poor timing with relatively longer measurement, and point-based data acquisition. Thus remote sensing technique is required because satellite image data offer more wide coverage in sea temperature monitoring. The purpose of this paper was to study on the sea temperature monitoring with thermal band information of Landsat ETM+. From this study, sea temperature map of Cheju island has been made efficiently.

  • PDF

A Study on Performace Evaluation of ITS Detectors using UAV (UAV를 활용한 ITS검지기 성능평가에 관한 연구)

  • Kang, Tae-Gyung;Lee, Si-Bok
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.17 no.6
    • /
    • pp.111-120
    • /
    • 2018
  • This study focuses on utilizing drones for performance evaluation of ITS detectors and analyzing economic feasibility when performance evaluation is conducted by the traffic management center's own personnel using drones. The study sites were selected from DSRC, video detector, and radar detector locations and drone filming was conducted to obtain travel speed, queue length, and delay time and compare with the detector data. It was shown that drones can be very effectively used to evaluate performance of major ITS detectors such as DSRC and video detectors. In addition, it was analyzed that a drone operated by the traffic management center's own personnel provides very economic solution for ITS detector performance evaluation when compared to consignment by external agencies.

Computer Vision-based Automated Adhesive Quality Inspection Model of Exterior Insulation and Finishing System (컴퓨터 비전 기반 외단열 공사의 접착제 도포품질 감리 자동화 모델)

  • Yoon, Sebeen;Kang, Mingyun;Jang, Hyounseung;Kim, Taehoon
    • Journal of the Korea Institute of Building Construction
    • /
    • v.23 no.2
    • /
    • pp.165-173
    • /
    • 2023
  • This research proposed a model for automatically monitoring the quality of insulation adhesive application in external insulation construction. Upon case implementation, the area segmentation model demonstrated a 92.3% accuracy, while the area and distance calculation accuracies of the proposed model were 98.8% and 96.7%, respectively. These findings suggest that the model can effectively prevent the most common insulation defect, insulation failure, while simultaneously minimizing the need for on-site supervisory personnel during external insulation construction. This, in turn, contributes to the enhancement of the external insulation system. Moving forward, we plan to gather construction images of various external insulation methods to refine the image segmentation model's performance and develop a model capable of automatically monitoring scenarios with a considerable number of insulation materials in the image.