Abstract:
Provided are a system and a method for image processing with G-ESA. The image processing system according to an embodiment of the present invention includes a GPU for collectively processing images inputted and outputting a processing result; and a CPU for controlling the GPU and receiving the processing result from the GPU. Thereby, the GPU collectively and actively processes the image processing function, thereby improving performance of whole system by reducing communication overhead between the CPU and the GPU.
Abstract:
Provided are a method for extracting an object in real time and a surveillance system using the same. According to an embodiment of the present invention, a method for extracting an object includes receiving an input image, extracting an object candidate group by subtracting a background from the input image, and extracting an object from the object candidate group. Accordingly, the real-time extraction of an object can be smoothly performed by increasing object extraction speed, and the accuracy and stability of the object extraction can be secured by reducing an object extraction error.
Abstract:
다양한 검증 기법이 복합된 전방 차량 영역 검증방법 및 장치가 제공된다. 본 발명의 실시예에 따른 차량 영역 검증 방법은, 현재 영상에서 차량 후보 영역들을 추출하고, 추출된 차량 후보 영역들의 형태를 분석하여 실제 차량이 존재하는 차량 영역인지 검증하는 한다. 이에 의해, 차량 미검출 또는 오검출을 줄일 수 있게 된다.
Abstract:
Provided are a camera calibration method using a multiple calibration technique and an image system using the same. The camera calibration method according to an embodiment of the present invention includes a step of extracting factors of cameras by photographing a pattern image; a step of converting the factors by arranging the pattern images; and a step of extracting the factors of the cameras of which the factors are converted again by photographing the pattern image again. Therefore, the factors of the cameras can be determined depending on installation and arrangement properties so that the present invention can generate a multi-view video and improve the quality of image processing such as depth image warping. Ultimately, the present invention can perform clean three-dimensional effects and converts viewpoints when the multi-view video is played. [Reference numerals] (AA) Start; (BB) End; (S410) Photographing a first pattern image; (S420) Correcting a primary camera; (S430) Arranging images; (S440) Photographing a second pattern image; (S450) Correcting a second camera
Abstract:
본 발명은 영상 분석 서버에 관한 것이며, 보다 구체적으로는 영상의 모든 피사체를 분석하여 잠재적인 위험 요소까지도 분석 데이터를 생성하는 영상 분석 서버에 관한 것이다. 본 발명의 일실시예에 다른 영상 분석 서버는 내장된 영상 분석 알고리즘을 통해, 입력 영상을 분석하고, 분석된 결과를 출력하는 영상분석 모듈; 상기 영상분석 모듈를 위한 메모리를 할당하고, 상기 영상분석 모듈간의 이벤트를 관리하는 관리 모듈; 사용자 단말기로부터 분석 시작 명령을 전달받고, 상기 분석 시작 명령을 상기 관리 모듈에 전달하고, 상기 영상분석 모듈을 통해 분석된 영상 분석 결과를 사용자 단말기로 전달하는 서버관리 모듈; 및 데이터를 저장하는 메모리;를 포함하고, 상기 영상분석 모듈은 복수이며, 상기 복수 개의 영상분석 모듈들이 상기 메모리를 함께 공유하여 사용함을 특징으로 할 수 있다.
Abstract:
The present invention relates to a video retrieval system and a video analysis server and, more particularly, to a video analysis server for analyzing a video, storing a subject in the video and features of the subject, and managing the subject and features, and a video retrieval system for retrieving a video using analysis data of the video analysis server. The video analysis server according to an embodiment of the present invention comprises: a subject detection module for searching a subject by analyzing video data and extracting a subject recognition video of which the background is removed from the video data; a feature extraction module for extracting feature data of the subject by analyzing the subject recognition video, generating subject feature data by converting the feature data into a text form or a binary form, and obtaining reproduction time of the video data having the subject therein as subject retrieval time; a storing unit for storing the subject retrieval time and the subject feature data as video analysis data; and a control unit for operating the subject detection module and the feature extraction module. [Reference numerals] (1) Image analyzing data;(AA) Image analyzing;(BB) Searching server;(CC) Searching client;(DD) Warning server (control)
Abstract:
PURPOSE: An eye detection device and a method thereof are provided to recognize eyes regardless of illumination change, thereby implementing a high speed algorithm in various image application fields. CONSTITUTION: An image storage unit(120) stores a digital image by receiving the same from an image input unit(110). First to third preprocessing units(130-150) perform preprocessing by using a histogram equalization method and a neighbor normalization method. A face area detection unit(160) detects a face area from the digital image which is preprocessed by the first preprocessing unit. An eye area detection unit(170) detects a candidate eye area from the face area which is preprocessed by the second preprocessing unit. An eye detection unit(180) scans a reference eye sample in the candidate eye area which is preprocessed by the third preprocessing unit and detects eyes. The eyes are formed of pixels having similarity higher than a set value. [Reference numerals] (110,120) Image input unit; (130) First preprocessing unit; (140) Second preprocessing unit; (150) Third preprocessing unit; (160) Face area detection unit; (170) Eye area detection unit; (180) Eye detection unit; (190) Database; (AA) Image input