• 한국멀티미디어학회논문지
• /
• 제25권3호
• /
• pp.546-557
• /
• 2022

Recently, the demand to interpret image data with artificial intelligence in various fields is rapidly increasing. Object recognition and detection techniques using deep learning are mainly used, and video integration analysis to determine unstructured object recognition is a particularly important problem. In the case of natural disasters or social disasters, there is a limit to the object recognition structure alone because it has an unstructured shape. In this paper, we propose intelligent video integration analysis system that can recognize unstructured objects based on video turning point and object detection. We also introduce a method to apply and evaluate object recognition using virtual augmented images from 2D to 3D through GAN.

• 한국전자통신학회논문지
• /
• 제13권6호
• /
• pp.1263-1268
• /
• 2018

본 논문에서는 영상 보안 감시를 위한 심층학습 객체 검출과 다중 객체 추적을 위한 확률적 데이터연관 필터를 연계한 영상분석 기법을 제안하고, GPU를 이용하여 구현하는 방안을 제시한다. 제안하는 영상분석 기법은 객체 검출과 추적으로 순차적으로 수행한다. 객체 검출을 위한 심층학습은 ResNet을 이용하고, 다중 객체 추적을 위하여 확률적 데이터 연관 필터를 적용한다. 제안하는 영상분석 기법은 임의의 영역으로 불법으로 침입하는 사람을 검출하거나 특정 공간에 출입하는 사람을 계수하는데 응용할 수 있다. 시뮬레이션을 통하여 약 25fps의 속도로 48채널의 영상을 분석할 수 있음을 보이고, RTSP 프로토콜을 통하여 실시간 영상분석이 가능함을 보인다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제8권4호
• /
• pp.430-441
• /
• 2002

비디오 객체 분할은 MPEG-4와 같은 객체기반 비디오 코딩을 위한 중요한 구성 요소이다. 본논문은 비디오 시퀸스에서 움직임 객체 분할을 위한 새로운 알고리즘과 VOP(Video Object Plane)추출 방법을 소개한다. 본 논문의 핵심은 시간적으로 변하는 움직임 객체 에지와 공간적 객체 에지 검출 결과를 효율적으로 조합하여 정확한 객체 경계를 추출하는 것이다. 이후 추출된 에지를 통하여 VOP를 생성한다. 본 알고리즘은 첫 번째 프레임을 기준영상으로 설정한 후 두 개의 연속된 프레임 사이의 움직임 픽셀 차이 값으로부터 시작된다. 차이영상을 추출한 후 차이영상에 Canny 에지 연산과 수리형태 녹임 연산(erosion)을 적용하고, 다음 프레임의 영상에 Canny 에지 연산과 수리형태 녹임 연산을 적용하여 두 프레임 사이의 에지 비교를 통하여 정확한 움직임 객체 경계를 추출한다. 이 과정에서 수리형태학 녹임 연산은 잘못된 객체 에지의 검출을 방지하는 작용을 한다. 두 영상 사이의 정확한 움직임 객체 에지(moving object edge)는 에지 크기를 조절하여 생성한다. 본 알고리즘은 픽셀 범위까지 고려한 정화한 객체의 경계를 얻음으로서 매우 쉬운 구현과 빠른 객체 추출을 보였다.

• 반도체디스플레이기술학회지
• /
• 제20권3호
• /
• pp.117-119
• /
• 2021

With the development of the industry, the use of drones in specific mission flight is being actively studied. These drones fly a specified path and perform repetitive tasks. if the drone system will detect objects in real time, the performance of these mission flight will increase. In this paper, we implement object detection system and mount GPU acceleration to maximize the efficiency of limited device resources with drone video using Tensorflow Lite which enables in-device inference from a mobile device and Mobile SDK of DJI, a drone manufacture. For performance comparison, the average processing time per frame was measured when object detection was performed using only the CPU and when object detection was performed using the CPU and GPU at the same time.

• 한국멀티미디어학회논문지
• /
• 제25권4호
• /
• pp.583-599
• /
• 2022

Although the object detection accuracy with a single image has been significantly improved with the advance of deep learning techniques, the detection accuracy for pig monitoring is challenged by occlusion problems due to a complex structure of a pig room such as food facility. These detection difficulties with a single image can be mitigated by using a video data. In this research, we propose a method in pig detection for video monitoring environment with a static camera. That is, by using both image processing and deep learning techniques, we can recognize a complex structure of a pig room and this information of the pig room can be utilized for improving the detection accuracy of pigs in the monitored pig room. Furthermore, we reduce the execution time overhead by applying a pruning technique for real-time video monitoring on an embedded board. Based on the experiment results with a video data set obtained from a commercial pig farm, we confirmed that the pigs could be detected more accurately in real-time, even on an embedded board.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2444-2463
• /
• 2020

Significant detection of video can more rationally allocate computing resources and reduce the amount of computation to improve accuracy. Deep learning can extract the edge features of the image, providing technical support for video saliency. This paper proposes a new detection method. We combine the Convolutional Neural Network (CNN) and the Deep Bidirectional LSTM Network (DB-LSTM) to learn the spatio-temporal features by exploring the object motion information and object motion information to generate video. A continuous frame of significant images. We also analyzed the sample database and found that human attention and significant conversion are time-dependent, so we also considered the significance detection of video cross-frame. Finally, experiments show that our method is superior to other advanced methods.

• 반도체디스플레이기술학회지
• /
• 제18권3호
• /
• pp.110-114
• /
• 2019

Recently, video monitoring system technology has been rapidly developed to monitor and respond quickly to various situations. In particular, computer vision and related research are being actively carried out to track objects in the video. This paper proposes an efficient multiple objects detection method based on convolutional neural network (CNN) for multiple objects tracking. The results of the experiment show that multiple objects can be detected and tracked in the video in the proposed method, and that our method is also good performance in complex environments.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1999년도 KOBA 방송기술 워크샵 KOBA Broadcasting Technology Workshop
• /
• pp.165.1-170
• /
• 1999

Object segmentation fro natural video scenes has recently become one of very active research to pics due to the object-based video coding standard MPEG-4. Object detection and isolation is also useful for object-based indexing and search of video content, which is a goal of the emerging new standard, MPEG-7. In this paper, an automatic segmentation method of moving objects in image sequence is presented which is applicable to multimedia content authoring for MPEG-4, and two different segmentation approaches suitable for surveillance applications are addressed in raw data domain and compressed bitstream domains. We also propose an object-based video description scheme based on object segmentation for video indexing purposes.

• 한국멀티미디어학회논문지
• /
• 제17권4호
• /
• pp.420-432
• /
• 2014

In detection of moving objects from video sequences, an essential process for intelligent visual surveillance, the cast shadows accompanying moving objects are different from background so that they may be easily extracted as foreground object blobs, which causes errors in localization, segmentation, tracking and classification of objects. Most of the previous research results about moving cast shadow detection and removal usually utilize color information about objects and scenes. In this paper, we proposes a novel cast shadow removal method of moving objects in gray level video data for visual surveillance application. The proposed method utilizes observations about edge patterns in the shadow region in the current frame and the corresponding region in the background scene, and applies Laplacian edge detector to the blob regions in the current frame and the corresponding regions in the background scene. Then, the product of the outcomes of application determines moving object blob pixels from the blob pixels in the foreground mask. The minimal rectangle regions containing all blob pixles classified as moving object pixels are extracted. The proposed method is simple but turns out practically very effective for Adative Gaussian Mixture Model-based object detection of intelligent visual surveillance applications, which is verified through experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권1호
• /
• pp.169-189
• /
• 2015

Detection of anomalous events from video streams is a challenging problem in many video surveillance applications. One such application that has received significant attention from the computer vision community is traffic video surveillance. In this paper, a Lossy Count based Sequential Temporal Pattern mining approach (LC-STP) is proposed for detecting spatio-temporal abnormal events (such as a traffic violation at junction) from sequences of video streams. The proposed approach relies mainly on spatial abstractions of each object, mining frequent temporal patterns in a sequence of video frames to form a regular temporal pattern. In order to detect each object in every frame, the input video is first pre-processed by applying Gaussian Mixture Models. After the detection of foreground objects, the tracking is carried out using block motion estimation by the three-step search method. The primitive events of the object are represented by assigning spatial and temporal symbols corresponding to their location and time information. These primitive events are analyzed to form a temporal pattern in a sequence of video frames, representing temporal relation between various object's primitive events. This is repeated for each window of sequences, and the support for temporal sequence is obtained based on LC-STP to discover regular patterns of normal events. Events deviating from these patterns are identified as anomalies. Unlike the traditional frequent item set mining methods, the proposed method generates maximal frequent patterns without candidate generation. Furthermore, experimental results show that the proposed method performs well and can detect video anomalies in real traffic video data.