• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.439-449
• /
• 2023

This paper deals with a resource efficient artificial intelligence (AI) service architecture for multi-channel video streams. As an AI service, we consider the object detection model, which is the most representative for video applications. Since most object detection models are basically designed for a single channel video stream, the utilization of the additional resource for multi-channel video stream processing is inevitable. Therefore, we propose a resource efficient AI service framework, which can be associated with various AI service models. Our framework is designed based on the modular architecture, which consists of adaptive frame control (AFC) Manager, multiplexer (MUX), adaptive channel selector (ACS), and YOLO interface units. In order to run only a single YOLO process without regard to the number of channels, we propose a novel approach efficiently dealing with multi-channel input streams. Through the experiment, it is shown that the framework is capable of performing object detection service with minimum resource utilization even in the circumstance of multi-channel streams. In addition, each service can be guaranteed within a deadline.

• Journal of Internet Computing and Services
• /
• v.3 no.5
• /
• pp.51-62
• /
• 2002

The development of computer technology and the advancement of the technology of information and communications spread the technology of multimedia and increased the use of multimedia data with large capacity, Users can grasp the overall video data and they are able to play wanted video back. To grasp the overall video data it is necessary to offer the list of summarized video data information, In order to search video efficiently on index process of video data is essential and it is also indispensable skill, Therefore, this thesis suggested the effective method about the cut detection of frames which will become a basis of an index based on contents of video image data. This suggested method was detected as the unchanging pixel color intelligence value, classified into diagonal direction. Pixel value of color detected in each frame of video data is stored as A(i, j) matrix-i is the number of frames. j is an image height of frame. By using the stored pixel value as the method of sum of squared difference of color two frames I calculated a specified value difference between frames and detected cut quickly and exactly in case it is bigger than threshold value set in advance, To carry out on experiment on the cut detection of frames comprehensively, I experimented on many kinds of video. analyzing and comparing efficiency of the cut detection system.

• Journal of Internet Computing and Services
• /
• v.11 no.6
• /
• pp.31-39
• /
• 2010

The Generalized Hough Transform(GHT) is the most used algorithm for circle detection with high accuracy. However, it requires many computation time, because many different templates are applied in order to find circles of various size. In the case of circle detection and tracking in video, the classical approach applies GHT for each frame in video and thus needs much high processing time for all frames. This paper proposes the fast GHT algorithm in video, using two consecutive frames are similar. In the proposed algorithm, a change-driven method conducts GHT only when two consecutive frames have many changes, and trajectory-based method does GHT in candidate areas and with candidate radius using circles detected in a previous frame. The algorithm can reduce computation time by reducing the number of frames, the edge count, and the number of searching circles, as factors which affects the speed of GHT. Our experimental results show that the algorithm successfully detects circles with less processing time and no loss of accuracy in video acquisited by a fixed camera and a moving camera.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.71-80
• /
• 2012

This paper proposes vehicle detection and tracking algorithm using a CCD camera. The proposed algorithm uses Haar-like wavelet edge detector to detect features of vehicle and estimates vehicle's location using calibration information of an image. After that, extract accumulated vehicle information in continuous k images to improve reliability. Finally, obtained vehicle region becomes a template image to find same object in the next continuous image using SURF(Speeded Up Robust Features). The template image is updated in the every frame. In order to reduce SURF processing time, ROI(Region of Interesting) region is limited on expended area of detected vehicle location in the previous frame image. This algorithm repeats detection and tracking progress until no corresponding points are found. The experimental result shows efficiency of proposed algorithm using images obtained on the road.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.2
• /
• pp.33-44
• /
• 2010

This paper propose the structure of real-time face detection hardware architecture for robot vision processing applications. The proposed architecture is robust against illumination changes and operates at no less than 60 frames per second. It uses Modified Census Transform to obtain face characteristics robust against illumination changes. And the AdaBoost algorithm is adopted to learn and generate the characteristics of the face data, and finally detected the face using this data. This paper describes the face detection hardware structure composed of Memory Interface, Image Scaler, MCT Generator, Candidate Detector, Confidence Comparator, Position Resizer, Data Grouper, and Detected Result Display, and verification Result of Hardware Implementation with using Virtex5 LX330 FPGA of Xilinx. Verification result with using the images from a camera showed that maximum 32 faces per one frame can be detected at the speed of maximum 149 frame per second.

• Journal of Microbiology and Biotechnology
• /
• v.30 no.5
• /
• pp.662-667
• /
• 2020

Epidermal growth factor receptor (EGFR) mutations are not only genetic markers for diagnosis but also biomarkers of clinical-response against tyrosine kinase inhibitors (TKIs) in non-small cell lung cancer (NSCLC). Among the EGFR mutations, the in-frame deletion mutation in EGFR exon 19 kinase domain (EGFR exon 19-del) is the most frequent mutation, accounting for about 45% of EGFR mutations in NSCLCs. Development of sensitive method for detecting the EGFR mutation is highly required to make a better screening for drug-response in the treatment of NSCLC patients. Here, we developed a fluorometric tandem gene amplification assay for sensitive detection of low-abundance EGFR exon 19-del mutant genomic DNA. The method consists of pre-amplification with PCR, thermal cycling of ligation by Taq ligase, and subsequent rolling circle amplification (RCA). PCR-amplified DNA from genomic DNA samples was used as splint DNA to conjugate both ends of linear padlock DNA, generating circular padlock DNA template for RCA. Long stretches of ssDNA harboring multiple copies of G-quadruplex structure was generated in RCA and detected by thioflavin T (ThT) fluorescence, which is specifically intercalated into the G-quadruplex, emitting strong fluorescence. Sensitivity of tandem gene amplification assay for detection of the EGFR exon 19-del from gDNA was as low as 3.6 pg, and mutant gDNA present in the pooled normal plasma was readily detected as low as 1% fraction. Hence, fluorometric detection of low-abundance EGFR exon 19 deletion mutation using tandem gene amplification may be applicable to clinical diagnosis of NSCLC patients with appropriate TKI treatment.

• Journal of Korea Multimedia Society
• /
• v.10 no.4
• /
• pp.432-440
• /
• 2007

In this paper, we propose a small target detection algorithm for FLIR image with complex background. First, we compute the motion information of target from the difference between the current frame and the created background image. However, the slow speed of target cause that it has the very low gray level value in the difference image. To improve the gray level value, we perform the local gamma correction for difference image. So, the detection index is computed by using statistical characteristics in the improved image and then we chose the lowest detection index a true target. Experimental results show that the proposed method has significantly the good detection performance.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.3
• /
• pp.389-396
• /
• 2001

In detection of a scene change of the moving pictures which has massive information capacity, the temporal sampling method has a faster searching speed and lower missing scene change detection than the sequential searching method for the whole moving pictures, yet employed searching algorithm and detection interval greatly affect missing frame and searching precision. In this study, the whole moving pictures were primarily retrieved threshold by the temporal difference of histogram scene change detection method. We suggested a dynamic threshold algorithm using cut detection interval and derived an equation formula to determine optimal primary retrieval threshold which can cut detection interval computation. Experimental results show that the proposed dynamic threshold algorithm using cut detection interval method works up about 30 percent in precision of performance than the sequential searching method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.4A
• /
• pp.356-363
• /
• 2002

Video scene segmentation is fundamental role for content based video analysis and many kinds of scene segmentation schemes have been proposed in previous researches. However, there is a problem, which is to find optimal threshold value according to various kinds of movies and its content because only fixed single threshold value usually used for cut detection. In this paper, we proposed the variable dynamic threshold method, which change the threshold value by a probability distribution of cut detection interval and information of frame feature differences and cut detection interval in previous cut detection is used to determine the next cut detection. For this, we present a cut detection algorithm and a parameter generation method to change the threshold value in runtime. We also show the proposed method, which can minimize fault alarm rate than the existing methods efficiently by experimental results.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1148-1155
• /
• 2020

Fire must be extinguished as quickly as possible because they cause a lot of economic loss and take away precious human lives. Especially, the detection of smoke, which tends to be found first in fire, is of great importance. Smoke detection based on image has many difficulties in algorithm research due to the irregular shape of smoke. In this study, we introduce a new real-time smoke detection algorithm that reduces the detection of false positives generated by irregular smoke shape based on faster r-cnn of factory-installed surveillance cameras. First, we compute the global frame similarity and mean squared error (MSE) to detect the movement of smoke from the input surveillance camera. Second, we use deep learning algorithm (Faster r-cnn) to extract deferred candidate regions. Third, the extracted candidate areas for acting are finally determined using space and temporal features as smoke area. In this study, we proposed a new algorithm using the space and temporal features of global and local frames, which are well-proposed object information, to reduce false positives based on deep learning techniques. The experimental results confirmed that the proposed algorithm has excellent performance by reducing false positives of about 99.0% while maintaining smoke detection performance.