• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.308-317
• /
• 2022

Researches are underway to efficiently reduce the size of video data transmitted and stored in the image analysis process using deep learning-based machine vision technology. MPEG (Moving Picture Expert Group) has newly established a standardization project called VCM (Video Coding for Machine) and is conducting research on video encoding for machines rather than video encoding for humans. We are researching a multitask that performs various tasks with one image input. The proposed pipeline does not perform all object detection of each task that should precede object detection, but precedes it only once and uses the result as an input for each task. In this paper, we propose a pipeline for efficient multitasking and perform comparative experiments on compression efficiency, execution time, and result accuracy of the input image to check the efficiency. As a result of the experiment, the capacity of the input image decreased by more than 97.5%, while the accuracy of the result decreased slightly, confirming the possibility of efficient multitasking.

• Journal of Advanced Navigation Technology
• /
• v.17 no.1
• /
• pp.98-106
• /
• 2013

In this paper, we propose a moving object detection and tracking method for multi-view camera environment. Based on the similarity and characteristics of motion vectors and coding block modes extracted from compressed bitstreams, validation of moving blocks, labeling of the validated blocks, and merging of neighboring blobs are performed. To continuously track objects for temporary stop, crossing, and overlapping events, a window based object updating algorithm is proposed for single- and multi-view environments. Object detection and tracking could be performed with an acceptable level of performance without decoding of video bitstreams for normal, temporary stop, crossing, and overlapping cases. The rates of detection and tracking are over 89% and 84% in multi-view environment, respectively. The rates for multi-view environment are improved by 6% and 7% compared to those of single-view environment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.213-216
• /
• 2022

There has been an increase in video surveillance for public safety and security, which increases the video data, leading to analysis, and storage issues. Furthermore, most surveillance videos contain an empty frame of hours of video footage; thus, extracting useful information is crucial. The prominent framework used in surveillance for efficient storage and analysis is video synopsis. However, the existing video synopsis procedure is not applicable for creating an abnormal object-based synopsis. Therefore, we proposed a lightweight synopsis methodology that initially detects and extracts abnormal foreground objects and their respective backgrounds, which is stitched to construct a synopsis.

• Journal of information and communication convergence engineering
• /
• v.3 no.1
• /
• pp.56-61
• /
• 2005

In this paper, we present a video rate control scheme for storage and delivery in which the time-varying viewing interests are controlled by human gaze. To track the gaze, the pupil's movement is detected using the three-step process : detecting face region, eye region, and pupil point. To control bit rates, the quantization parameter (QP) is changed by considering the static parameters, the video object priority derived from the pupil tracking, the target PSNR, and the weighted distortion value of the coder. As results, we achieved human interfaced visual model and corresponding region-of-interest rate control system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.967-970
• /
• 2020

In a previous work we have done, we presented a monitoring system to automatically detect some dogs' behaviors from videos. However, the input video data used by that system was pre-trimmed to ensure it contained a dog only. In a real-life situation, the monitoring system would continuously receive video data, including frames that are empty and ones that contain people. In this paper, we propose a YOLOv4-based system for automatic object detection and trimming of dog videos. Sequences of frames trimmed from the video data received from the camera are analyzed to detect dogs and people frame by frame using a YOLOv4 model, and then records of the occurrences of dogs and people are generated. The records of each sequence are then analyzed through a rule-based decision tree to classify the sequence, forward it if it contains a dog only or ignore it otherwise. The results of the experiments on long untrimmed videos show that our proposed method manages an excellent detection performance reaching 0.97 in average of precision, recall and f-1 score at a detection rate of approximately 30 fps, guaranteeing with that real-time processing.

• Journal of Korea Multimedia Society
• /
• v.18 no.2
• /
• pp.138-148
• /
• 2015

Object detection methods based on background learning are widely used in video surveillance. However, when a car runs with headlights on, these methods are likely to detect the car region and the area illuminated by the headlights as one connected change region. This paper describes a method of separating the car region from the area illuminated by the headlights. First, we detect change regions with a background learning method, and extract blobs, connected components in the detected change region. If a blob is larger than the maximum object size, we extract candidate object regions from the blob by clustering the intensity histogram of the frame difference between the mean of background images and an input image. Finally, we compute the similarity between the mean of background images and the input image within each candidate region and select a candidate region with weak similarity as an object region.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.3
• /
• pp.321-329
• /
• 1999

Moving Object segmentation extracts an interested moving object on a consecutive image frames, and has been used for factory automation, autonomous navigation, video surveillance, and VOP(Video Object Plane) detection in a MPEG-4 method. This paper proposes new segmentation method using difference images are calculated with three consecutive input image frames, and used to calculate both coarse object area(AI) and it's movement area(OI). An AI is extracted by removing background using background area projection(BAP). Missing parts in the AI is recovered with help of the OI. Boundary information of the OI confines missing parts of the object and gives inital curves for active contour optimization. The optimized contours in addition to the AI make the boundaries of the moving object. Experimental results of a fast moving object on a complex background scene are included.

• Journal of Broadcast Engineering
• /
• v.25 no.7
• /
• pp.1081-1094
• /
• 2020

With the recent development of deep learning, most computer vision-related tasks are being solved with deep learning-based network technologies such as CNN and RNN. Computer vision tasks such as object detection or object segmentation use intermediate features extracted from the same backbone such as Resnet or FPN for training and inference for object detection and segmentation. In this paper, an experiment was conducted to find out the compression efficiency and the effect of encoding on task inference performance when the features extracted in the intermediate stage of CNN are encoded. The feature map that combines the features of 256 channels into one image and the original image were encoded in HEVC to compare and analyze the inference performance for object detection and segmentation. Since the intermediate feature map encodes the five levels of feature maps (P2 to P6), the image size and resolution are increased compared to the original image. However, when the degree of compression is weakened, the use of feature maps yields similar or better inference results to the inference performance of the original image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.2C
• /
• pp.147-161
• /
• 2003

Video object segmentation is one of the core technologies for content-based real-time MPEG-4 encoding system. For real-time requirement, the segmentation algorithm should be fast and accurate but almost all existing algorithms are computationally intensive and not suitable for real-time applications. The MPEG-4 VM(Verification Model) has provided basic algorithms for MPEG-4 encoding but it has many limitations in practical software development, real-time camera input system and compression efficiency. In this paper, we implemented the preprocessing system for real-time camera input and VOP extraction for content-based video coding and also implemented motion detection to achieve the 180 : 1 compression rate for real-time and high compression MPEG-4 encoding.

• Journal of Korea Multimedia Society
• /
• v.5 no.2
• /
• pp.167-175
• /
• 2002

Image Mosaicing creates a new image by composing video frames or still images that are related, and performed by arrangement, composition and redundancy analysis of images. This paper proposes a hierarchical image mosaicing system using camera and object parameters far efficient video database construction. A tree-based image mosiacing has implemented for high-speed computation time and for construction of static and dynamic image mosaic. Camera parameters are measured by using least sum of squared difference and affine model. Dynamic object detection algorithm has proposed for extracting dynamic objects. For object extraction, difference image, macro block, region splitting and 4-split detection methods are proposed and used. Also, a dynamic positioning method is used for presenting dynamic objects and a blurring method is used for creating flexible mosaic image.