• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.4
• /
• pp.641-647
• /
• 2018

Recently, CCTV, which provides video information for multiple purposes, has been transformed into an intelligent, and the range of automation applications increased using the computer vision. A highly reliable detection method must be performed for accurate recognition of pedestrians and vehicles and various methods are being studied for this purpose. In such an object detection system. In this paper, we propose a method to detect a large number of pedestrians by acquiring three characteristic information that features of color information using HSI, motion vector information and shaping information using HOG feature information of a pedestrian in a situation where a large number of pedestrians are moving. The proposed method distinguishes each pedestrian while minimizing the failure or confusion of pedestrian detection and tracking. Also when pedestrians approach or overlap, pedestrians are identified and detected using stored frame feature data.

• The KIPS Transactions:PartA
• /
• v.19A no.4
• /
• pp.175-180
• /
• 2012

This paper describes the design of high-performance pedestrian and vehicle detection circuit using the Haar-like features. The proposed circuit uses a sliding window for every image frame in order to extract Haar-like features and to detect pedestrians and vehicles. A total of 200 Haar-like features per sliding window is extracted from Haar-like feature extraction circuit and the extracted features are provided to AdaBoost classifier circuit. In order to increase the processing speed, the proposed circuit adopts the parallel architecture and it can process two sliding windows at the same time. We described the proposed high-performance pedestrian and vehicle detection circuit using Verilog HDL and synthesized the gate-level circuit using the 130nm standard cell library. The synthesized circuit consists of 1,388,260 gates and its maximum operating frequency is 203MHz. Since the proposed circuit processes about 47.8 $640{\times}480$ image frames per second, it can be used to provide the real-time detection of pedestrians and vehicles.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.10C
• /
• pp.958-966
• /
• 2003

Change detection algorithms based on frame difference are frequently used for finding moving objects in image sequences. These algorithms detect the change of frames using estimated statistical background model. But, if this estimated background model is different from the actual statistical distribution, false detections are generated. In this paper, we propose an improved change detection algorithm using euler number and structure tensor. The proposed mapping method which is based on the euler number can be used for reducing the false detections that generated by nonparametric change detection algorithm. In this paper, the change in the region of moving object also can be detected by the proposed method using structure tensor. Experimental result shows that the proposed method reduces the false detections effectively by 90% on "Weather", by 34% on "Mother & daughter" and by 43% on "Aisle" than an existing method does.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.1-10
• /
• 2015

In this paper, we propose an efficient parallel implementation method of a widely used complex four-stage fire detection algorithm using a graphics processing unit (GPU) to improve the performance of the algorithm and analyze the performance of the parallel implementation method. In addition, we use seven different resolution videos (QVGA, VGA, SVGA, XGA, SXGA+, UXGA, QXGA) as inputs of the four-stage fire detection algorithm. Moreover, we compare the performance of the GPU-based approach with that of the CPU implementation for each different resolution video. Experimental results using five different fire videos with seven different resolutions indicate that the execution time of the proposed GPU implementation outperforms that of the CPU implementation in terms of execution time and takes a 25.11ms per frame for the UXGA resolution video, satisfying real-time processing (30 frames per second, 30fps) of the fire detection algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.364-370
• /
• 2020

This paper is related to detection and classification for micro-sized aircraft that flies at low-altitude. The deep-learning based method using sounds coming from the micro-sized aircraft is proposed to detect and identify them efficiently. We use MFCC as sound features and CNN as a detector and classifier. We've proved that each micro-drones have their own distinguishable MFCC feature and confirmed that we can apply CNN as a detector and classifier even though drone sound has time-related sequence. Typically many papers deal with RNN for time-related features, but we prove that if the number of frame in the MFCC features are enough to contain the time-related information, we can classify those features with CNN. With this approach, we've achieved high detection and classification ratio with low-computation power at the same time using the data set which consists of four different drone sounds. So, this paper presents the simple and effecive method of detection and classification method for micro-sized aircraft.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.853-862
• /
• 2002

Face Detection can be defined as follows : Given a digitalized arbitrary or image sequence, the goal of face detection is to determine whether or not there is any human face in the image, and if present, return its location, direction, size, and so on. This technique is based on many applications such face recognition facial expression, head gesture and so on, and is one of important qualify factors. But face in an given image is considerably difficult because facial expression, pose, facial size, light conditions and so on change the overall appearance of faces, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact face detection which overcomes some restrictions by using neural network. The proposed system can be face detection irrelevant to facial expression, background and pose rapidily. For this. face detection is performed by neural network and detection response time is shortened by reducing search region and decreasing calculation time of neural network. Reduced search region is accomplished by using skin color segment and frame difference. And neural network calculation time is decreased by reducing input vector sire of neural network. Principle Component Analysis (PCA) can reduce the dimension of data. Also, pose estimates in extracted facial image and eye region is located. This result enables to us more informations about face. The experiment measured success rate and process time using the Squared Mahalanobis distance. Both of still images and sequence images was experimented and in case of skin color segment, the result shows different success rate whether or not camera setting. Pose estimation experiments was carried out under same conditions and existence or nonexistence glasses shows different result in eye region detection. The experiment results show satisfactory detection rate and process time for real time system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.7A
• /
• pp.586-599
• /
• 2012

This paper proposes a fast face detection and tracking method which uses depth images as well as RGB images. It consists of the face detection procedure and the face tracking procedure. The face detection method basically uses an existing method, Adaboost, but it reduces the size of the search area by using the depth image. The proposed face tracking method uses a template matching technique and incorporates an early-termination scheme to reduce the execution time further. The results from implementing and experimenting the proposed methods showed that the proposed face detection method takes only about 39% of the execution time of the existing method. The proposed tracking method takes only 2.48ms per frame with $640{\times}480$ resolution. For the exactness, the proposed detection method showed a little lower in detection ratio but in the error ratio, which is for the cases when a detected one as a face is not really a face, the proposed method showed only about 38% of that of the previous method. The proposed face tracking method turned out to have a trade-off relationship between the execution time and the exactness. In all the cases except a special one, the tracking error ratio is as low as about 1%. Therefore, we expect the proposed face detection and tracking methods can be used individually or in combined for many applications that need fast execution and exact detection or tracking.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.9
• /
• pp.1825-1838
• /
• 2012

This paper proposes a fast face detection and tracking method which uses depth images as well as RGB images. It consists of the face detection procedure and the face tracking procedure. The face detection method basically uses an existing method, Adaboost, but it reduces the size of the search area by using the depth information and skin color. The proposed face tracking method uses a template matching technique and incorporates an early-termination scheme to reduce the execution time further. The results from implementing and experimenting the proposed methods showed that the proposed face detection method takes only about 39% of the execution time of the existing method. The proposed tracking method takes only 2.48ms per frame. For the exactness, the proposed detection method and previous method showed a same detection ratio but in the error ratio, which is about 0.66%, the proposed method showed considerably improved performance. In all the cases except a special one, the tracking error ratio is as low as about 1%. Therefore, we expect the proposed face detection and tracking methods can be used individually or in combined for many applications that need fast execution and exact detection or tracking.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.3
• /
• pp.38-47
• /
• 2008

A vehicle counting system at intersection is designed and implemented using analyzing a video stream from a camera. To separate foreground image from background, we compare three different methods, among which Li's method is chosen. Blobs are extracted from the foreground image using connected component analysis and the blobs are tracked by a blob tracker, frame by frame. The primary tracker use only the size and location of blob in foreground image. If there is a collision between blobs, the mean-shift tracking algorithm based on color distribution of blob is used. The proposed system is tested using real video data at intersection. If some huristics is applied, the system shows a good detection rate and a low error rate.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.678-681
• /
• 2004

In this paper, efficient tracking of a moving object using optimal representative blocks is implemented by a mobile robot with a pan-tilt camera. The key idea comes from the fact that when the image size of moving object is shrunk in an image frame according to the distance between the camera of mobile robot and the moving object, the tracking performance of a moving object can be improved by changing the size of representative blocks according to the object image size. Motion estimation using Edge Detection(ED) and Block-Matching Algorithm(BMA) is often used in the case of moving object tracking by vision sensors. However these methods often miss the real-time vision data since these schemes suffer from the heavy computational load. In this paper, the optimal representative block that can reduce a lot of data to be computed, is defined and optimized by changing the size of representative block according to the size of object in the image frame to improve the tracking performance. The proposed algorithm is verified experimentally by using a two degree-of-freedom active camera mounted on a mobile robot.