• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1396-1406
• /
• 2018

Lane detection is a key function in developing autonomous vehicle technology. In this paper, we propose a lane marker detection algorithm robust to environmental variation targeting low cost embedded computing devices. The proposed algorithm consists of two phases: initialization phase which is slow but has relatively higher accuracy; and the tracking phase which is fast and has the reliable performance in a limited condition. The initialization phase detects lane markers using a set of filters utilizing the various features of lane markers. The tracking phase uses Kalman filter to accelerate the lane marker detection processing. In a tracking phase, we measure the reliability of the detection results and switch it to initialization phase if the confidence level becomes below a threshold. By combining the initialization and tracking phases we achieved high accuracy and acceptable computing speed even under a low cost computing resources in which we cannot use the computing intensive algorithm such as deep learning approach. Experimental results show that the detection accuracy is about 95% on average and the processing speed is about 20 frames per second with Raspberry Pi 3 which is low cost device.

• Journal of Information Processing Systems
• /
• v.12 no.2
• /
• pp.183-195
• /
• 2016

This paper presents a complete method for vehicle detection and tracking in a fixed setting based on computer vision. Vehicle detection is performed based on Scale Invariant Feature Transform (SIFT) feature matching. With SIFT feature detection and matching, the geometrical relations between the two images is estimated. Then, the previous image is aligned with the current image so that moving vehicles can be detected by analyzing the difference image of the two aligned images. Vehicle tracking is also performed based on SIFT feature matching. For the decreasing of time consumption and maintaining higher tracking accuracy, the detected candidate vehicle in the current image is matched with the vehicle sample in the tracking sample set, which contains all of the detected vehicles in previous images. Most remarkably, the management of vehicle entries and exits is realized based on SIFT feature matching with an efficient update mechanism of the tracking sample set. This entire method is proposed for highway traffic environment where there are no non-automotive vehicles or pedestrians, as these would interfere with the results.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.421-429
• /
• 2015

This paper is about an approach for pedestrian detection and tracking with infrared imagery. We used the CUDA(Computer Unified Device Architecture) that is a parallel processing language in order to improve the speed of video-based pedestrian detection and tracking. The detection phase is performed by Adaboost algorithm based on Haar-like features. Adaboost classifier is trained with datasets generated from infrared images. After detecting the pedestrian with the Adaboost classifier, we proposed a particle filter tracking strategies on HSV histogram feature that exploit adaptively at the same time. The proposed approach is implemented on an NVIDIA Jetson TK1 developer board that is full-featured device ideal for software development within the Linux environment. In this paper, we presented the results of parallel processing with the NVIDIA GPU on the CUDA development environment for detection and tracking of pedestrians. We compared the object detection and tracking processing time for night-time images on both GPU and CPU. The result showed that the detection and tracking speed of the pedestrian with GPU is approximately 6 times faster than that for CPU.

• 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.

• ETRI Journal
• /
• v.33 no.3
• /
• pp.415-422
• /
• 2011

In this paper, we present a novel vision-based method of recognizing finger actions for use in electronic appliance interfaces. Human skin is first detected by color and consecutive motion information. Then, fingertips are detected by a novel scale-invariant angle detection based on a variable k-cosine. Fingertip tracking is implemented by detected region-based tracking. By analyzing the contour of the tracked fingertip, fingertip parameters, such as position, thickness, and direction, are calculated. Finger actions, such as moving, clicking, and pointing, are recognized by analyzing these fingertip parameters. Experimental results show that the proposed angle detection can correctly detect fingertips, and that the recognized actions can be used for the interface with electronic appliances.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.4
• /
• pp.353-358
• /
• 2012

Human detection is a challenging task in many fields because it is difficult to detect humans due to their variable appearance and posture. Furthermore, it is also hard to track the detected human because of their dynamic and unpredictable behavior. The evaluation speed of method is also important as well as its accuracy. In this paper, we propose unified detection and tracking method for humans using Gaussian-PSO (Gaussian Particle Swarm Optimization) with the HOG (Histograms of Oriented Gradients) features to achieve a fast and accurate performance. Keeping the robustness of HOG features on human detection, we raise the process speed in detection and tracking so that it can be used for real-time applications. These advantages are given by a simple process which needs just one linear-SVM classifier with HOG features and Gaussian-PSO procedure for the both of detection and tracking.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• The Journal of Korea Robotics Society
• /
• v.7 no.2
• /
• pp.142-149
• /
• 2012

The camera has limitations of poor visibility in underwater environment due to the limited light source and medium noise of the environment. However, its usefulness in close range has been proved in many studies, especially for navigation. Thus, in this paper, vision-based object detection and tracking techniques using artificial objects for underwater robots have been studied. We employed template matching and mean shift algorithms for the object detection and tracking methods. Also, we propose the weighted correlation coefficient of adaptive threshold -based and color-region-aided approaches to enhance the object detection performance in various illumination conditions. The color information is incorporated into the template matched area and the features of the template are used to robustly calculate correlation coefficients. And the objects are recognized using multi-template matching approach. Finally, the water basin experiments have been conducted to demonstrate the performance of the proposed techniques using an underwater robot platform yShark made by KORDI.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.418-427
• /
• 2016

A smart parking management requires to track a vehicle in a indoor parking lot and to detect the place where the vehicle is parked. An advanced parking system watches all space of the parking lot with CCTV cameras. We can use these cameras for vehicles tracking and detection. In order to cover a wide area with a camera, a fisheye lens is used. In this case the shape and size of an moving vehicle vary much with distance and angle to the camera. This makes vehicle detection and tracking difficult. In addition to the fisheye lens, the vehicle headlights also makes vehicle detection and tracking difficult. This paper describes a method of realtime vehicle detection and tracking robust to the harsh situation described above. In each image frame, we update the region of a vehicle and estimate the vehicle movement. First we approximate the shape of a car with a quadrangle and estimate the four sides of the car using multiple histograms of oriented gradient. Second we create a template by applying a distance transform to the car region and estimate the motion of the car with a template matching method.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.43-53
• /
• 2012

In the this paper, a gesture-based user interface based on object detection using predefined gesture and the tracking of the detected object is proposed. For object detection, moving objects in a frame are computed by comparing multiple previous frames and predefined gesture is used to detect the target object among those moving objects. Any object with the predefined gesture can be used to control. We also propose an object tracking algorithm, namely density based meanshift algorithm, that uses color distribution of the target objects. The proposed object tracking algorithm tracks a target object crossing the background with a similar color more accurately than existing techniques. Experimental results show that the proposed object detection and tracking algorithms achieve higher detection capability with less computational complexity.