• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.232-237
• /
• 2020

In this paper, we propose an efficient sensor fusion method for autonomous vehicle recognition and distance measurement. Typical sensors used in autonomous vehicles are radar, lidar and camera. Among these, the lidar sensor is used to create a map around the vehicle. This has the disadvantage, however, of poor performance in weather conditions and the high cost of the sensor. In this paper, to compensate for these shortcomings, the distance is measured with a radar sensor that is relatively inexpensive and free of snow, rain and fog. The camera sensor with excellent object recognition rate is fused to measure object distance. The converged video is transmitted to a smartphone in real time through an IP server and can be used for an autonomous driving assistance system that determines the current vehicle situation from inside and outside.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.195-198
• /
• 2013

Recognition and Tracking of interesting object is the significant field in Computer Vision. Mean-Shift algorithm have chronic problems that some errors are occurred when histogram of tracking area is similar to another area. in this paper, we propose to solve the problem. Each algorithm blocks skin color filtering, face detect and Mean-Shift started consecutive order assists better operation of the next algorithm. Avoid to operations of the overhead of tracking area similar to a histogram distribution areas overlap only consider the number of white pixels by running the Viola-Jones algorithm, simple arithmetic increases the convergence of the Mean-Shift. The experimental results, it comes to 78% or more of white pixels in the Mean-Shift search area, only if the recognition of the face area when it is configured to perform a Viola-Jones algorithm is tracking the object, was 100 percent successful.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.393-394
• /
• 2018

In this paper, the new system which improve the previously reported "Implementation to human-computer interface system with motion tracking using OpenCV and FPGA" is introduced and in this system, a character selection system for the physically uncomfortable patients is proposed. Using OpenCV, the eye area is detected, the pupil position is determined, and then the results are sent to the FPGA, and the character is selected finally. The method to minimize the pupil movement of the patient is used to output the character according to the user's intention. Using OpenCV, various computer vision algorithms can be easily applied, and using programmable FPGA, a pupil motion recognition and character selection system are implemented with a low cost.

• Journal of the Ergonomics Society of Korea
• /
• v.30 no.1
• /
• pp.229-235
• /
• 2011

Objective: Making a new ergonomic interface system based on camera vision system, which helps the handicapped in home environment. Background: Enabling the handicapped to manipulate the consumer electronics by the proposed interface system. Method: A wearable device for capturing the eye image using a near-infrared(NIR) camera and illuminators is proposed for tracking eye gaze position(Heo et al., 2011). A frontal viewing camera is attached to the wearable device, which can recognize the consumer electronics to be controlled(Heo et al., 2011). And the amount of user's eye fatigue can be measured based on eye blink rate, and in case that the user's fatigue exceeds in the predetermined level, the proposed system can automatically change the mode of gaze based interface into that of manual selection. Results: The experimental results showed that the gaze estimation error of the proposed method was 1.98 degrees with the successful recognition of the object by the frontal viewing camera(Heo et al., 2011). Conclusion: We made a new ergonomic interface system based on gaze tracking and object recognition Application: The proposed system can be used for helping the handicapped in home environment.

• KIISE Transactions on Computing Practices
• /
• v.21 no.8
• /
• pp.549-554
• /
• 2015

As intuitive hardware interfaces continue to be developed, it has become more important to recognize the posture of the user. An efficient alternative to adding expensive sensors is to implement computer vision systems. This paper proposes a method to recognize a user's postured in a live broadcast bi-directional participatory TV program. The proposed method first estimates the position of the user's hands by generation a facial color map for the user and a motion map. The posture is then recognized by computing the relative position of the face and the hands. This method exhibited 90% accuracy in an experiment to recognize three defined postures during the live broadcast bi-directional participatory TV program, even when the input images contained a complex background.

• Journal of the Korean Institute of Gas
• /
• v.25 no.5
• /
• pp.88-96
• /
• 2021

Advanced Internet of Things (IoT) technology is being used in various ways for the safety of the energy industry. At the center of safety measures, drones play various roles on behalf of humans. Drones are playing a role in reaching places that are difficult to reach due to large-scale facilities and space restrictions that are difficult for humans to inspect. In this study, the accuracy and completeness of movement of dangerous facilities were tested using drone images, and it was confirmed that the movement recognition accuracy was 100%, the average data analysis accuracy was 95.8699%, and the average completeness was 100%. Based on the experimental results, a future-oriented facility risk analysis system combined with ICT technology was implemented and presented. Additional experiments with diversified conditions are required in the future, and ICT convergence analysis system implementation is required.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.525-531
• /
• 2019

Efforts to utilize human gestures to effectively implement a more natural and interactive interface between humans and computers have been ongoing in recent years. In this paper, we propose a new algorithm that accepts consecutive three-dimensional (3D) depth images, defines a hand model, and robustly extracts the human hand region based on six palm joints and 15 finger joints. Then, the 3D depth images are adaptively binarized to exclude non-interest areas, such as the background, and accurately extracts only the hand of the person, which is the area of interest. Experimental results show that the presented algorithm detects only the human hand region 2.4% more accurately than the existing method. The hand region extraction algorithm proposed in this paper is expected to be useful in various practical applications related to computer vision and image processing, such as gesture recognition, virtual reality implementation, 3D motion games, and sign recognition.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.2
• /
• pp.35-41
• /
• 2021

In this study, improved path tracking control algorithm based on pure pursuit algorithm is newly proposed by using improved lane detection algorithm through real time post-processing with interpolation methodology. Since the original pure pursuit works well only at speeds below 20 km/h, the look-ahead distance is implemented as a sigmoid function to work well at an average speed of 45 km/h to improve tracking performance. In addition, a smoothing filter was added to reduce the steering angle vibration of the original algorithm, and the stability of the steering angle was improved. The post-processing algorithm presented has implemented more robust lane recognition system using real-time pre/post processing method with deep learning and estimated interpolation. Real time processing is more cost-effective than the method using lots of computing resources and building abundant datasets for improving the performance of deep learning networks. Therefore, this paper also presents improved lane detection performance by using the final results with naive computer vision codes and pre/post processing. Firstly, the pre-processing was newly designed for real-time processing and robust recognition performance of augmentation. Secondly, the post-processing was designed to detect lanes by receiving the segmentation results based on the estimated interpolation in consideration of the properties of the continuous lanes. Consequently, experimental results by utilizing driving guidance line information from processing parts show that the improved lane detection algorithm is effective to minimize the lateral offset error in the diverse maneuvering roads.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.637-644
• /
• 2021

In general, in the fields of computer vision, robotics, and augmented reality, the importance of 3D space and 3D object detection and recognition technology has emerged. In particular, since it is possible to acquire RGB images and depth images in real time through an image sensor using Microsoft Kinect method, many changes have been made to object detection, tracking and recognition studies. In this paper, we propose a method to improve the quality of 3D reconstructed images by processing images acquired through a depth-based (RGB-Depth) camera on a multi-view camera system. In this paper, a method of removing noise outside an object by applying a mask acquired from a color image and a method of applying a combined filtering operation to obtain the difference in depth information between pixels inside the object is proposed. Through each experiment result, it was confirmed that the proposed method can effectively remove noise and improve the quality of 3D reconstructed image.

• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.1-9
• /
• 2021

Deep learning in computer vision has made accelerated improvement over a short period but large-scale learning data and computing power are still essential that required time-consuming trial and error tasks are involved to derive an optimal network model. In this study, we propose a similar image classification performance improvement method based on CR (Confusion Rate) that considers only the characteristics of the data itself regardless of network optimization or data reinforcement. The proposed method is a technique that improves the performance of the deep learning model by calculating the CRs for images in a dataset with similar characteristics and reflecting it in the weight of the Loss Function. Also, the CR-based recognition method is advantageous for image identification with high similarity because it enables image recognition in consideration of similarity between classes. As a result of applying the proposed method to the Resnet18 model, it showed a performance improvement of 0.22% in HanDB and 3.38% in Animal-10N. The proposed method is expected to be the basis for artificial intelligence research using noisy labeled data accompanying large-scale learning data.