• Journal of information and communication convergence engineering
• /
• v.12 no.2
• /
• pp.128-134
• /
• 2014

In this paper, we present a graphics processing unit (GPU)-based matching technique for the purpose of fast feature matching between different images. The scale invariant feature transform algorithm developed by Lowe for various feature matching applications, such as stereo vision and object recognition, is computationally intensive. To address this problem, we propose a matching technique optimized for GPUs to perform computations in less time. We optimize GPUs for fast computation of keypoints to make our system quick and efficient. The proposed method uses a self-organizing map feature matching technique to perform efficient matching between the different images. The experiments are performed on various image sets to examine the performance of the system under varying conditions, such as image rotation, scaling, and blurring. The experimental results show that the proposed algorithm outperforms the existing feature matching methods, resulting in fast feature matching due to the optimization of the GPU.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• pp.75-78
• /
• 2022

Deep Neural Networks (DNN) has become an essential data processing architecture for the implementation of multiple computer vision tasks. Recently, DNN-based algorithms achieve much higher recognition accuracy than traditional algorithms based on shallow learning. However, training and inference DNNs require huge computational capabilities than daily usage purposes of computers. Moreover, with increased size and depth of DNNs, CPUs may be unsatisfactory since they use serial processing by default. GPUs are the solution that come up with greater speed compared to CPUs because of their Parallel Processing/Computation nature. In this paper, we analyze the inference time complexity of DNNs using well-known computer vision library, OpenCV. We measure and analyze inference time complexity for three cases, CPU, GPU-Float32, and GPU-Float16.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2020.11a
• /
• pp.55-56
• /
• 2020

The construction industry has the highest occupational fatality and injury rates related to accidents of any industry. Accordingly, safety managers closely monitor to prevent accidents in real-time by installing surveillance cameras at construction sites. However, due to human cognitive ability limitations, it is impossible to monitor many videos simultaneously, and the fatigue of the person monitoring surveillance cameras is also very high. Thus, to help safety managers monitor work and reduce the occupational accident rate, a study on object recognition in construction sites was conducted through surveillance cameras. In this study, we applied to the instance segmentation to identify the classification and location of objects and extract the size and shape of objects in construction sites. This research considers ways in which deep learning-based computer vision technology can be applied to safety management on a construction site.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.15 no.4
• /
• pp.51-59
• /
• 2016

Measurements of the automobile manufacturers are available anywhere and anytime, directly based on the criterion of failure is measured. The maintenance of high-precision production activities is direct evidence of the fact that competitive manufacturing activities are very important in determining the success of companies to recall defective starting from raw material costs. The current manufacturing sites produce calipers and clearance gauge the degree of tool only specific. Therefore, judging the quality, including the number of errors, requires a lot of attention to the dimension failures in day-to-day measurements and measurement tasks and duties repeated in difficult situations. In this paper, we aim to develop a vehicle manufacturing plant site using each of the manufacturing processes while operating a measurement tool. We display it using the Image Processing PC-based S/W with all those visual facts by management and recorded as image information a more accurate and current situation to obtain information and share visual measurements. We carry out research on the design and development vision inspection algorithm applied for pattern-recognition techniques that can help manufacturing site quality control.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.43-45
• /
• 2012

This paper is based on embedding the biometrics techniques on GPU for better computational efficiency and fast matching process using the parallel nature of the GPU processors to compare thousands of images for fingerprint recognition in a fraction of a second. In this paper we worked on GPU (INVIDIA GeForce GTX 260 with compute capability 1.3 and dual core-2-dou processor) for fingerprint matching and found that the efficiency is better than the results with related work already done on CMOS, CPU, ARM9, MATLAB Neural Networks etc which shows the better performance of our system in terms of computational time. The features matching process proposed for fingerprint recognition and the verification procedure is done on 5,000 images which are available online in the databases FVC2000, 2002, 2004 [1].

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.78-80
• /
• 2005

The pattern recognition of automobile and parking line for the automatic car parking system was processed based on statistical method for reducing the processing time. The command of driving for parking at the vacant parking lot was transmitted from processor to motor driven actuator using direct sequence spread spectrum communication, which enables the multiple transmission in CAN(controller area network). The test-bed which has CCD camera, processor, radio transceiver and FPGA was implemented and demonstrated to be operated well.

• The Journal of Korea Robotics Society
• /
• v.6 no.2
• /
• pp.182-188
• /
• 2011

This paper describes a method of road tracking by using a vision and laser with extracting road boundary (road lane and curb) for navigation of intelligent transport robot in structured road environments. Road boundary information plays a major role in developing such intelligent robot. For global navigation, we use a global positioning system achieved by means of a global planner and local navigation accomplished with recognizing road lane and curb which is road boundary on the road and estimating the location of lane and curb from the current robot with EKF(Extended Kalman Filter) algorithm in the road assumed that it has prior information. The complete system has been tested on the electronic vehicles which is equipped with cameras, lasers, GPS. Experimental results are presented to demonstrate the effectiveness of the combined laser and vision system by our approach for detecting the curb of road and lane boundary detection.

• Journal of Drive and Control
• /
• v.19 no.3
• /
• pp.16-22
• /
• 2022

Crushers are equipment that crush natural stones, to produce aggregates used at construction sites. As the crusher proceeds, the inner liner becomes worn, causing the size of the aggregate produced to gradually increase. The vision sensor-based aggregate analysis system analyzes the size and distribution of aggregates in production, in real time through image analysis. This study developed an algorithm that can segmentate aggregates in images in real time. using image preprocessing technology combining various filters and morphology techniques, and aggregate region characteristics such as convex hull and concave hull. We applied the developed algorithm to fine aggregate, intermediate aggregate, and thick aggregate images to verify their performance.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.795-800
• /
• 2016

In image classification, recent CNNs compete with human performance. However, there are limitations in more general recognition. Herein we deal with indoor images that contain too much information to be directly processed and require information reduction before recognition. To reduce the amount of data processing, typically variational inference or variational Bayesian methods are suggested for object detection. However, these methods suffer from the difficulty of marginalizing over the given space. In this study, we propose an image-text integrated recognition system using active vision based on Spatial Transformer Networks. The system attempts to efficiently sample a partial region of a given image for a given language information. Our experimental results demonstrate a significant improvement over traditional approaches. We also discuss the results of qualitative analysis of sampled images, model characteristics, and its limitations.

• Smart Media Journal
• /
• v.1 no.2
• /
• pp.40-46
• /
• 2012

In this paper, we describe interactive contents which is used the result of the inputted interface recognizing vision-based body gesture. Because the content uses the imp which is the common culture as the subject in Asia, we can enjoy it with culture familiarity. And also since the player can use their own gesture to fight with the imp in the game, they are naturally absorbed in the game. And the users can choose the multiple endings of the contents in the end of the scenario. In the part of the gesture recognition, KINECT is used to obtain the three-dimensional coordinates of each joint of the limb to capture the static pose of the actions. The vision-based 3D human pose recognition technology is used to method for convey human gesture in HCI(Human-Computer Interaction). 2D pose model based recognition method recognizes simple 2D human pose in particular environment On the other hand, 3D pose model which describes 3D human body skeletal structure can recognize more complex 3D pose than 2D pose model in because it can use joint angle and shape information of body part Because gestures can be presented through sequential static poses, we recognize the gestures which are configured poses by using HMM In this paper, we describe the interactive content which is used as input interface by using gesture recognition result. So, we can control the contents using only user's gestures naturally. And we intended to improve the immersion and the interest by using the imp who is used real-time interaction with user.