• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.41-51
• /
• 2024

In this paper, we explore the enhancement of target detection accuracy in the guided weapon using deep learning object detection on infrared (IR) images. Due to the characteristics of IR images being influenced by factors such as time and temperature, it's crucial to ensure a consistent representation of object features in various environments when training the model. A simple way to address this is by emphasizing the features of target objects and reducing noise within the infrared images through appropriate pre-processing techniques. However, in previous studies, there has not been sufficient discussion on pre-processing methods in learning deep learning models based on infrared images. In this paper, we aim to investigate the impact of image pre-processing techniques on infrared image-based training for object detection. To achieve this, we analyze the pre-processing results on infrared images that utilized global or local information from the video and the image. In addition, in order to confirm the impact of images converted by each pre-processing technique on object detector training, we learn the YOLOX target detector for images processed by various pre-processing methods and analyze them. In particular, the results of the experiments using the CLAHE (Contrast Limited Adaptive Histogram Equalization) shows the highest detection accuracy with a mean average precision (mAP) of 81.9%.

• Wind and Structures
• /
• v.21 no.6
• /
• pp.709-726
• /
• 2015

In this study, a novel vision-based bolt-loosening monitoring technique is proposed for bolted joints connecting tubular steel segments of the wind turbine tower (WTT) structure. Firstly, a bolt-loosening detection algorithm based on image processing techniques is developed. The algorithm consists of five steps: image acquisition, segmentation of each nut, line detection of each nut, nut angle estimation, and bolt-loosening detection. Secondly, experimental tests are conducted on a lab-scale bolted joint model under various bolt-loosening scenarios. The bolted joint model, which is consisted of a ring flange and 32 sets of bolt and nut, is used for simulating the real bolted joint connecting steel tower segments in the WTT. Finally, the feasibility of the proposed vision-based technique is evaluated by bolt-loosening monitoring in the lab-scale bolted joint model.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.5
• /
• pp.14-23
• /
• 2007

Welding fabrication invariantly involves three district sequential steps: preparation, actual process execution and post-weld inspection. One of the major problems in automating these steps and developing autonomous welding system is the lack of proper sensing strategies. Conventionally, machine vision is used in robotic arc welding only for the correction of pre-taught welding paths in single pass. However, in this paper, multipass tracking more than single pass tracking is performed by conventional seam tracking algorithm and developed one. And tracking performances of two algorithm are compared in multipass tracking. As the result, tracking performance in multi-pass welding shows superior conventional seam tracking algorithm to developed one.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.557-560
• /
• 2023

In this paper, we introduce a pre-training method leveraging the capabilities of the Vision Transformer (ViT) for disease diagnosis in conventional Fundus images. Recognizing the need for effective representation learning in medical images, our method combines the Vision Transformer with a Masked Autoencoder to generate meaningful and pertinent image augmentations. During pre-training, the Masked Autoencoder produces an altered version of the original image, which serves as a positive pair. The Vision Transformer then employs contrastive learning techniques with this image pair to refine its weight parameters. Our experiments demonstrate that this dual-model approach harnesses the strengths of both the ViT and the Masked Autoencoder, resulting in robust and clinically relevant feature embeddings. Preliminary results suggest significant improvements in diagnostic accuracy, underscoring the potential of our methodology in enhancing automated disease diagnosis in fundus imaging.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.231-234
• /
• 2003

This paper describes the structure, operation, image processing, and decision making techniques of a color machine vision system designed for the automatic sorting of soybeans. The system consists of feeder, conveyor belt, line-scan camera, lights. ejector, and a PC Unlike manufactured goods, agricultural products including soybeans have quite uneven features. The criteria for sorting good and bad beans also vary depending on inspectors. We tackle these problem by letting the system learn the inspecting parameters from good samples selected manually by a machine user before running the system for sorting. Real-time processing has another importance In the design. Four parallel DSPs are employed to increase the processing speed. When the designed system was tested with real soybeans and the result was successful.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2531-2533
• /
• 2005

The proposed neural network technique is the real time computation method based theory of inter-node diffusion for searching the safety distances from the sudden appearance-objects during the work driving. The main steps of the distance computation using the theory of stereo vision like the eyes of man is following steps. One is the processing for finding the corresponding points of stereo images and the other is the interpolation processing of full image data from nonlinear image data of objects. All of therm request much memory space and time. Therefore the most reliable neural-network algorithm is drived for real-time matching of obejects, which is composed of a dynamic programming algorithm based on sequence matching techniques in moving objects.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.6
• /
• pp.492-499
• /
• 2000

In this paper, realization techniques of the parallel processing and the parallel network system for image processing are described. The parallel image processing system is constructed by the characterization of image processing and processor. Several problems are solved to achieve effective parallel processing and processor networking with the particular properties of image processing, which are reduction of communication quantity, equalization of load and delay depreciation on communication. A parallel image input device is developed for the flexible networking of parallel image processing. An abnormal region detection algorithm which is the basic function in machine vision is applied to evaluate the constructed parallel image processing system. The performance and effectiveness of the system are confirmed by experiments.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2006.06a
• /
• pp.34-39
• /
• 2006

An automated surface-strain measurement system, named ASIAS, was developed by using the image processing and stereo vision techniques in the previous studies by the corresponding author and his coworkers. This system has been upgraded mainly to improve the accuracy through image enhancement, sub-pixel measurement, surface smoothing, etc., since the first version was released. The present study has still more improved the convenience of users as well as the accuracy of measurement by processing high resolution images 8 mega pixels or more which can be easily obtained from a portable digital steal camera. It is proved that high resolution image processing greatly decreases the measurement error and gives strain data without considerable deterioration of accuracy even when the deformed grids to be measured and the master grids for camera calibration are captured together in the same image, making the whole process of strain measurement much simpler.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.4948-4967
• /
• 2017

On mobile devices, image sequences are widely used for multimedia applications such as computer vision, video enhancement, and augmented reality. However, the real-time processing of mobile devices is still a challenge because of constraints and demands for higher resolution images. Recently, heterogeneous computing methods that utilize both a central processing unit (CPU) and a graphics processing unit (GPU) have been researched to accelerate the image sequence processing. This paper deals with various optimizing techniques such as parallel processing by the CPU and GPU, distributed processing on the CPU, frame buffer object, and double buffering for parallel and/or distributed tasks. Using the optimizing techniques both individually and combined, several heterogeneous computing structures were implemented and their effectiveness were analyzed. The experimental results show that the heterogeneous computing facilitates executions up to 3.5 times faster than CPU-only processing.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.154-154
• /
• 2017

Root is an important organ of plant that typically lies below the surface of the soil. Root surface determines the ability of plants to absorb nutrient and water from the surrounding soil. This study describes an application of image processing and computer vision which was implemented for rapid measurement of seed germination such as root length, surface area, average diameter, branching points of roots. A CCD camera was used to obtain RGB image of seed germination which have been planted by wet paper in a humidity chamber. Temperature was controlled at approximately 250C and 90% relative humidity. Pre-processing techniques such as color space, binarized image by customized threshold, removal noise, dilation, skeleton method were applied to the obtained images for root segmentation. The various morphological parameters of roots were estimated from a root skeleton image with the accuracy of 95% and the speed of within 10 seconds. These results demonstrated the high potential of computer vision technique for the measurement of seed germination.