• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.45-54
• /
• 2018

This paper presents a vision-based fall detection system to automatically monitor and detect people's fall accidents, particularly those of elderly people or patients. For video analysis, the system should be able to extract both spatial and temporal features so that the model captures appearance and motion information simultaneously. Our approach is based on 3-dimensional convolutional neural networks, which can learn spatiotemporal features. In addition, we adopts a thermal camera in order to handle several issues regarding usability, day and night surveillance and privacy concerns. We design a pan-tilt camera with two actuators to extend the range of view. Performance is evaluated on our thermal dataset: TCL Fall Detection Dataset. The proposed model achieves 90.2% average clip accuracy which is better than other approaches.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.13 no.4
• /
• pp.683-688
• /
• 2010

The ability to navigate autonomously in off-road terrain is the most critical technology needed for Unmanned Ground Vehicles(UGV). In this paper, we present a method for vision-based terrain cover classification using DCT features. To classify the terrain, we acquire image from a CCD sensor, then the image is divided into fixed size of blocks. And each block transformed into DCT image then extracts features which reflect frequency band characteristics. Neural network classifier is used to classify the features. The proposed method is validated and verified through many experiments and we compare it with wavelet feature based method. The results show that the proposed method is more efficiently classify the terrain-cover than wavelet feature based one.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.6
• /
• pp.810-812
• /
• 2014

In this paper, a hagwon-bus boarding danger warning system based on computer vision is proposed to protect children from an accident causing injuries or death. Three zones are defined and different algorithms are applied to detect moving objects. In zone 1, a block-based entropy value is calculated using the absolute difference image generated by the absolute differential estimation between background image and incoming video frame. In zone 2, an effective and robust motion object tracking algorithm is performed based on the particle filter. Experimental results demonstrate the efficient and effectively of the algorithm for moving object inspection in each zone.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.04a
• /
• pp.225-226
• /
• 2022

The construction industry, which has a labour-intensive and conservative nature, is exclusive to adopt new technologies. However, the construction industry is viably introducing the 4th Industrial Revolution technologies represented by artificial intelligence, Internet of Things, robotics and unmanned transportation to promote change into a smart industry. An image-based artificial intelligence technology is a field of computer vision technology that refers to machines mimicking human visual recognition of objects from pictures or videos. The purpose of this article is to explore image-based artificial intelligence technologies which would be able to apply to the construction sites. In this study, we show two examples which is one for a construction waste classification model and another for cast in-situ anchor bolts defection detection model. Image-based intelligence technologies would be used for various measurement, classification, and detection works that occur in the construction projects.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.7
• /
• pp.976-980
• /
• 2018

The traction power system is configured to transmit electricity to the vehicles through mechanical contact between the OCL (Overhead Contact Line) and the pantograph. The system measures the current collection performance of the OCL, or the OCL installation condition is examined through maintenance for commercial operation. Maintenance continues to check the conditions through visual inspection by walking and inspection vehicles. The current collection performance is divided into the percentage of arcing(%), the contact force, and the uplift. The percentage of arcing is composed of a vision based system and used to verify the performance of a new OCL. However, it is not always possible to measure the current collection performance during commercial operation, and maintenance based on human resources can not be replaced. This paper presents the minimum performance condition of video devices in the current collection system of commercial vehicles. In addition, a continuous arcing was measured, and current collection performance was examined on the traction power system at the 250 km/h. It was analyzed with a minimum duration of arc of 1 ms. The frame rate is then shown by comparing the number of frames in the image at the time intervals of the number of the arcing. It is expected that the result of this study can be used for examining the minimum performance of video devices depending on their purpose.

• ETRI Journal
• /
• v.37 no.6
• /
• pp.1143-1153
• /
• 2015

In this paper, we propose an efficient architecture for a real-time image stitching engine for vision SoCs found in motor vehicles. To enlarge the obstacle-detection distance and area for safety, we adopt panoramic images from multiple telegraphic cameras. We propose a stitching method based on a fixed homography that is educed from the initial frame of a video sequence and is used to warp all input images without regeneration. Because the fixed homography is generated only once at the initial state, we can calculate it using SW to reduce HW costs. The proposed warping HW engine is based on a linear transform of the pixel positions of warped images and can reduce the computational complexity by 90% or more as compared to a conventional method. A dual-core SW/HW image stitching engine is applied to stitching input frames in parallel to improve the performance by 70% or more as compared to a single-core engine operation. In addition, a dual-core structure is used to detect a failure in state machines using rock-step logic to satisfy the ISO26262 standard. The dual-core SW/HW image stitching engine is fabricated in SoC with 254,968 gate counts using Global Foundry's 65 nm CMOS process. The single-core engine can make panoramic images from three YCbCr 4:2:0 formatted VGA images at 44 frames per second and frequency of 200 MHz without an LCD display.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.23-32
• /
• 2021

Semantic image segmentation technology in the field of computer vision is a technology that classifies an image by dividing it into pixels. This technique is also rapidly improving performance using a machine learning method, and a high possibility of utilizing information in units of pixels is drawing attention. However, this technology has been raised from the early days until recently for 'lack of detailed segmentation' problem. Since this problem was caused by increasing the size of the label map, it was expected that the label map could be improved by using the edge map of the original image with detailed edge information. Therefore, in this paper, we propose a post-processing algorithm that maintains semantic image segmentation based on learning, but modifies the resulting label map based on the edge map of the original image. After applying the algorithm to the existing method, when comparing similar applications before and after, approximately 1.74% pixels and 1.35% IoU (Intersection of Union) were applied, and when analyzing the results, the precise targeting fine segmentation function was improved.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.13 no.3
• /
• pp.24-29
• /
• 2004

The grinding process plays a key role which decides the quality of a product finally. But the grinding process is very irregular, so it is very difficult to analyse the process accurately. Therefore it is very important in the aspect of precision and automation to reduce the idle time and to decide the proper dressing time by watching. In this study, we choose the method which can be observed directly by using of computer vision and then apply pattern classification technique to the method of measuring the wheel surface. Pattern classification technique is proper to analyse complicated surface image. We observe the change of the wheel surface by using of the gray level run lengths which are representative in this technique.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.2
• /
• pp.37-43
• /
• 2007

In this paper, laser vision sensor is used to detect some defects any $co_{2}$ welded specimen in hardware. But, as the best expression of defects of welded specimen, the concept of segment splitting method and mean distance are introduced in software. The developed GUI software is used for deriding whether any welded specimen makes as proper shape or detects in real time. The criteria are based upon ISO 5817 as limits of imperfections in metallic fusion welds.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.10
• /
• pp.28-34
• /
• 1997

This paper describes an automatic measurement method for the in-line inspection of assembly tolerances of cathod ray electron guns. The method uses an optical microscope with a CCD camera as a probe. An automatic gap recognition algorthm with digital image processing and a new software autofocus algorithm based on using an optimal edge detector have been developed to improve the measuring accuracy. An inspection system has been proposed and practically implemented for in-line inspection to a real factory automation line. The inspection system consists of a gap inspection part and an eyelet. Total time consumed for inspecting all measuring items is about 10 seconds and the repeatability is below .+-. 5 .mu. m