• ETRI Journal
• /
• v.42 no.2
• /
• pp.230-238
• /
• 2020

Human-object interaction (HOI) detection is a popular computer vision task that detects interactions between humans and objects. This task can be useful in many applications that require a deeper understanding of semantic scenes. Current HOI detection networks typically consist of a feature extractor followed by detection layers comprising small filters (eg, 1 × 1 or 3 × 3). Although small filters can capture local spatial features with a few parameters, they fail to capture larger context information relevant for recognizing interactions between humans and distant objects owing to their small receptive regions. Hence, we herein propose a three-stream HOI detection network that employs a context convolution module (CCM) in each stream branch. The CCM can capture larger contexts from input feature maps by adopting combinations of large separable convolution layers and residual-based convolution layers without increasing the number of parameters by using fewer large separable filters. We evaluate our HOI detection method using two benchmark datasets, V-COCO and HICO-DET, and demonstrate its state-of-the-art performance.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.13 no.5
• /
• pp.894-902
• /
• 2010

This paper presents a vision-based robust off-road terrain classification method against environmental variation. As a supervised classification algorithm, we applied a neural network classifier using wavelet features extracted from wavelet transform of an image. In order to get over an effect of overall image feature variation, we adopted environment sensors and gathered the training parameters database according to environmental conditions. The robust terrain classification algorithm against environmental variation was implemented by choosing an optimal parameter using environmental information. The proposed algorithm was embedded on a processor board under the VxWorks real-time operating system. The processor board is containing four 1GHz 7448 PowerPC CPUs. In order to implement an optimal software architecture on which a distributed parallel processing is possible, we measured and analyzed the data delivery time between the CPUs. And the performance of the present algorithm was verified, comparing classification results using the real off-road images acquired under various environmental conditions in conformity with applied classifiers and features. Experiments show the robustness of the classification results on any environmental condition.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.30 no.3
• /
• pp.184-189
• /
• 2016

Human appearance analysis is an important part of both eastern and western medicine fields, such as Sasang constitutional medicine, rehabilitation medicine, dental medicine, and etc. By the rapid growing of depth camera technology, 3D measuring becomes popular in many applications including medical area. In this study, the possibility of using depth cameras in asymmetry analysis of human appearance is examined. We introduce the development of 3D measurement system using 2 Microsoft Kinect depth cameras and fully automated asymmetry analysis algorithms based on computer vision technology. We compare the proposed automated method to the manual method, which is usually used in asymmetry analysis. As a measure of repeatability, standard deviations of asymmetry indices are examined by 10 times repeated experiments. Experimental results show that the standard deviation of the automated method (1.00mm for face, 1.22mm for body) is better than that of the manual method (2.06mm for face, 3.44mm for body) for the same 3D measurement. We conclude that the automated method using depth cameras can be successfully applicable to practical asymmetry analysis and contribute to reliable human appearance analysis.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_1
• /
• pp.693-698
• /
• 2021

As technology advances, there is increasing need for research in different fields where this technology is applied. On of the most researched topic in computer vision is Human activity recognition (HAR), which has widely been implemented in various fields which include healthcare, video surveillance and education. We therefore present in this paper a human activity recognition system based on scale and rotation while employing the Kinect depth sensors to obtain the human skeleton joints. In contrast to previous approaches that use joint angles, in this paper we propose that each limb has an angle with the X, Y, Z axes which we employ as feature vectors. The use of the joint angles makes our system scale invariant. We further calculate the body relative direction in the egocentric coordinates in order to provide the rotation invariance. For the system parameters, we employ 8 limbs with their corresponding angles each having the X, Y, Z axes from the coordinate system as feature vectors. The extracted features are finally trained and tested with the Long short term memory (LSTM) Network which gives us an average accuracy of 98.3%.

• Nuclear Engineering and Technology
• /
• v.53 no.4
• /
• pp.1277-1283
• /
• 2021

It is important for operators of poly-pipelines in petroleum industry to continuously monitor characteristics of transferred fluid such as its type and amount. To achieve this aim, in this study a dual energy gamma attenuation technique in combination with artificial neural network (ANN) is proposed to simultaneously determine type and amount of four different petroleum by-products. The detection system is composed of a dual energy gamma source, including americium-241 and barium-133 radioisotopes, and one 2.54 cm × 2.54 cm sodium iodide detector for recording the transmitted photons. Two signals recorded in transmission detector, namely the counts under photo peak of Americium-241 with energy of 59.5 keV and the counts under photo peak of Barium-133 with energy of 356 keV, were applied to the ANN as the two inputs and volume percentages of petroleum by-products were assigned as the outputs.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.53-64
• /
• 2023

Early detection of endometrial carcinoma in uterus is essential for effective treatment. Endometrial carcinoma is the worst kind of endometrium cancer among the others since it is considerably more likely to affect the additional parts of the body if not detected and treated early. Non-invasive medical computer vision, also known as medical image processing, is becoming increasingly essential in the clinical diagnosis of various diseases. Such techniques provide a tool for automatic image processing, allowing for an accurate and timely assessment of the lesion. One of the most difficult aspects of developing an effective automatic categorization system is the absence of huge datasets. Using image processing and deep learning, this article presented an artificial endometrium cancer diagnosis system. The processes in this study include gathering a dermoscopy images from the database, preprocessing, segmentation using hybrid Fuzzy C-Means (FCM) and optimizing the weights using the Whale Optimization Algorithm (WOA). The characteristics of the damaged endometrium cells are retrieved using the feature extraction approach after the Magnetic Resonance pictures have been segmented. The collected characteristics are classified using a deep learning-based methodology called Long Short-Term Memory (LSTM) and Bi-directional LSTM classifiers. After using the publicly accessible data set, suggested classifiers obtain an accuracy of 97% and segmentation accuracy of 93%.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.4
• /
• pp.48-52
• /
• 2023

From the past to the present, banners are consistently used as effective advertising means. In the case of Korea, there are frequent situations in which hidden advertisements are installed. As a result, such hidden advertisement materials may damage urban aesthetics and moreover, incur unnecessary manpower consumption and waste of money. The proposed method classifies the detected banners into good banner and bad banner. The classification results are based on whether the relevant banners are installed in compliance with legal guidelines. In the process, YOLO and Open Computer Vision library are used to determine from various perspectives whether banners in CCTV images comply with the guidelines. YOLO is used to detect the banner area in CCTV images, and OpenCV is used to detect the color values in the area for color comparison. If a banner is detected in the video, the proposed method calculates the location of the banner and the distance from the designated bulletin to determine whether it was installed within the designated location, and then compares whether the color used in the banner is complied with local government guidelines.

• Journal of Ocean Engineering and Technology
• /
• v.38 no.4
• /
• pp.174-186
• /
• 2024

In coastal video monitoring, the direct linear transform (DLT) method with ground control points (GCPs) is commonly used for geo-rectification. However, current practices often overlook the impact of GCP quantity, arrangement, and the geographical characteristics of beaches. To address this, we designed scenarios at Chuam Beach to evaluate how factors such as the distance from the camera to GCPs, the number of GCPs, and the height of each point affect the DLT method. Accuracy was assessed by calculating the root mean square error of the distance errors between the actual GCP coordinates and the image coordinates for each setting. This analysis aims to propose an optimal GCP placement method. Our results show that placing GCPs within 200 m of the camera ensures high accuracy with few points, whereas positioning them at strategic heights enhances shoreline extraction. However, since only fixed cameras were used in this study, factors like varying heights, orientations, and resolutions could not be considered. Based on data from a single location, we propose an optimal method for GCP placement that takes into account distance, number, and height using the DLT method.

• Agricultural and Biosystems Engineering
• /
• v.7 no.1
• /
• pp.18-26
• /
• 2006

In-field site-specific nitrogen (N) management increases crop yield, reduces N application to minimize the risk of nitrate contamination of ground water, and thus reduces farming cost. Real-time N sensing and fertilization is required for efficient N management. An 'on-the-go' site-specific N management system was developed and evaluated for the supplemental N application to com (Zea mays L.). This real-time N sensing and fertilization system monitored and assessed N fertilization needs using a vision-based spectral sensor and controlled the appropriate variable N rate according to N deficiency level estimated from spectral signature of crop canopies. Sensor inputs included ambient illumination, camera parameters, and image histogram of three spectral regions (red, green, and near-infrared). The real-time sensor-based supplemental N treatment improved crop N status and increased yield over most plots. The largest yield increase was achieved in plots with low initial N treatment combined with supplemental variable-rate application. Yield data for plots where N was applied the latest in the season resulted in a reduced impact on supplemental N. For plots with no supplemental N application, yield increased gradually with initial N treatment, but any N application more than 101 kg/ha had minimal impact on yield.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.54-66
• /
• 2020

Nowadays, the broad availability of cameras and embedded systems makes the application of computer vision very promising as a supporting technology for intelligent transportation systems, particularly in the field of vehicle tracking. Although there are several existing trackers, the limitation of using low-cost cameras, besides the relatively low processing power in embedded systems, makes most of these trackers useless. For the tracker to work under those conditions, the video frame rate must be reduced to decrease the burden on computation. However, doing this will make the vehicle seem to move faster on the observer's side. This phenomenon is called the fast motion challenge. This paper proposes a tracker called dynamic swarm particle (DSP), which solves the challenge. The term particle refers to the particle filter, while the term swarm refers to particle swarm optimization (PSO). The fundamental concept of our method is to exploit the continuity of vehicle dynamic motions by creating dynamic models based on PSO. Based on the experiments, DSP achieves a precision of 0.896 and success rate of 0.755. These results are better than those obtained by several other benchmark trackers.