• Journal of Korea Multimedia Society
• /
• v.19 no.12
• /
• pp.1927-1935
• /
• 2016

This paper propose a framework for human body parts in RGB-D image. We conduct tasks of obtaining person area, finding candidate areas and local detection in order to detect hand, foot and head which have features of long accumulative geodesic distance. A person area is obtained with background subtraction and noise removal by using depth image which is robust to illumination change. Finding candidate areas performs construction of graph model which allows us to measure accumulative geodesic distance for the candidates. Instead of raw depth map, our approach constructs graph model with segmented regions by quadtree structure to improve searching time for the candidates. Local detection uses HOG based SVM for each parts, and head is detected for the first time. To minimize false detections for hand and foot parts, the candidates are classified with upper or lower body using the head position and properties of geodesic distance. Then, detect hand and foot with the local detectors. We evaluate our algorithm with datasets collected Kinect v2 sensor, and our approach shows good performance for head, hand and foot detection.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.611-624
• /
• 2012

'Gesture' is the most intuitive means of communication except the voice. Therefore, there are many researches for method that controls computer using gesture input to replace the keyboard or mouse. In these researches, the method of user detection and main body parts estimation is one of the very important process. in this paper, we propose user objects detection and main body parts estimation method on inaccurate depth information for pose estimation. we present user detection method using 2D and 3D depth information, so this method robust to changes in lighting and noise and 2D signal processing 1D signals, so mainly suitable for real-time and using the previous object information, so more accurate and robust. Also, we present main body parts estimation method using 2D contour information, 3D depth information, and tracking. The result of an experiment, proposed user detection method is more robust than only using 2D information method and exactly detect object on inaccurate depth information. Also, proposed main body parts estimation method overcome the disadvantage that can't detect main body parts in occlusion area only using 2D contour information and sensitive to changes in illumination or environment using color information.

• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.179-184
• /
• 2024

In the car industry, welding is a fundamental linking technique used for joining components, such as steel, molds, and automobile parts. However, accurate inspection is required to test the reliability of the welding components. In this study, we investigate the detection of weld beads using 2D image processing in an automatic recognition system. The sample image is obtained using a 2D vision camera embedded in a lighting system, from where a portion of the bead is successfully extracted after image processing. In this process, the soot removal algorithm plays an important role in accurate weld bead detection, and adopts adaptive local gamma correction and gray color coordinates. Using this automatic recognition system, geometric parameters of the weld bead, such as its length, width, angle, and defect size can also be defined. Finally, on comparing the obtained data with the industrial standards, we can determine whether the weld bead is at an acceptable level or not.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.6
• /
• pp.1857-1862
• /
• 2016

Human activity recognition using depth information is an emerging and challenging technology in computer vision due to its considerable attention by many practical applications such as smart home/office system, personal health care and 3D video games. This paper presents a novel framework of 3D human body detection, tracking and recognition from depth video sequences using spatiotemporal features and modified HMM. To detect human silhouette, raw depth data is examined to extract human silhouette by considering spatial continuity and constraints of human motion information. While, frame differentiation is used to track human movements. Features extraction mechanism consists of spatial depth shape features and temporal joints features are used to improve classification performance. Both of these features are fused together to recognize different activities using the modified hidden Markov model (M-HMM). The proposed approach is evaluated on two challenging depth video datasets. Moreover, our system has significant abilities to handle subject's body parts rotation and body parts missing which provide major contributions in human activity recognition.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.181-186
• /
• 2014

The paper proposes a new method of segmentation-based feature extraction to improve performance in pedestrian upper-body detection. General pedestrian detectors that use local features are often plagued by false positives due to the locality. Color information of multi parts of the upper body is utilized in figure-ground segmentation scheme to extract an salient, "global" shape feature capable of reducing the false positives. The performance of the multi-part color segmentation-based feature is evaluated by changing color spaces and the parameters of color histogram. The experimental result from an upper-body dataset shows that the proposed feature is effective in reducing the false positives of local feature-based detectors.

• Journal of Multimedia Information System
• /
• v.7 no.4
• /
• pp.257-262
• /
• 2020

In this paper, a method of detecting the emergency situations such as body fall is proposed by using color images. We detect body areas and key parts of a body through a pre-learned Mask R-CNN in the images captured by a camera. Then we find the centerline of the body through the joint points of both shoulders and feet. Also, we calculate an angle to the center line and then calculate the amount of change in the angle per hour. If the angle change is more than a certain value, then it is decided as a suspected fall. Also, if the suspected fall state persists for more than a certain frame, then it is determined as a fall situation. Simulation results show that the proposed method can detect body fall situation accurately.

• Journal of Veterinary Clinics
• /
• v.15 no.2
• /
• pp.450-454
• /
• 1998

These studies were performed to find out the possibility of automatic detection of the diseased animal with fever by farmers themselves. Firstly, the body temperature of 331 dairy cows was investigated according to major disease symptoms manifested. Secondly, AD 590 thermometer was used to take the teat temperature of the milking cows to determine the possibility of automatic taking of body temperature while milking. The temperatures of scapha of ear and coccygeal artery part were also taken fur the non-milking dairy cows and Korean native cowl 1. The average body temperature of dairy cows associated with respiratory diseases puerperal disease, or mastitis was higher than normal temperature denoting respectively 39.8,39.6, and $39.3{\circ}C.2.$ The teat temperaure of the milking dairy cows with fever($39.5~39.6{\circ}C$) and the cows with mastitis was respectively 1.02 and 0.56${\circ}C$ higher than that of normal cows. 3. The average teat temperature taken by AD 590 was 33.91, 34.93, and 34.50${\circ}C$ in normal milking dairy cows, cows with fever(39.5~39.6${\circ}C$), and cows with mastitis, respectively. 4. The mean temperatures at scapha and coccygeal part of non-milking dairy cows and Korean native cows were 35.62 and 36.63${\circ}C$, respectively. It was concluded that AD 590 thermometer would be usable for the farmers to automatirally detect the body temperature of dairy cows while milking and subsquently to find the diseased cow with fever and that the scapha of ear and coccygeal artery part of the cattle could be the body parts of simply detecting body temperature of non-milking cattle.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.171-177
• /
• 2021

It is difficult to accurately extract features of pedestrian because the pedestrian is photographed at a crosswalk using a camera positioned higher than the pedestrian. In addition, it is more difficult to extract features when a part of the pedestrian's body is covered by an umbrella or parasol or when the pedestrian is holding an object. Representative methods to solve this problem include Object Detection, Instance Segmentation, and Pose Estimation. Among them, this study intends to use the Pose Estimation method. In particular, we intend to increase the recognition rate of pedestrians in crosswalks by maintaining the image resolution through HigherHRNet and applying the foot estimation technique. Finally, we show the superiority of the proposed method by applying and analyzing several data sets covered by body parts to the existing method and the proposed method.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.15 no.3
• /
• pp.36-43
• /
• 2016

Carbon fiber-reinforced silicon carbide (Cf-SiC) and SiC / SiC composites have high thermal conductivity, and excellent corrosion and wear resistance, a low coefficient for thermal expansion and are lightweight. This is why they are commonly used in parts of the aerospace industry to develop an aircraft thrust deflector, jet vane, combustion chamber, elevens, body flap, and a shingle. So, understanding how this state-of-the-art Cf-SiC affects both internal and external crack detection and determining issues during the manufacturing process of composite materials, should be evaluated according to valuation techniques in the external environment. In this paper, we apply a non-contact air ultrasonic technique of non-destructive testing techniques to perform a study on internal defect detection identification and assessment of carbon-fiber reinforced silicon carbide composites to perform basic research and applied research.

• Tribology and Lubricants
• /
• v.40 no.1
• /
• pp.24-27
• /
• 2024

A monotype valve body for a dual clutch transmission has the potential to reduce costs, weight, and manufacturing time by modularizing various parts, including those of existing solenoid packs and valve bodies, into one through the application of super-precision die casting technology. However, this approach may lead to challenges such as reduced rigidity and increased interference due to modularization and compactness, impacting both product performance due to the reduced weight as well as durability and reliability. Unlike existing products, this approach requires a high-precision thin-wall block to avoid more complicated flow line formation, interference between flow lines, and leaks, as well as a strict quality requirement standard and precise inspections including detection of internal defects. To conduct precise inspections, we built an equivalent model corresponding to a driving distance of 300,000 km. Testing involved simulating actual road loads using a real vehicle and a chassis dynamometer in the FTP-75 mode (EPA Federal Test Procedure). The aim of the study was to establish a vehicle load-based part durability model for manufacturing a mono-type valve body and to develop fundamental technology for part weight reduction through preliminary design by introducing analytical weight reduction technology based on the derived results.