Robotic arms have been widely utilized in various labor-intensive industries such as manufacturing, agriculture, and food services, contributing to increasing productivity. In the development of industrial robotic arms, camera sensors have many advantages due to their cost-effectiveness and small sizes. However, estimating object positions is a challenging problem, and it critically affects to the robustness of object manipulation functions. This paper proposes a method for estimating the 3D positions of objects, and it is applied to a pick-and-place task. A deep learning model is utilized to detect 2D bounding boxes in the image plane, and the pinhole camera model is employed to compute the object positions. To improve the robustness of measuring the 3D positions of objects, we analyze the effect of lens distortion and introduce a false positive filtering process. Experiments were conducted on a real-world scenario for moving medicine bottles by using a camera-based manipulator. Experimental results demonstrated that the distortion removal and false positive filtering are effective to improve the position estimation precision and the manipulation success rate.

It is widely recognized that for 3D human pose estimation (HPE), dataset acquisition is expensive and the effectiveness of augmentation techniques of conventional visual recognition tasks is limited. We address these difficulties by presenting a simple but effective method that augments input images in terms of viewpoints when training a 3D human pose estimation (HPE) model. Our intuition is that meaningful variants of the input images for HPE could be obtained by viewing a human instance in the images from an arbitrary viewpoint different from that in the original images. The core idea is to synthesize new images that have self-occlusion and thus are difficult to predict at different viewpoints even with the same pose of the original example. We incorporate this idea into the training procedure of the 3D HPE model as an augmentation stage of the input samples. We show that a strategy for augmenting the synthesized example should be carefully designed in terms of the frequency of performing the augmentation and the selection of viewpoints for synthesizing the samples. To this end, we propose a new metric to measure the prediction difficulty of input images for 3D HPE in terms of the distance between corresponding keypoints on both sides of a human body. Extensive exploration of the space of augmentation probability choices and example selection according to the proposed distance metric leads to a performance gain of up to 6.2% on Human3.6M, the well-known pose estimation dataset.

This paper proposes an artificial intelligence-based personal information area object detection optimization method in an embedded system to de-identify personal information in video data. As an object detection optimization method, first, in order to increase the detection rate for personal information areas when detecting objects, a gyro sensor is used to collect the shooting angle of the image data when acquiring the image, and the image data is converted into a horizontal image through the collected shooting angle. Based on this, each learning model was created according to changes in the size of the image resolution of the learning data and changes in the learning method of the learning engine, and the effectiveness of the optimal learning model was selected and evaluated through an experimental method. As a de-identification method, a shuffling-based masking method was used, and double-key-based encryption of the masking information was used to prevent restoration by others. In order to reuse the original image, the original image could be restored through a security key. Through this, we were able to secure security for high personal information areas and improve usability through original image restoration. The research results of this paper are expected to contribute to industrial use of data without personal information leakage and to reducing the cost of personal information protection in industrial fields using video through de-identification of personal information areas included in video data.

Recently, there has been a growing interest in integrating physical toys into video gaming within the game content business. This paper introduces a novel method that leverages low-cost camera as an alternative to using sensor attachments to meet this rising demand. We address the limitations associated with low-cost cameras and propose an optical design tailored to the specific environment of model car recognition. We overcome the inherent limitations of low-cost cameras by proposing an optical design specifically tailored for model car recognition. This approach primarily focuses on recognizing the underside of the car and addresses the challenges associated with this particular perspective. Our method employs a transfer learning model that is specifically trained for this task. We have achieved a 100% recognition rate, highlighting the importance of collecting data under various camera exposures. This paper serves as a valuable case study for incorporating low-cost cameras into vision systems.

In this paper, we propose the implementation of a drone delivery system using artificial intelligence in a situation where the use of drones is rapidly increasing and human errors are occurring. This system requires the implementation of an accurate control algorithm, assuming that last-mile delivery is delivered to the apartment veranda. To recognize the delivery location, a recognition system using the YOLO algorithm was implemented, and a delivery system was installed on the drone to measure the distance to the object and increase the delivery distance to ensure stable delivery even at long distances. As a result of the experiment, it was confirmed that the recognition system recognized the marker with a match rate of more than 60% at a distance of less than 10m while the drone hovered stably. In addition, the drone carrying a 500g package was able to withstand the torque applied as the rail lengthened, extending to 1.5m and then stably placing the package down on the veranda at the end of the rail.

In this paper, we propose an efficient method for estimating the number of people and their locations using multiple IR-UWB radar sensors. Using three IR-UWB radar sensors in the indoor space, the measured signal from the target is processed to remove the clutter using rejection methods. Then, to further remove the clutter and to determine the presence of the human, the time-frequency image representing the micro-Doppler is obtained and classified by a convolutional neural network. Finally, the system finds the number of human objects and estimates each position in a two-dimensional space. In experiments using the measured data, the system successfully estimated the location and number of individuals with a high accuracy ≈ 88.68 %.

We spend a lot of time in indoor space, and the space has a huge impact on our lives. Interior design plays a significant role to make an indoor space attractive and functional. However, it should consider a lot of complex elements such as color, pattern, and material etc. With the increasing demand for interior design, there is a growing need for technologies that analyze these design elements accurately and efficiently. To address this need, this study suggests a deep learning-based design analysis system. The proposed system consists of a semantic segmentation model that classifies spatial components and an image classification model that classifies attributes such as color, pattern, and material from the segmented components. Semantic segmentation model was trained using a dataset of 30000 personal indoor interior images collected for research, and during inference, the model separate the input image pixel into 34 categories. And experiments were conducted with various backbones in order to obtain the optimal performance of the deep learning model for the collected interior dataset. Finally, the model achieved good performance of 89.05% and 0.5768 in terms of accuracy and mean intersection over union (mIoU). In classification part convolutional neural network (CNN) model which has recorded high performance in other image recognition tasks was used. To improve the performance of the classification model we suggests an approach that how to handle data that has data imbalance and vulnerable to light intensity. Using our methods, we achieve satisfactory results in classifying interior design component attributes. In this paper, we propose indoor space design analysis system that automatically analyzes and classifies the attributes of indoor images using a deep learning-based model. This analysis system, used as a core module in the A.I interior recommendation service, can help users pursuing self-interior design to complete their designs more easily and efficiently.

In the industrial field, robots are used to increase productivity by replacing labors with dangerous, difficult, and hard tasks. However, failures of individual industrial robots in the entire production process may cause product defects or malfunctions, and may cause dangerous disasters in the case of manufacturing parts used in automobiles and aircrafts. Although requirements for early diagnosis of industrial robot failures are steadily increasing, there are many limitations in early detection. This paper introduces methods for diagnosing robot failures using sound-based data and deep learning. This paper also analyzes, compares, and evaluates the performance of failure diagnosis using various deep learning technologies. Furthermore, in order to improve the performance of the fault diagnosis system using deep learning technology, we propose a method to increase the accuracy of fault diagnosis based on an inference window. When adopting the inference window of deep learning, the accuracy of the failure diagnosis was increased up to 94%.

An indirect visual SLAM takes raw image data and exploits geometric information such as key-points and line edges. Due to various environmental changes, SLAM performance may decrease. The main problem is caused by dynamic objects especially in highly crowded environments. In this paper, we propose a robust feature-based visual SLAM, building on ORB-SLAM, via multi-channel dynamic objects estimation. An optical flow and deep learning-based object detection algorithm each estimate different types of dynamic object information. Proposed method incorporates two dynamic object information and creates multi-channel dynamic masks. In this method, information on actually moving dynamic objects and potential dynamic objects can be obtained. Finally, dynamic objects included in the masks are removed in feature extraction part. As a results, proposed method can obtain more precise camera poses. The superiority of our ORB-SLAM was verified to compared with conventional ORB-SLAM by the experiment using KITTI odometry dataset.