• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.163-169
• /
• 2021

In this paper, we implemented a deep learning-based automatic object tracking and handy motion control drone system and analyzed the performance of the proposed system. The drone system automatically detects and tracks targets by analyzing images obtained from the drone's camera using deep learning algorithms, consisting of the YOLO, the MobileNet, and the deepSORT. Such deep learning-based detection and tracking algorithms have both higher target detection accuracy and processing speed than the conventional color-based algorithm, the CAMShift. In addition, in order to facilitate the drone control by hand from the ground control station, we classified handy motions and generated flight control commands through motion recognition using the YOLO algorithm. It was confirmed that such a deep learning-based target tracking and drone handy motion control system stably track the target and can easily control the drone.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.422-424
• /
• 2021

In this paper, it leads the approach of fusing multiple RGB cameras for visual objects recognition based on deep learning with convolution neural network and 3D Light Detection and Ranging (LiDAR) to observe the environment and match into a 3D world in estimating the distance and position in a form of point cloud map. The goal of perception in multiple cameras are to extract the crucial static and dynamic objects around the autonomous vehicle, especially the blind spot which assists the AV to navigate according to the goal. Numerous cameras with object detection might tend slow-going the computer process in real-time. The computer vision convolution neural network algorithm to use for eradicating this problem use must suitable also to the capacity of the hardware. The localization of classified detected objects comes from the bases of a 3D point cloud environment. But first, the LiDAR point cloud data undergo parsing, and the used algorithm is based on the 3D Euclidean clustering method which gives an accurate on localizing the objects. We evaluated the method using our dataset that comes from VLP-16 and multiple cameras and the results show the completion of the method and multi-sensor fusion strategy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.510-513
• /
• 2016

Detecting of the object in image processing is substantial but it depends on the object itself and the environment. An object can be detected either by its shape or color. Color is an essential for pattern recognition and computer vision. It is an attractive feature because of its simplicity and its robustness to scale changes and to detect the positions of the object. Generally, color of an object depends on its characteristics of the perceiving eye and brain. Physically, objects can be said to have color because of the light leaving their surfaces. Here, we conducted experiment in the aquarium fish tank. Different color of fish robots are mimic the natural swim of fish. Unfortunately, in the underwater medium, the colors are modified by attenuation and difficult to identify the color for moving objects. We consider the fish motion as a moving object and coordinates are found at every instinct of the aquarium to detect the position of the fish robot using OpenCV color detection. In this paper, we proposed to identify the position of the fish robot by their color and use the position data to control the fish robot gathering in one point in the fish tank through serial communication using RF module. It was verified by the performance test of detecting the position of the fish robot.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.2_1
• /
• pp.217-223
• /
• 2023

With the rapid advancement of technologies, need for different research fields where this technology can be used is also increasing. One of the most researched topic in computer vision is object detection, which has widely been implemented in various fields which include healthcare, video surveillance and education. The main goal of object detection is to identify and categorize all the objects in a target environment. Specifically, methods of object detection consist of a variety of significant techniq ues, such as image processing and patterns recognition. Anomaly detection is a part of object detection, anomalies can be found various scenarios for example crowded places such as subway stations. An abnormal event can be assumed as a variation from the conventional scene. Since the abnormal event does not occur frequently, the distribution of normal and abnormal events is thoroughly imbalanced. In terms of public safety, abnormal events should be avoided and therefore immediate action need to be taken. When abnormal events occur in certain places, real time detection is required to prevent and protect the safety of the people. To solve the above problems, we propose a modified YOLOv5 object detection algorithm by implementing dilated convolutional layers which achieved 97% mAP50 compared to other five different models of YOLOv5. In addition to this, we also created a simple mobile application to avail the abnormal event detection on mobile phones.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.396-399
• /
• 2003

This paper proposes a simple digital image stabilization(DIS) algorithm for roll motion, which has not been compensated in the 2-axes mechanical stabilization system, using aero-crossing of the rotational motion vectors. The 2-axes stabilization system cannot stabilize rolled images, which causes the deteriorated performance of the object detection and recognition. In this paper, we propose the rotational motion stabilization algorithm which estimates and compensates global motion in terms of rotational center and rotational angle. Both the synthetic images with undesirable rotational disturbance and the real images from 2-axes stabilization system are used to evaluate the proposed algorithm. The results show that our proposed algorithm suppresses the undesirable rotational disturbance effectively.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.9
• /
• pp.77-83
• /
• 1997

Based on the curve segment grouping, an efficient recognition of round objects form partially occuluded round boundaries is proposed. Curve segments are extracted from an image using a criterion based on the intra-segment curvature and local contrast. During the curve segment extraction the boundaries of pratially occluding and occuluded objects are segmented to different curve segments. The extracted segments of constant intra-segment curvature are grouped to different curve segments. The extracted segments of constant intra-segment curvature are grouped nto a round boundary by the proposed grouping algorithm using inter-segment curvature which gives the relatinships among the curve segments of the same round boundary. The 1st and the 2nd order moments are used for the parameter estimation of the best fitted ellipse with round boundary, and then recognition is perfomed based on the estimated parameters. The proposed scheme processes in segment unit and is more efficient in computational complexity and memory requirements those that of the conventional scheme which processed in pixel units. Experimental results show that the proposed technique is very efficient in recognizing the round object sfrom the real images with apples and pumpkins.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.306-311
• /
• 2003

This paper presents a novel localization paradigm for mobile robots based on artificial and natural landmarks. A model-based object recognition method detects natural landmarks and conducts the global and topological localization. In addition, a metric localization method using artificial landmarks is fused to complement the deficiency of topology map and guide to action behavior. The recognition algorithm uses a modified local Zernike moments and a probabilistic voting method for the robust detection of objects in cluttered indoor environments. An artificial landmark is designed to have a three-dimensional multi-colored structure and the projection distortion of the structure encodes the distance and viewing direction of the robot. We demonstrate the feasibility of the proposed system through real world experiments using a mobile robot, KASIRI-III.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.35D no.3
• /
• pp.82-90
• /
• 1998

A hit-miss transform(HMT) using synthetic structuring elements(SE's) for optical recognition of a moving target is proposed. A moving target which was obtained from a fixed view point has objects. In proposed HMT, SE's are synthesized by using SDF(synthetic discriminant function) algorithm for efficient recognitionof various shapes of true class objects in noisy and cluttered scene. The synthetic hit SE and the synthetic miss SE are composed of SDF of hit SE's and miss SE's for each true class object. Simulation results show the proposed method can be used for the recognition of various shapes of the true class with one one HMT operation.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.11
• /
• pp.1455-1463
• /
• 1995

A new automatic tracking & recognition algorithm which decides the opening & the closing states of subject's eye and isn't affected by the subject's background is proposed. And it was tested in circumstances in which subject's background was not restricted using the developed system, ATRS(Automatic Tracking & Recognition System). The significant characteristic of the ATRS is new movement detection of object that is a body in motion with accelated velocity and it doesn't need any extra hardware except a formal CCD camera and an image grabber but it works so well and so fast. The ATRS would be particularly well suited to a way of communications of patients in a hospital, who can not communicate otherwise.

• Journal of Aerospace System Engineering
• /
• v.16 no.1
• /
• pp.49-55
• /
• 2022

The role of drones has been expanded to various fields such as agriculture, construction, and logistics. In particular, agriculture drones are emerging as an effective alternative to solve the problem of labor shortage and reduce the input cost. In this study therefore, we proposed the fruit recognition algorithm and harvesting mechanism for fruit harvesting drone system that can safely harvest fruits at high positions. In the fruit recognition algorithm, we employ "You-Only-Look-Once" which is a deep learning-based object detection algorithm and verify its feasibility by establishing a virtual simulation environment. In addition, we propose the fruit harvesting mechanism which can be operated by a single driving motor. The rotational motion of the motor is converted into a linear motion by the scotch yoke, and the opened gripper moves forward, grips a fruit and rotates it for harvesting. The feasibility of the proposed mechanism is verified by performing Multi-body dynamics analysis.