• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.10
• /
• pp.883-892
• /
• 2021

This paper provides a process for developing deep learning-based aerial object detection models that can run in realtime on onboard. To improve object detection performance, we pre-process and augment the training data in the training stage. In addition, we perform transfer learning and apply a weighted cross-entropy method to reduce the variations of detection performance for each class. To improve the inference speed, we have generated inference acceleration engines with quantization. Then, we analyze the real-time performance and detection performance on custom aerial image dataset to verify generalization.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.1
• /
• pp.19-24
• /
• 2023

In traditional fish farming way, the workers have to observe all of the pools every time and every day to feed at the right timing. This method causes tremendous stress on workers and wastes time. To solve this problem, we implemented an automatic detection system for feeding time using deep neural network. The detection system consists of two steps: classification of the presence or absence of feed and checking DO (Dissolved Oxygen) of the pool. For the classification, the pretrained ResNet18 model and transfer learning with custom dataset are used. DO is obtained from the DO sensor in the pool through HTTP in real time. For better accuracy, the next step, checking DO proceeds when the result of the classification is absence of feed several times in a row. DO is checked if it is higher than a DO reference value that is set by the workers. These actions are performed automatically in the UI programs developed with LabVIEW.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.2
• /
• pp.91-99
• /
• 2024

Collision avoidance system is important to improve the robustness and functional safety of autonomous vehicles. This paper proposes an object-level distance estimation method to develop a collision avoidance system, and it is applied to golfcarts utilized in country club environments. To improve the detection accuracy, we continually trained an object detection model based on pseudo labels generated by a pre-trained detector. Moreover, we propose object-aware depth estimation (OADE) method which trains a depth model focusing on object regions. In the OADE algorithm, we generated dense depth information for object regions by utilizing detection results and sparse LiDAR points, and it is referred to as object-aware LiDAR projection (OALP). By using the OALP maps, a depth estimation model was trained by backpropagating more gradients of the loss on object regions. Experiments were conducted on our custom dataset, which was collected for the travel distance of 22 km on 54 holes in three country clubs under various weather conditions. The precision and recall rate were respectively improved from 70.5% and 49.1% to 95.3% and 92.1% after the continual learning with pseudo labels. Moreover, the OADE algorithm reduces the absolute relative error from 4.76% to 4.27% for estimating distances to obstacles.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.146-151
• /
• 2021

Currently, the demand for vehicles from one family is increasing in many countries at home and abroad, reducing the number of people on the vehicle and increasing the number of vehicles on the road. The multi-passenger lane system, which is available to solve the problem of traffic congestion, is being implemented. The system allows police to monitor fast-moving vehicles with their own eyes to crack down on illegal vehicles, which is less accurate and accompanied by the risk of accidents. To address these problems, applying deep learning object recognition techniques using images from road sites will solve the aforementioned problems. Therefore, in this paper, we compare and analyze the performance of existing deep learning models, select a deep learning model that can identify real-time vehicle occupants through video, and propose a vehicle occupancy detection algorithm that complements the object-ident model's problems.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.3
• /
• pp.83-95
• /
• 2022

This paper proposes a system that performs object detection and distance estimation for application to autonomous vehicles. Object detection is performed by a network that adjusts the split grid to the input image ratio using the characteristics of the recently actively used deep learning model YOLOv4, and is trained to a custom dataset. The distance to the detected object is estimated using a bounding box and homography. As a result of the experiment, the proposed method improved in overall detection performance and processing speed close to real-time. Compared to the existing YOLOv4, the total mAP of the proposed method increased by 4.03%. The accuracy of object recognition such as pedestrians, vehicles, construction sites, and PE drums, which frequently occur when driving to the city center, has been improved. The processing speed is approximately 55 FPS. The average of the distance estimation error was 5.25m in the X coordinate and 0.97m in the Y coordinate.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.353-360
• /
• 2022

Due to the dense and complicated working environment, the construction industry is susceptible to many accidents. Worker's fall is a severe problem at the construction site, including falling into holes or openings because of the inadequate coverings as per the safety rules. During the construction or demolition of a building, openings and holes are formed in the floors and roofs. Many workers neglect to cover openings for ease of work while being aware of the risks of holes, openings, and gaps at heights. However, there are safety rules for worker safety; the holes and openings must be covered to prevent falls. The safety inspector typically examines it by visiting the construction site, which is time-consuming and requires safety manager efforts. Therefore, this study presented a worker-driven approach (the worker is involved in the reporting process) to facilitate safety managers by developing integrated computer vision and inertia sensors-based mobile applications to identify openings. The TensorFlow framework is used to design Convolutional Neural Network (CNN); the designed CNN is trained on a custom dataset for binary class openings and covered and deployed on an android smartphone. When an application captures an image, the device also extracts the accelerometer values to determine the inclination in parallel with the classification task of the device to predict the final output as floor (openings/ covered), wall (openings/covered), and roof (openings / covered). The proposed worker-driven approach will be extended with other case scenarios at the construction site.

• Journal of Veterinary Science
• /
• v.23 no.1
• /
• pp.17.1-17.10
• /
• 2022

Background: Inspection of livestock farms using surveillance cameras is emerging as a means of early detection of transboundary animal disease such as African swine fever (ASF). Object tracking, a developing technology derived from object detection aims to the consistent identification of individual objects in farms. Objectives: This study was conducted as a preliminary investigation for practical application to livestock farms. With the use of a high-performance artificial intelligence (AI)-based 3D depth camera, the aim is to establish a pathway for utilizing AI models to perform advanced object tracking. Methods: Multiple crossovers by two humans will be simulated to investigate the potential of object tracking. Inspection of consistent identification will be the evidence of object tracking after crossing over. Two AI models, a fast model and an accurate model, were tested and compared with regard to their object tracking performance in 3D. Finally, the recording of pig pen was also processed with aforementioned AI model to test the possibility of 3D object detection. Results: Both AI successfully processed and provided a 3D bounding box, identification number, and distance away from camera for each individual human. The accurate detection model had better evidence than the fast detection model on 3D object tracking and showed the potential application onto pigs as a livestock. Conclusions: Preparing a custom dataset to train AI models in an appropriate farm is required for proper 3D object detection to operate object tracking for pigs at an ideal level. This will allow the farm to smoothly transit traditional methods to ASF-preventing precision livestock farming.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.469-472
• /
• 2022

With the recent development of intelligent transportation systems, various technologies applying deep learning technology are being used. To crackdown on illegal vehicles and criminal vehicles driving on the road, a vehicle type classification system capable of accurately determining the type of vehicle is required. This study proposes a vehicle type classification system optimized for mobile traffic control systems using YOLO(You Only Look Once). The system uses a one-stage object detection algorithm YOLOv5 to detect vehicles into six classes: passenger cars, subcompact, compact, and midsize vans, full-size vans, trucks, motorcycles, special vehicles, and construction machinery. About 5,000 pieces of domestic vehicle image data built by the Korea Institute of Science and Technology for the development of artificial intelligence technology were used as learning data. It proposes a lane designation control system that applies a vehicle type classification algorithm capable of recognizing both front and side angles with one camera.

• Korean Journal of Remote Sensing
• /
• v.40 no.2
• /
• pp.151-166
• /
• 2024

Coastal debris presents a significant environmental threat globally. This research sought to improve the monitoring methods for coastal debris by employing deep learning and remote sensing technologies. To achieve this, an object detection approach utilizing the You Only Look Once (YOLO)v8 model was implemented to develop a comprehensive image dataset for 11 primary types of coastal debris in our country, proposing a protocol for the real-time detection and analysis of debris. Drone imagery was collected over Sinja Island, situated at the estuary of the Nakdong River, and analyzed using our custom YOLOv8-based analysis program to identify type-specific hotspots of coastal debris. The deployment of these mapping and analysis methodologies is anticipated to be effectively utilized in managing coastal debris.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.43-51
• /
• 2024

This paper proposes a method for acquiring and analyzing ocular data using a special-purpose diver mask targeted at divers who primarily engage in underwater activities. This involves tracking the user's gaze with the help of a custom-built ocular dataset and a YOLOv8-nano model developed for this purpose. The model achieved an average processing time of 45.52ms per frame and successfully recognized states of eyes being open or closed with 99% accuracy. Based on the analysis of the ocular data, a gaze tracking algorithm was developed that can map to real-world coordinates. The validation of this algorithm showed an average error rate of about 1% on the x-axis and about 6% on the y-axis.