• International Journal of Internet, Broadcasting and Communication
• /
• 제10권4호
• /
• pp.50-64
• /
• 2018

This paper describes a visual object detection approach utilizing ensemble based machine learning. Object detection methods employing 1D features have the benefit of fast calculation speed. However, for real image with complex background, detection accuracy and performance are degraded. In this paper, we propose an ensemble learning algorithm that combines a 1D feature classifier and 2D DNF (Disjunctive Normal Form) classifier to improve the object detection performance in a single input image. Also, to improve the computing efficiency and accuracy, we propose a feature selecting method to reduce the computing time and ensemble algorithm by combining the 1D features and 2D DNF features. In the verification experiments, we selected the Haar-like feature as the 1D image descriptor, and demonstrated the performance of the algorithm on a few datasets such as face and vehicle.

• 전기학회논문지P
• /
• 제67권1호
• /
• pp.42-46
• /
• 2018

In this paper, we propose fast object detection method of the cars by applying YOLOv2(You Only Look Once version 2) and UAVs (Unmanned Aerial Vehicles) while on the highway. We operated Darknet, OpenCV, CUDA and Deep Learning Server(SDX-4185) for our simulation environment. YOLOv2 is recently developed fast object detection algorithm that can detect various scale objects as fast speed. YOLOv2 convolution network algorithm allows to calculate probability by one pass evaluation and predicts location of each cars, because object detection process has simple single network. In our result, we could find cars on the highway area as fast speed and we could apply to the real time.

• 로봇학회논문지
• /
• 제14권4호
• /
• pp.357-362
• /
• 2019

This paper proposes a model and train method that can real-time detect objects and distances estimation based on a monocular camera by applying deep learning. It used YOLOv2 model which is applied to autonomous or robot due to the fast image processing speed. We have changed and learned the loss function so that the YOLOv2 model can detect objects and distances at the same time. The YOLOv2 loss function added a term for learning bounding box values x, y, w, h, and distance values z as 클래스ification losses. In addition, the learning was carried out by multiplying the distance term with parameters for the balance of learning. we trained the model location, recognition by camera and distance data measured by lidar so that we enable the model to estimate distance and objects from a monocular camera, even when the vehicle is going up or down hill. To evaluate the performance of object detection and distance estimation, MAP (Mean Average Precision) and Adjust R square were used and performance was compared with previous research papers. In addition, we compared the original YOLOv2 model FPS (Frame Per Second) for speed measurement with FPS of our model.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.304-309
• /
• 2015

On construction sites, it is important to monitor the performance of construction equipment and workers to achieve successful construction project management; especially, vision-based detection methods have advantages for the real-time site data collection for safety and productivity analyses. Although many researchers developed vision-based detection methods with acceptable performance, there are still limitations to be addressed: 1) sensitiveness to the shape and appearance changes of moving objects in difference working postures, and 2) high computation time. To deal with the limitations, this paper proposes a detection algorithm of construction equipment based on Integral Channel Features. For validation, 16,850 frames of video streams were recorded and analyzed. The results showed that the proposed method worked in high performance in terms of accuracy and processing time. In conclusion, the developed method can help to understand useful site information including working pattern, working time and input manpower analyses.

• 한국항공우주학회지
• /
• 제49권8호
• /
• pp.671-680
• /
• 2021

본 논문은 정찰용 하드웨어와 소프트웨어를 설계하고 제작하여 캔위성 플랫폼과 지상국에 탑재 후 기능을 검증한 내용을 다루고 있다. 주요 정찰 임무는 크게 2가지로 구성되는데, 레이더와 GPS, IMU 센서를 이용해 주변 지형을 3D로 렌더링하는 지형탐색과 광학 카메라 영상분석을 통한 실시간 주요 물체 검출이다. 그리고 캔위성 시스템의 완성도를 높이기 위해 GUI 소프트웨어를 통해 데이터 분석효율을 향상하였다. 구체적으로 지형정보와 물체 탐지정보를 실시간으로 지상국에서 확인할 수 있는 소프트웨어를 제작하였으며, 비정상패킷 예외처리와 시스템 초기화 기능을 통해 임무 실패를 방지하였다. 통신계는 LTE와 AWS 서버를 통한 통신을 메인 채널로 사용했고, 보조 채널로 지그비를 사용하였다. 완성된 캔위성을 로켓 발사 방식과 드론 탑재 방식으로 공중 낙하 실험하였다. 실험 결과, 지형탐색과 물체 검출 성능이 우수하였으며, 모든 결과를 실시간으로 처리 후 지상국 소프트웨어에 성공적으로 시현하였다.

• 사물인터넷융복합논문지
• /
• 제10권2호
• /
• pp.85-91
• /
• 2024

본 논문에서는 테마파크, 메가 이벤트, 전시공연에 시공간을 넘어서 디지털 캔버스로 활용하고 있는 프로젝션 매핑에 대해서 연구하였다. 기존 고정된 대상에 사용하던 프로젝션 기술은 활용도에 있어서 움직이는 대상에 맵핑 하기 힘들다는 한계점이 있기 때문에 움직이는 피사체를 추적하여 매핑할 수 있는 기술과 동적으로 움직이는 대상을 기반으로 실시간 동적 프로젝션 매핑 시스템을 개발하여 공연, 전시, 테마파크 등 다양한 시장 대응이 가능하도록 관련 연구가 시급한 실정이다. 본문에서는 실시간 사물에 해당하는 요소를 추적할 수 있는 하드웨어 개발과 초고속 영상처리를 하여 딜레이 현상이 없는 시스템을 제시하고자 한다. 구체적으로 실시간 오브제 영상분석 및 프로젝션 포커싱 제어부 개발, 실시간 오브제 추적 시스템을 위한 통합 운영 시스템, 프로젝션 매핑을 위한 영상처리 라이브러리 개발을 구현한다. 본 연구는 최근 실시간 비전머신 기반의 검출 기술을 활용한 기술 집약적인 산업임과 동시에 첨단의 과학기술이 융합되어 연출되는 산업으로 활용도가 다양할 것으로 기대된다.

• 디지털융복합연구
• /
• 제14권2호
• /
• pp.183-190
• /
• 2016

본 논문은 서베일런스 네트워크에서 이동하는 객체 추적 시 영상 데이터의 전송량을 감소시키는 신경망 계산 시간의 단축 알고리즘을 제안한다. 객체 검출은 디지털화 연속된 영상으로부터 객체 존재 유무를 판단하고, 객체가 존재할 경우 영상 내 객체의 위치, 방향, 크기 등을 알아내는 기술로 정의된다. 그러나 영상 내의 객체는 위치, 크기, 빛의 방향 및 밝기, 장애물 등의 환경적 변화로 인해 객체 모양이 다양해지므로 정확하고 빠른 검출이 어렵다. 따라서 본 논문에서는 신경망을 사용하여 몇 가지 환경적 조건을 극복한 정확하고 빠른 객체 검출 방법을 제안한다. 검색 영역의 축소는 영상 내 색상 영역의 분할과 차영상을 이용하였고, 주성분 분석을 통해 신경망의 입력 벡터를 축소시킴으로써 신경망 수행 시간과 학습 시간을 단축시켰다. 실시간으로 입력되는 동영상에서 모두 실험하였으며, 색상 영역의 분할을 사용할 경우 입력 영상의 칼라 설정의 유무에 따른 검출 성공률의 차를 보였다. 실험 결과에서 보면 제안하는 방법으로써 객체의 움직임을 탐지하였을 때 기존의 방법보다 30% 정도 더 높은 인식 성능을 보여준다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 추계학술발표대회
• /
• pp.967-970
• /
• 2020

In a previous work we have done, we presented a monitoring system to automatically detect some dogs' behaviors from videos. However, the input video data used by that system was pre-trimmed to ensure it contained a dog only. In a real-life situation, the monitoring system would continuously receive video data, including frames that are empty and ones that contain people. In this paper, we propose a YOLOv4-based system for automatic object detection and trimming of dog videos. Sequences of frames trimmed from the video data received from the camera are analyzed to detect dogs and people frame by frame using a YOLOv4 model, and then records of the occurrences of dogs and people are generated. The records of each sequence are then analyzed through a rule-based decision tree to classify the sequence, forward it if it contains a dog only or ignore it otherwise. The results of the experiments on long untrimmed videos show that our proposed method manages an excellent detection performance reaching 0.97 in average of precision, recall and f-1 score at a detection rate of approximately 30 fps, guaranteeing with that real-time processing.

• 한국멀티미디어학회논문지
• /
• 제25권3호
• /
• pp.546-557
• /
• 2022

Recently, the demand to interpret image data with artificial intelligence in various fields is rapidly increasing. Object recognition and detection techniques using deep learning are mainly used, and video integration analysis to determine unstructured object recognition is a particularly important problem. In the case of natural disasters or social disasters, there is a limit to the object recognition structure alone because it has an unstructured shape. In this paper, we propose intelligent video integration analysis system that can recognize unstructured objects based on video turning point and object detection. We also introduce a method to apply and evaluate object recognition using virtual augmented images from 2D to 3D through GAN.

• 로봇학회논문지
• /
• 제16권1호
• /
• pp.49-55
• /
• 2021

Recently, a smart farm technology is drawing attention as an alternative to the decline of farm labor population problems due to the aging society. Especially, there is an increasing demand for automatic harvesting system that can be commercialized in the market. Pre-harvest crop detection is the most important issue for the harvesting robot system in a real-world environment. In this paper, we proposed a real-time tomato instance tracking algorithm by using deep learning and probability models. In general, It is hard to keep track of the same tomato instance between successive frames, because the tomato growing environment is disturbed by the change of lighting condition and a background clutter without a stochastic approach. Therefore, this work suggests that individual tomato object detection for each frame is conducted by YOLOv3 model, and the continuous instance tracking between frames is performed by Kalman filter and probability model. We have verified the performance of the proposed method, an experiment was shown a good result in real-world test data.