• Title/Summary/Keyword: object detection system

Search Result 1,078, Processing Time 0.025 seconds

Sector Based Scanning and Adaptive Active Tracking of Multiple Objects

  • Cho, Shung-Han;Nam, Yun-Young;Hong, Sang-Jin;Cho, We-Duke
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.5 no.6
    • /
    • pp.1166-1191
    • /
    • 2011
  • This paper presents an adaptive active tracking system with sector based scanning for a single PTZ camera. Dividing sectors on an image reduces the search space to shorten selection time so that the system can cover many targets. Upon the selection of a target, the system estimates the target trajectory to predict the zooming location with a finite amount of time for camera movement. Advanced estimation techniques using probabilistic reason suffer from the unknown object dynamics and the inaccurate estimation compromises the zooming level to prevent tracking failure. The proposed system uses the simple piecewise estimation with a few frames to cope with fast moving objects and/or slow camera movements. The target is tracked in multiple steps and the zooming time for each step is determined by maximizing the zooming level within the expected variation of object velocity and detection. The number of zooming steps is adaptively determined according to target speed. In addition, the iterative estimation of a zooming location with camera movement time compensates for the target prediction error due to the difference between speeds of a target and a camera. The effectiveness of the proposed method is validated by simulations and real time experiments.

Realization for Moving Object Sensing and Path Tracking System using Stereo Line CCDs (스테레오 라인 CCD를 이용한 이동객체감지 및 경로추적 시스템 구현)

  • Ryu, Kwang-Ryol;Kim, Young-Bin
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.12 no.11
    • /
    • pp.2050-2056
    • /
    • 2008
  • A realization for moving object sensing and tracking system in two dimensional plane using stereo line CCDs and lighting source is presented in this paper. The system is realized that instead of processing camera images directly, two line CCD sensor and input line image is used to measure two dimensional distance by comparing the brightness on line CCDs. The algorithms are used the moving object sensing, path tracking and coordinate converting method. To ensure the effective detection of moving path, a detection algorithm to evaluate the reliability of each measured distance is developed. The realized system results are that the performance of moving object recognizing shows 5mm resolution, and enables to track a moving path of object per looms period.

A study of object analysis in safety management zone (안전관리 지역 내의 객체 분석 연구)

  • Park, Sang-Joon;Kim, Kwan-Joong
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.12 no.12
    • /
    • pp.5873-5877
    • /
    • 2011
  • In this paper, we propose a study of analysis to the mobility of object such like pedestrian in safety management zone. If unusual situation is detected in safety management zone, it's designed that previous agreed mission will be processed. By human resource, safety management zone cannot be detected continuously so that through the induction of such detection system the reliability of area can be obtained. Hence, in this paper we propose the reaction scheme to detect special situation by object detection. By using sensor based processing system proposed by this paper, the detection of mobility and unusual situation can be implemented.

Near-Range Object Detection System Based on Code Correlation (코드 상관을 이용한 근거리 물체 탐지 장치)

  • Yoo, Ho-Sang;Gimm, Youn-Myoung;Jung, Jong-Chul
    • The Journal of Korean Institute of Electromagnetic Engineering and Science
    • /
    • v.18 no.4 s.119
    • /
    • pp.455-463
    • /
    • 2007
  • In this paper, it is proposed how to implement the object detection system which is able to apply to vehicular applications, unmanned facilities, automatic door and others with microwave. As the technology which detects an object with microwave is becoming more popular, it seems impossible to avoid mutual interference and jamming caused by limited frequency bandwidth. The system in this paper detects an object by correlating the code of TX and RX signals with the pseudo-random code having best quality in interference and jamming environment. In order to generate simulant doppler signal for detecting the distance of an fixed object where there is no doppler effect, the phase of TX signal is shifted continually. Also, the saturation of receiver was removed and the error of distance measurement was decreased by controlling the power of TX signal for getting constant RX signal. The proposed system detects a object which ranges from 0.5 m to 2.0 m and informs vocally whether there is the object within 1.0 m or not.

A Development of Road Crack Detection System Using Deep Learning-based Segmentation and Object Detection (딥러닝 기반의 분할과 객체탐지를 활용한 도로균열 탐지시스템 개발)

  • Ha, Jongwoo;Park, Kyongwon;Kim, Minsoo
    • The Journal of Society for e-Business Studies
    • /
    • v.26 no.1
    • /
    • pp.93-106
    • /
    • 2021
  • Many recent studies on deep learning-based road crack detection have shown significantly more improved performances than previous works using algorithm-based conventional approaches. However, many deep learning-based studies are still focused on classifying the types of cracks. The classification of crack types is highly anticipated in that it can improve the crack detection process, which is currently relying on manual intervention. However, it is essential to calculate the severity of the cracks as well as identifying the type of cracks in actual pavement maintenance planning, but studies related to road crack detection have not progressed enough to automated calculation of the severity of cracks. In order to calculate the severity of the crack, the type of crack and the area of the crack in the image must be identified together. This study deals with a method of using Mobilenet-SSD that is deep learning-based object detection techniques to effectively automate the simultaneous detection of crack types and crack areas. To improve the accuracy of object-detection for road cracks, several experiments were conducted to combine the U-Net for automatic segmentation of input image and object-detection model, and the results were summarized. As a result, image masking with U-Net is able to maximize object-detection performance with 0.9315 mAP value. While referring the results of this study, it is expected that the automation of the crack detection functionality on pave management system can be further enhanced.

An Overloaded Vehicle Identifying System based on Object Detection Model (객체 인식 모델을 활용한 적재 불량 화물차 탐지 시스템)

  • Jung, Woojin;Park, Jinuk;Park, Yongju
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.12
    • /
    • pp.1794-1799
    • /
    • 2022
  • Recently, the increasing number of overloaded vehicles on the road poses a risk to traffic safety, such as falling objects, road damage, and chain collisions due to the abnormal weight distribution, and can cause great damage once an accident occurs. therefore we propose to build an object detection-based AI model to identify overloaded vehicles that cause such social problems. In addition, we present a simple yet effective method to construct an object detection model for the large-scale vehicle images. In particular, we utilize the large-scale of vehicle image sets provided by open AI-Hub, which include the overloaded vehicles. We inspected the specific features of sizes of vehicles and types of image sources, and pre-processed these images to train a deep learning-based object detection model. Also, we propose an integrated system for tracking the detected vehicles. Finally, we demonstrated that the detection performance of the overloaded vehicle was improved by about 23% compared to the one using raw data.

A Study on Object Detection Algorithm for Abandoned and Removed Objects for Real-time Intelligent Surveillance System (실시간 지능형 감시 시스템을 위한 방치, 제거된 객체 검출에 관한 연구)

  • Jeon, Ji-Hye;Park, Jong-Hwa;Jeong, Cheol-Jun;Kang, In-Goo;An, Tae-Ki;Park, Goo-Man
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.35 no.1C
    • /
    • pp.24-32
    • /
    • 2010
  • In this paper we proposed an object tracking system that detects the abandoned and removed objects, which is to be used in the intelligent surveillance applications. After the GMM based background subtraction and by using histogram method, the static region is identified to detect abandoned and removed objects. Since the system is implemented on DSP chip, it operates in realtime and is programmable. The input videos used in the experiment contain various indoor and outdoor scenes, and they are categorized into three different complexities; low, midium and high. By 10 times of experiment, we obtained high detection ratio at low and medium complexity sequences. On the high complexity video, successful detection ratio was relatively low because the scene contains crowdedness and repeated occlusion. In the future work, these complicated situation should be solved.

People Detection Algorithm in the Beach (해변에서의 사람 검출 알고리즘)

  • Choi, Yu Jung;Kim, Yoon
    • Journal of Korea Multimedia Society
    • /
    • v.21 no.5
    • /
    • pp.558-570
    • /
    • 2018
  • Recently, object detection is a critical function for any system that uses computer vision and is widely used in various fields such as video surveillance and self-driving cars. However, the conventional methods can not detect the objects clearly because of the dynamic background change in the beach. In this paper, we propose a new technique to detect humans correctly in the dynamic videos like shores. A new background modeling method that combines spatial GMM (Gaussian Mixture Model) and temporal GMM is proposed to make more correct background image. Also, the proposed method improve the accuracy of people detection by using SVM (Support Vector Machine) to classify people from the objects and KCF (Kernelized Correlation Filter) Tracker to track people continuously in the complicated environment. The experimental result shows that our method can work well for detection and tracking of objects in videos containing dynamic factors and situations.

Vehicle Manufacturer Recognition using Deep Learning and Perspective Transformation

  • Ansari, Israfil;Shim, Jaechang
    • Journal of Multimedia Information System
    • /
    • v.6 no.4
    • /
    • pp.235-238
    • /
    • 2019
  • In real world object detection is an active research topic for understanding different objects from images. There are different models presented in past and had significant results. In this paper we are presenting vehicle logo detection using previous object detection models such as You only look once (YOLO) and Faster Region-based CNN (F-RCNN). Both the front and rear view of the vehicles were used for training and testing the proposed method. Along with deep learning an image pre-processing algorithm called perspective transformation is proposed for all the test images. Using perspective transformation, the top view images were transformed into front view images. This algorithm has higher detection rate as compared to raw images. Furthermore, YOLO model has better result as compare to F-RCNN model.

Object Recognition and Pose Estimation Based on Deep Learning for Visual Servoing (비주얼 서보잉을 위한 딥러닝 기반 물체 인식 및 자세 추정)

  • Cho, Jaemin;Kang, Sang Seung;Kim, Kye Kyung
    • The Journal of Korea Robotics Society
    • /
    • v.14 no.1
    • /
    • pp.1-7
    • /
    • 2019
  • Recently, smart factories have attracted much attention as a result of the 4th Industrial Revolution. Existing factory automation technologies are generally designed for simple repetition without using vision sensors. Even small object assemblies are still dependent on manual work. To satisfy the needs for replacing the existing system with new technology such as bin picking and visual servoing, precision and real-time application should be core. Therefore in our work we focused on the core elements by using deep learning algorithm to detect and classify the target object for real-time and analyzing the object features. We chose YOLO CNN which is capable of real-time working and combining the two tasks as mentioned above though there are lots of good deep learning algorithms such as Mask R-CNN and Fast R-CNN. Then through the line and inside features extracted from target object, we can obtain final outline and estimate object posture.