• Title/Summary/Keyword: vision-based recognition

Search Result 633, Processing Time 0.032 seconds

Navigation of a Mobile Robot Using the Hand Gesture Recognition

  • Kim, Il-Myung;Kim, Wan-Cheol;Yun, Jae-Mu;Jin, Tae-Seok;Lee, Jang-Myung
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2001.10a
    • /
    • pp.126.3-126
    • /
    • 2001
  • A new method to govern the navigation of a mobile robot is proposed based on the following two procedures: one is to achieve vision information by using a 2 D-O-F camera as a communicating medium between a man and a mobile robot and the other is to analyze and to behave according to the recognized hand gesture commands. In the previous researches, mobile robots are passively to move through landmarks, beacons, etc. To incorporate various changes of situation, a new control system manages the dynamical navigation of a mobile robot. Moreover, without any generally used expensive equipments or complex algorithms for hand gesture recognition, a reliable hand gesture recognition system is efficiently implemented to convey the human commands to the mobile robot with a few constraints.

  • PDF

Gabor Filter-based Feature Extraction for Human Activity Recognition (인간의 활동 인정 가보 필터 기반의 특징 추출)

  • AnhTu, Nguyen;Lee, Young-Koo;Lee, Sung-Young
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2011.06c
    • /
    • pp.429-432
    • /
    • 2011
  • Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous work on activity recognition focuses on recognition from a single view and ignores the issue of view invariance. In this paper, we present an independent Gabor features (IGFs) method comes from the derivation of independent Gabor features in the feature extraction stage. The Gabor transformed human image exhibit strong characteristics of spatial locality, scale and orientation selectivity.

Hand Shape Classification using Contour Distribution (윤곽 분포를 이용한 이미지 기반의 손모양 인식 기술)

  • Lee, Changmin;Kim, DaeEun
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.20 no.6
    • /
    • pp.593-598
    • /
    • 2014
  • Hand gesture recognition based on vision is a challenging task in human-robot interaction. The sign language of finger spelling alphabets has been tested as a kind of hand gesture. In this paper, we test hand gesture recognition by detecting the contour shape and orientation of hand with visual image. The method has three stages, the first stage of finding hand component separated from the background image, the second stage of extracting the contour feature over the hand component and the last stage of comparing the feature with the reference features in the database. Here, finger spelling alphabets are used to verify the performance of our system and our method shows good performance to discriminate finger alphabets.

Implementation of Moving Object Recognition based on Deep Learning (딥러닝을 통한 움직이는 객체 검출 알고리즘 구현)

  • Lee, YuKyong;Lee, Yong-Hwan
    • Journal of the Semiconductor & Display Technology
    • /
    • v.17 no.2
    • /
    • pp.67-70
    • /
    • 2018
  • Object detection and tracking is an exciting and interesting research area in the field of computer vision, and its technologies have been widely used in various application systems such as surveillance, military, and augmented reality. This paper proposes and implements a novel and more robust object recognition and tracking system to localize and track multiple objects from input images, which estimates target state using the likelihoods obtained from multiple CNNs. As the experimental result, the proposed algorithm is effective to handle multi-modal target appearances and other exceptions.

Lightweight CNN based Meter Digit Recognition

  • Sharma, Akshay Kumar;Kim, Kyung Ki
    • Journal of Sensor Science and Technology
    • /
    • v.30 no.1
    • /
    • pp.15-19
    • /
    • 2021
  • Image processing is one of the major techniques that are used for computer vision. Nowadays, researchers are using machine learning and deep learning for the aforementioned task. In recent years, digit recognition tasks, i.e., automatic meter recognition approach using electric or water meters, have been studied several times. However, two major issues arise when we talk about previous studies: first, the use of the deep learning technique, which includes a large number of parameters that increase the computational cost and consume more power; and second, recent studies are limited to the detection of digits and not storing or providing detected digits to a database or mobile applications. This paper proposes a system that can detect the digital number of meter readings using a lightweight deep neural network (DNN) for low power consumption and send those digits to an Android mobile application in real-time to store them and make life easy. The proposed lightweight DNN is computationally inexpensive and exhibits accuracy similar to those of conventional DNNs.

Video augmentation technique for human action recognition using genetic algorithm

  • Nida, Nudrat;Yousaf, Muhammad Haroon;Irtaza, Aun;Velastin, Sergio A.
    • ETRI Journal
    • /
    • v.44 no.2
    • /
    • pp.327-338
    • /
    • 2022
  • Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

Enhancing Automated Recognition of Small-Sized Construction Tools Using Synthetic Images: Validating Practical Applicability Through Confidence Scores

  • Soeun HAN;Choongwan KOO
    • International conference on construction engineering and project management
    • /
    • 2024.07a
    • /
    • pp.1308-1308
    • /
    • 2024
  • Computer vision techniques have been widely employed in automated construction management to enhance safety and prevent accidents at construction sites. However, previous research in the field of vision-based approaches has often overlooked small-sized construction tools. These tools present unique challenges in data collection due to their diverse shapes and sizes, as well as in improving model performance to accurately detect and classify them. To address these challenges, this study aimed to enhance the performance of vision-based classifiers for small-sized construction tools, including bucket, cord reel, hammer, and tacker, by leveraging synthetic images generated from a 3D virtual environment. Three classifiers were developed using the YOLOv8 algorithm, each differing in the composition of the training dataset: (i) 'Real-4000', trained on 4,000 authentic images collected through web crawling methods (1,000 images per object); (ii) 'Hybrid-4000', consisting of 2,000 authentic images and 2,000 synthetic images; and (iii) 'Hybrid-8000', incorporating 4,000 authentic images and 4,000 synthetic images. To validate the performance of the classifiers, 144 directly-captured images for each object were collected from real construction sites as the test dataset. The mean Average Precision at an IoU threshold of 0.5 (mAP_0.5) for the classifiers was 79.6%, 90.8%, and 94.8%, respectively, with the 'Hybrid-8000' model demonstrating the highest performance. Notably, for objects with significant shape variations, the use of synthetic images led to the enhanced performance of the vision-based classifiers. Moreover, the practical applicability of the proposed classifiers was validated through confidence scores, particularly between the 'Hybrid-4000' and 'Hybrid-8000' models. Statistical analysis using t-tests indicated that the performance of the 'Hybrid-4000' model would either matched or exceeded that of the 'Hybrid-8000'model based on confidence scores. Thus, employing the 'Hybrid-4000' model may be preferable in terms of data collection efficiency and processing time, contributing to enhanced safety and real-time automation and robotics in construction practices.

A Vision Based Bio-Cell Recognition for Biomanipulation with Multiple Views

  • Jang, Min-Soo;Lee, Seok-Joo;Lee, Ho-Dong;Kim, Byung-Kyu;Park, Jong-Oh;Park, Gwi-Tae
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2003.10a
    • /
    • pp.2435-2440
    • /
    • 2003
  • Manipulation of the nano/micro scale object has been a key technology in biology as the sizes of DNA, chromosome, nucleus, cell and embryo are within such order. For instance, for embryo cell manipulation, the cell injection is performed manually. The operator often spends over a year to carry out a cell manipulation project. Since the typical success rate of such operation is extremely low, automation of such biological cell manipulation has been asked. As the operator spends most of his time in finding the position of cell in the Petri dish and in injecting bio-material to the cell from the best orientation. In this paper, we propose a new strategy and a vision system, by which one can find, recognize and track nucleus, polar body, and zona pellucida of the embryo cell for automatic biomanipulation. The deformable template matching algorithm has been used in recognizing the nucleus and polar body of each cell. Result suggests that it outperforms the conventional methods.

  • PDF

A Practical Solution toward SLAM in Indoor environment Based on Visual Objects and Robust Sonar Features (가정환경을 위한 실용적인 SLAM 기법 개발 : 비전 센서와 초음파 센서의 통합)

  • Ahn, Sung-Hwan;Choi, Jin-Woo;Choi, Min-Yong;Chung, Wan-Kyun
    • The Journal of Korea Robotics Society
    • /
    • v.1 no.1
    • /
    • pp.25-35
    • /
    • 2006
  • Improving practicality of SLAM requires various sensors to be fused effectively in order to cope with uncertainty induced from both environment and sensors. In this case, combining sonar and vision sensors possesses numerous advantages of economical efficiency and complementary cooperation. Especially, it can remedy false data association and divergence problem of sonar sensors, and overcome low frequency SLAM update caused by computational burden and weakness in illumination changes of vision sensors. In this paper, we propose a SLAM method to join sonar sensors and stereo camera together. It consists of two schemes, extracting robust point and line features from sonar data and recognizing planar visual objects using multi-scale Harris corner detector and its SIFT descriptor from pre-constructed object database. And fusing sonar features and visual objects through EKF-SLAM can give correct data association via object recognition and high frequency update via sonar features. As a result, it can increase robustness and accuracy of SLAM in indoor environment. The performance of the proposed algorithm was verified by experiments in home -like environment.

  • PDF

A Study on the Improved Line Detection Method for Pipeline Recognition of P&ID (P&ID의 파이프라인 인식 향상을 위한 라인 검출 개선에 관한 연구)

  • Oh, Sangjin;Chae, Myeonghoon;Lee, Hyun;Lee, Younghwan;Jeong, Eunkyung;Lee, Hyunsik
    • Plant Journal
    • /
    • v.16 no.4
    • /
    • pp.33-39
    • /
    • 2020
  • For several decades, productivity in construction industry has been regressed and it is inevitable to improve productivity for major EPC players. One of challenges to achieve this goal is automatically extracting information from imaged drawings. Although computer vision technique has been advanced rapidly, it is still a problem to detect pipe lines in a drawing. Earlier works for line detection have problems that detected line elements be broken into small pieces and accuracy of detection is not enough for engineers. Thus, we adopted Contour and Hough Transform algorithm and reinforced these to improve detection results. First, Contour algorithm is used with Ramer Douglas Peucker algorithm(RDP). Weakness of contour algorithm is that some blank spaces are occasionally found in the middle of lines and RDP covers them around 17%. Second, HEC Hough Transform algorithm, we propose on this paper, is improved version of Hough Transform. It adopted iteration of Hough Transform and merged detected lines by conventional Hough Transform based on Euclidean Distance. As a result, performance of Our proposed method improved by 30% than previous.