23.12.2014 Views

OCTOBER 19-20, 2012 - YMCA University of Science & Technology

OCTOBER 19-20, 2012 - YMCA University of Science & Technology

OCTOBER 19-20, 2012 - YMCA University of Science & Technology

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Proceedings <strong>of</strong> the National Conference on<br />

Trends and Advances in Mechanical Engineering,<br />

<strong>YMCA</strong> <strong>University</strong> <strong>of</strong> <strong>Science</strong> & <strong>Technology</strong>, Faridabad, Haryana, Oct <strong>19</strong>-<strong>20</strong>, <strong>20</strong>12<br />

(a) (b) (c)<br />

Fig. 8 Image captured at higher light intensity<br />

Using algorithm proposed in this paper, the experimental results in different illumination conditions are shown<br />

in Fig. 7 and Fig.8. The test results are as given below in Table 1.<br />

Sl. No. Colour Minimum light<br />

intensity(Threshold )<br />

Table 1. Test results<br />

Higher light<br />

intensity(Threshold )<br />

Action taken<br />

By robot<br />

1 Red Any Value less than 225 Any Value less than 255 Localization<br />

2 Blue Below 150 Below 175 Turn towards<br />

Right<br />

3 Green Below 100 Below 125 Turn towards light<br />

As per Table 1, the threshold values are more for higher light intensity when compared to that <strong>of</strong> minimum light<br />

intensity environmental conditions. According to overall results, higher the light intensity higher values <strong>of</strong><br />

threshold can be obtained.<br />

6. Conclusion<br />

In connection with the demand <strong>of</strong> the robot application, this work proposes colour image detection method for<br />

target object recognition. Using colour image segmentation algorithm in MATLAB to find target object is a<br />

slow process. From the tests it’s recognized that estimation accuracy depends on object colour detection. The<br />

effectiveness <strong>of</strong> this algorithm was verified through real experiments. Autonomous robot localization and<br />

functionality depends on the image processing <strong>of</strong> data taken by the camera. Data can be greatly affected by light<br />

energy received from the environment. It can be concluded from the test results; light illumination problem can<br />

be overcome by adjusting the threshold value and improve the robustness and adaptability <strong>of</strong> the system. Realtime<br />

image processing and camera calibration are future research work needed to improve the estimation<br />

accuracy for the mobile robot.<br />

References<br />

[1] J. BORENSTEIN, H.R. EVERETT, L. FENG, AND D. WEHE, Mobile Robot Positioning & Sensors and<br />

Techniques, Invited paper for the Journal <strong>of</strong> Robotic Systems, Special Issue on Mobile Robots. 14(4),. 231<br />

– 249.<br />

[2] SOOYONG LEE AND JAE-BOK SONG, <strong>20</strong>05, Mobile Robot Localization using Range Sensors :<br />

Consecutive Scanning and Cooperative Scanning“, International Journal <strong>of</strong> Control, Automation, and<br />

Systems, 3(1), 1-14, March <strong>20</strong>05<br />

[3] R. A. BROOKS, <strong>19</strong>86, A robust layered control system for a mobile robot, IEEE J. Robot. Automat., vol.<br />

RA-2, 14–23.<br />

[4] Y. NAKAMURA, <strong>19</strong>91, Advanced Robotics: Redundancy and Optimization. Reading, MA: Addison-<br />

Wesley,<br />

294

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!