eduzhai > Applied Sciences > Engineering >

Image Enhancement and Object Recognition for Night Vision Surveillance

  • Save

... pages left unread,continue reading

Document pages: 6 pages

Abstract: Object recognition is a critical part of any surveillance system. It is thematter of utmost concern to identify intruders and foreign objects in the areawhere surveillance is done. The performance of surveillance system using thetraditional camera in daylight is vastly superior as compared to night. Themain problem for surveillance during the night is the objects captured bytraditional cameras have low contrast against the background because of theabsence of ambient light in the visible spectrum. Due to that reason, the imageis taken in low light condition using an Infrared Camera and the image isenhanced to obtain an image with higher contrast using different enhancingalgorithms based on the spatial domain. The enhanced image is then sent to theclassification process. The classification is done by using convolutionalneural network followed by a fully connected layer of neurons. The accuracy ofclassification after implementing different enhancement algorithms is comparedin this paper.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×