The paper describes the use of thermal cameraand IR night vision system for the detection of Pedestriansand objects that may cause accident at night time. As per thesurvey most of the accidents cause is due to low vision abilityof human at night time, which leads to most dangerous andhigher number of accidents at night with respect to day time.This system include the IR night vision camera which detectsthe object with the help of IR LED and photodiode pair, thiscamera have capability to detect the object up to 100m. Thethermal camera detects the heat generated by any of theobject like cars, Human animals etc. which gives us thefacility to detect the object for higher range and with lowreflective surface where IR night vision may fails. With theuse of these two cameras mounted on car which helps thedriver to drive safely. In this system, HOG (Histogram oforientated gradients) algorithm and support vector machine (SVM) is performed with the help of OpenCV in Matlab and Emgu CV in Visual Basic 2012. The system is tested on thevideo recorded using these cameras, and got good andefficient result. And this system is cost efficient and easy to implement.

Thermal and IR Night vision, OpenCV, VideoProcessing, Object and Human Detection, Automobile Safty.