Autonomous car steering control and sign detection utilizing Haar Cascade and PID

This study applies methods of Image processing, Haar Cascade, and PID in building a system on an autonomous car. The working car has currently gained interest for the exploration. processing method is utilized to detect road markings applying algorithms (BGR RGB, Perspective transformation, threshold, canny edge, histogram) navigating pixel parameter values with actual distances. line detection results are applied input system, controlling handling five seconds settling time 1.5 cm overshoot. On other hand, Cascade image training requires positive (1000) negative (1400) sample images obtain statistical model. Regarding test results, correlation between distance camera pixels 1 cm/10 pixels. hence demonstrates accuracy 0.1cm/pixel. statistic detecting traffic signs obtained at 5 120 cm, optimal 90 cm. signs’ point view angle 10° 140,° 20° 1300. Meanwhile, when testing dynamically, performance depends reading as static appropriate lighting factor data signs. In addition, average sign 92.3%.