Autonomous Braking in a vehicle is governed by certain key parameters -
- Obstacle Detection & Tracking - This revolves around identifying common objects in the path of a car.
- Obstacle's Distance Estimation - Assessment of the distance of an obstacle from a particular point is fundamental for autonomous braking.
- Obstacle's Speed Evaluation - Finding the relative speed between these two players is crucial for approximating stopping time and the required deacceleration amount.
Lane Detection -
Pedestrian Detection -
For Pedestrian Detection we make use of the haarcascade_fullbody
module from OpenCV.
Obstacle Detection uses
cv2.findContours
to isolate contours in a masked image and sort out those which are above a certain threshold/value.
The function accepts three positional arguments cv2.findContours(image,cv.RETR_TREE,cv.CHAIN_APPROX_SIMPLE)
-
- First argument takes in the source image/frame
- Second one is contour retrieval mode
- Third argument is contour's approximation
Countour Map of the Region of Interest (ROI) -
Numbered Map of the Region of Interest (ROI) -
Masked Video of a Highway -
Countour Map of the Entire Video Frame -
Object Tracking PySource - YouTube