/Traffic-Sign-Classifier

An autonomous braking system that uses sensor data from Radar and Computer Vision to localize the accurate position of an object around a vehicle using Neural Networks. An algorithm to fuse the data from sensors and camera to perform odometry operations

Primary LanguageJupyter Notebook

Autonomous-Guided-Vehicle

Autonomous Braking in a vehicle is governed by certain key parameters -

  1. Obstacle Detection & Tracking - This revolves around identifying common objects in the path of a car.
  2. Obstacle's Distance Estimation - Assessment of the distance of an obstacle from a particular point is fundamental for autonomous braking.
  3. 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) -

  1. First argument takes in the source image/frame
  2. Second one is contour retrieval mode
  3. 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 -

References -

Object Tracking PySource - YouTube