Beruflich Dokumente
Kultur Dokumente
Introduction
Application of lane detection : 1. Lane excursion detection and warning 2. Intelligent cruise control 3. Autonomous driving Some lane detection algorithms Edge-based, Deformable-template, Bsnake
Approach (Edge-based)
Step 1: Get the edge information Step 2: Hough Transform Step 3: Search out the lane marking candidates Step 4: Decide the lane marking
Approach
Approach
Compare these images Edges are preserved using background subtraction method Edge operation
Approach
Approach
1. 2. 3.
The red lines are the first 20 lines which have the biggest count numbers in Hough parameter space. For each lane marking in the real scene, there are many line candidates around it. There are some fake lines caused by the vehicle queue.
Approach
Result
There is a little offset between the detected lane marking and that in real scene. This is because the lane is not completely straight and the lane mark is broken in the scene.
University Ave.
Edge image
Without restriction to
Restrict
University Ave.
Restrict
Note: Because lots of the edge information for the left lane marking are lost, there is an offset between the detected lane marking and that in the real scene
Summary
Alg. works well for these straight lane cases. Key methods includes:
Find the background gray range, background subtraction, edge detection, Hough Transform, find the lane marking candidates, sort the lane marking candidates, group the cluster lines as one line, delete fake lines and calculate the mid-line of each lane
Reference
Karl Kluge, Sridhar Lakshmanan, A deformabletemplate approach to lane detection, Gonzalez, J.P.; Ozguner, U.; Lane detection using histogram-based segmentation and decision trees, Yu, B.; Jain, A.K.; Lane boundary detection using a multiresolution Hough transform, Yue Wang; Eam Khwang Teoh; Dinggang Shen; Lane detection using B-snake, Others