Download presentation
Presentation is loading. Please wait.
1
CS223B Assignment 1 Recap
2
Lots of Solutions! 37 Groups Many different approaches Let’s take a peek at all 37 results on one image from the test set
39
Possible Things to Look For Symmetry Color Shadow Corners Edges Texture Taillights
40
Road Finding Tactic 1 Run adaptive flood fill on the image starting at the pixels near the bottom Everything that gets filled in is considered road Holes inside the road are likely car candidates
41
Road Finding Tactic 2 Run an edge detector (such as Prewitt or Canny) and a Hough transform, and then look for lines with the right approximate angle and position.
42
Road Finding Tactic 3 Sample the color from some pixels directly in front of car (bottom of image) Generate a difference map using this color Run an edge detector on this difference map, followed by a Hough transform
43
Road Finding Tactic 4 Assume the road is in pretty much the same place in every image and hard code it in
44
Edge Approach 1 Detect edges with Canny detector Dilate image to join nearby edges Fill in closed regions
45
Edge Approach 2 Custom edge mask that considers vertical and horizontal edges in likely configurations
46
Shadow Finding Use a mask that enhances horizontal edges Look for several adjacent rows of dark pixels in the road region
47
Corner Approach Compute strong corners Cluster them with kmeans Find the densest clusters and compute their convex hulls
48
Texture Approach Look for regions of high frequency –Find density of edges in rectangular regions –Mask or sum the derivative across rectangular regions –Take FFT of image and set magnitudes to 1, leaving only phase info; inverse FFT then enhances portions with many frequencies
49
Taillight Detection Transforming the color space can help spot the reddest pixels Groups of these pixels are good candidates for taillights If there’s a horizontal pair of taillights, even better Or, use a mask with the pair built in
50
Going from Pixels to Regions Count the number of “car pixels” in square regions; if above a threshold, consider it a car region
51
Statistical Classifier More stages mean many fewer false positives (and only slightly fewer missed cars)
52
Multiple Classifiers
53
Filtering Classifier Output Tactics Check number of corners in the rectangle. If too low, reject. Check position and size of rectangle. If it doesn’t make sense given perspective, then reject. Run an edge detector on the rectangular region and then sum the pixels inside. If below threshold, reject. Look at the average derivative of image intensity. If below threshold, reject.
54
Consider Geometry of Scene
55
Combining Results from Different Detectors Many of the best solutions used some weighted combination of several heuristics to verify the strength of hypotheses …
56
Building a Better Bounding Box Get the strong corners in the box, and then trace the convex hull of these corners to eliminate some of the road. Alternatively, make a 2D or 3D model of car shape based on image position and replace rectangle with appropriate polygon. Or, segment the rectangle by colors and keep only the inner segments.
57
Common Mistakes Strange ways of drawing car regions Don’t use anti-aliased lines or flood fill, just draw filled polygons with cvPolyLine
58
Common Mistakes Stray Pixels Could be fixed with image close operation
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.