Structured_Hough_Voting

Download Report

Transcript Structured_Hough_Voting

GM-Carnegie Mellon Autonomous Driving CRL

Structured Hough Voting for Vision based Highway Border Detection

Zhiding Yu Carnegie Mellon University 1

GM-Carnegie Mellon Autonomous Driving CRL

Autonomous Driving: Not If, But When

2

GM-Carnegie Mellon Autonomous Driving CRL

GM-CMU Collaborative Research

GM-Carnegie Mellon Autonomous Driving CRL

Sensors Setup on SRX Platform

Images from: Junqing Wei et al., “Towards a Viable Autonomous Driving Research Platform,” IEEE Intelligent Vehicles Symposium (IV), 2013

GM-Carnegie Mellon Autonomous Driving CRL

Sensors: Price vs Information Camera Lidar Radar Price

GM-Carnegie Mellon Autonomous Driving CRL

Computer Vision Applications

    

Object detection

(pedestrian, vehicle, bicycle…)

Road parsing

(lane/border detection, road segmentation, vanishing point estimation…)

Localization and tracking Driver status monitoring Many other applications……

GM-Carnegie Mellon Autonomous Driving CRL

Motivation, Description and Goal Goal

– Development for future driving assistance system and autonomous driving system – Robust detection within 0.5 to 6 meters detection range. Achieve near 100% accuracy in daytime and over 90% in nighttime on the right most lane – Handling various scenarios including highway entrance and exit – Extend to the joint system with front view 7

GM-Carnegie Mellon Autonomous Driving CRL

High-Level Idea: Learning based Method Concrete Barrier Densely Fired scanning windows Returned Voting Points Guard Rail Soft Shoulder Concrete Barrier Guard Rail Soft Shoulder Lane Marking Structured Hough Voting Border / lane marking hypotheses

GM-Carnegie Mellon Autonomous Driving CRL

Dataset Collection Overall 1592 training images:

1. Concrete Barrier (839 images) 2. Guard Rail (300 images) 3. Soft Shoulder (453 images)

Overall 2638 testing images:

GM-Carnegie Mellon Autonomous Driving CRL

Training Patch Alignment Positive Samples: Negative Samples: Concrete Natural Steel Lane Marker

GM-Carnegie Mellon Autonomous Driving CRL

Feature Extraction HOG Filter Bank Concatenated Filter Bank Feature Patches that are discriminative to HOG Patches that are discriminative to filter banks Concatenated HOG Feature

GM-Carnegie Mellon Autonomous Driving CRL

Classification & Detection

   

Extract features from all training patches (based on previous page) Perform Fisher discriminant analysis Train an RBF kernel SVM Scanning window detection (Deliberately having a lot of positive firing) Concrete Barrier Guard Rail Soft Shoulder Lane Marking

GM-Carnegie Mellon Autonomous Driving CRL

Hough Voting

GM-Carnegie Mellon Autonomous Driving CRL

Structured Hough Voting: Intuitions

  

Basic philosophy: A model that assumes voting results are correlated rather than independent Inter-frame structural info on hypotheses (Temporal smoothness) Intra-frame structural info (Geometric relationship)

Multiple candidate hypotheses generation (Proposals with diversity)

1. Constrained Hough Voting on detected voting points (

Detection + Tracking

) 2. Arbitrary Hough Voting on detected voting points (

Detection

) 3. Constrained Hough Voting on image gradients (

Pure Tracking

)

GM-Carnegie Mellon Autonomous Driving CRL

Purpose of Candidate 1

Deals most of the frames where hypotheses from consecutive frames have strong correlation.

GM-Carnegie Mellon Autonomous Driving CRL

Purpose of Candidate 2

Automatically corrects result through searching for “much better” voting configurations (This is the power of detection, avoids error from tracking)

GM-Carnegie Mellon Autonomous Driving CRL

Purpose of Candidate 3

In the worst case where Type 1 voters fail, perform tracking by gradients from previous pose configuration.

GM-Carnegie Mellon Autonomous Driving CRL

Modeling under CRF: Background

 A Conditional Random Field (CRF) discriminatively defines the joint posterior probability as the product of a set of

potentials Unary Potential Pairwise Potential H 1 H 2 … H N X 1 X 2 X N

 The potentials are functions with hypotheses

H i

in such a way that a

larger potential value

being the variables. They are modeled generally indicates a

better hypothesis

configuration.

 CRF inference seeks to find the joint hypothesis configuration

H

that maximizes

GM-Carnegie Mellon Autonomous Driving CRL

Modeling under CRF: Intuition

    

What are the hypothesis H

i

?

E.g.: image pixel labels (FG/BG, Object Class, etc.), if it is a segmentation problem.

In our problem, H

i

is the Hough Voting hypothesis: H

i

= (r,

θ

).

X is the observation of voting point coordinates and their weights.

The unary potential corresponds to the exponential of Hough voting weights: exp(v(H

i

)).

The pairwise potential corresponds to the inter-frame smoothness (tracking) constraint.

H 1 H 2 … H N X 1 X 2 X N

GM-Carnegie Mellon Autonomous Driving CRL

No Structural Information … H bd,1 H bd,2 H bd,N X 1 X 2 X

N

H ln,1 H ln,2 … H ln,N X 1 X 2 X

N

Simplest Case:

frame-wise independent Hough voting

GM-Carnegie Mellon Autonomous Driving CRL

Adding Inter-frame Structural Info.

… H bd,1 H bd,2 H bd,N X 1 X 2 X

N

H ln,1 H ln,2 … H ln,N X 1 X 2 X

N

Adding temporal smoothness:

Hough voting constrained by neighboring frames

GM-Carnegie Mellon Autonomous Driving CRL

Adding Intra-frame Structural Info.

… H bd,1 H bd,2 H bd,N X 1 X 2 X

N

H ln,1 H ln,2 … H ln,N X 1 X 2 X

N

Adding Geometric Constraint:

Hough voting constrained by both neighboring frames and intra-frame hypotheses

GM-Carnegie Mellon Autonomous Driving CRL

The Structured Hough Voting Model Candidate Hypotheses Generation Unit

• • •

Coupled Structure Potential

• • •

Mode Selection Potential

GM-Carnegie Mellon Autonomous Driving CRL

The Structured Hough Voting Model

GM-Carnegie Mellon Autonomous Driving CRL

Candidate Hypotheses Generation Unit

GM-Carnegie Mellon Autonomous Driving CRL

Mode Selection Potential

 Use

decision tree

to guide the mode selection.

 The mode selection basically forces the output to be one of the candidate hypotheses, but allows discrepancy with the decision tree prediction with a penalty.

GM-Carnegie Mellon Autonomous Driving CRL

Coupled Structure Potential

   The coupled structure potential captures two most important relations between a border hypothesis and a lane hypothesis

Parallelism Distance

GM-Carnegie Mellon Autonomous Driving CRL

Inference

  Conducting a whole inference each time given a new frame is computationally infeasible.

Relaxation: Initialize with the inferred state variable configuration of the previous

t

-1 frames and infer the current state variables, updating in an incremental way.

Inference procedure at t = 1:

1. Perform Hough voting for both border and lane marking 2. Perturbate hypotheses if geometric relationship violated (optional) 

Inference procedure at t > 1:

1. Generate the 3 candidate hypotheses for both border and lane marking 2. Use decision tree to help selecting the best candidate 3. Perturbate candidate hypotheses if geometric relationship violated (optional) 4. Re-select the best candidate

GM-Carnegie Mellon Autonomous Driving CRL

Experiments: Adding Coupled Structure

GM-Carnegie Mellon Autonomous Driving CRL

Experiments: Qualitative Results Ground Truth and Baseline methods:

1. Ground Truth 2. Independent Hough voting in each frame using the fired detector voting points 3. Hough voting using the triggered detector voting points constrained by previous frame 4. Adding gradient tracking to Baseline 2.

5. Kalman filter.

6. Proposed Method

GM-Carnegie Mellon Autonomous Driving CRL

Experiments: Quantitative Results

GM-Carnegie Mellon Autonomous Driving CRL

Highway Entrance Detection and Lane State Tracking

GM-Carnegie Mellon Autonomous Driving CRL

Summary

Proposed the Structured Hough Voting Model

The proposed model can be theoretically formulated under a CRF

Fast real-time feature extraction and online inference

Achieves very robust and good performance under challenging scenarios and low quality inputs from production camera

GM-Carnegie Mellon Autonomous Driving CRL

Thank You!

Q & A