CNN을 사용한 차선검출 시스템 = Lane Detection System using CNN

다국어 초록 (Multilingual Abstract)

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

참고문헌 (Reference)

1 김현구, "지능형 자동차의 적응형 제어를 위한 차선인식" 대한임베디드공학회 4 (4): 180-189, 2009

2 김병수, "도로 환경 변화에 강인한 차선 검출 방법" 대한전자공학회 49 (49): 88-93, 2012

3 A. Fischer, "Training Restricted Boltzmann Machines : An Introduction" 47 (47): 25-39, 2014

4 F. Rosenblatt, "The Perceptron : a Probabilistic Model for Information Storage and Organization in The Brain" 65 (65): 386-408, 1958

5 D.W. Ruck, "The Multilayer Perceptron as An Approximation to A Bayes Optimal Discriminant Function" 1 (1): 296-298, 1990

6 K. ZuWhan, "Robust Lane Detection and Tracking in Challenging Scenarios" 9 (9): 16-26, 2008

7 A.F. Martin, "Random Sample Consensus : a Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography" 24 (24): 381-395, 1981

8 D.E. Rumelhart, "Learning Representations by Back-propagating Errors" 1988

9 D.E. Rumelhart, "Learning Representations by Back-propagating Errors" 1988

10 Y. Bin, "Lane Boundary Detection Using A Multiresolution Hough Transform" 2 : 748-751, 1997

11 D. H. Ballard, "Generalizing The Hough Transform to Detect Arbitrary Shapes" 13 (13): 111-122, 1981

12 S. Lawrence, "Face Recognition : A Convolutional Neural-network Approach" 8 (8): 98-113, 1997

13 A. Borkar, "A Novel Lane Detection System with Efficient Ground Truth Generation" 13 (13): 365-374, 2012

14 W.S. McCulloch, "A Logical Calculus of The Ideas Immanent in Nervous Activity" 5 (5): 115-133, 1943

15 G. Hinton, "A Fast Learning Algorithm for Deep Belief Nets" 18 (18): 1527-1554, 2006