Matching vehicle sensors to reference sensors using machine learning methods

Vehicle manufacturers equip their products with many sensors which are used to analyze the surroundings. In this thesis the environment is described with a set of high level objects where an object can be either a vehicle, a person or an animal. These objects are given different properties such as position and heading relative to the ego-vehicle. It is of interest to know the accuracy of the measurements describing the high level objects. To measure the accuracy one must first find the true state of the high level objects. In this work measurements from a more accurate system that tracks the same high level objects have been considered the ground truth. A matching algorithm was developed which matches the high level objects to ground truth objects. The matching was done using a variety of machine learning algorithms where some reach a correct classification rate of ∼ 99% with a low sensitivity to added noise.

[1]  Robert Hecht-Nielsen,et al.  Theory of the backpropagation neural network , 1989, International 1989 Joint Conference on Neural Networks.

[2]  Julian Ryde,et al.  Performance of laser and radar ranging devices in adverse environmental conditions , 2009, J. Field Robotics.

[3]  Charu C. Aggarwal,et al.  Neural Networks and Deep Learning , 2018, Springer International Publishing.

[4]  Lunman Deng,et al.  Decision tree classification algorithm based on cost and benefit dual-sensitive , 2014, IEEE International Conference on Electro/Information Technology.

[5]  Loc Nguyen,et al.  Tutorial on Support Vector Machine , 2016 .

[6]  Yan Zhang,et al.  A preprocessing method of AdaBoost for mislabeled data classification , 2017, 2017 29th Chinese Control And Decision Conference (CCDC).

[7]  José Luis Rojo-Álvarez,et al.  An Introduction to Kernel Methods , 2009, Encyclopedia of Data Warehousing and Mining.

[8]  Shashi Pal Singh,et al.  Machine translation using deep learning: An overview , 2017, 2017 International Conference on Computer, Communications and Electronics (Comptelix).

[9]  Geoffrey E. Hinton,et al.  On the importance of initialization and momentum in deep learning , 2013, ICML.

[10]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[11]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Jinwen Ma,et al.  ICA and PCA integrated feature extraction for classification , 2016, 2016 IEEE 13th International Conference on Signal Processing (ICSP).

[13]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[14]  Luis Mateus Rocha,et al.  Singular value decomposition and principal component analysis , 2003 .

[15]  J.J. Hopfield,et al.  Artificial neural networks , 1988, IEEE Circuits and Devices Magazine.

[16]  King Ngi Ngan,et al.  Jaccard index compensation for object segmentation evaluation , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[17]  Erkki Oja,et al.  Classification with learning k-nearest neighbors , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[18]  Shawki Areibi,et al.  Design exploration of ASIP architectures for the K-Nearest Neighbor machine-learning algorithm , 2016, 2016 28th International Conference on Microelectronics (ICM).

[19]  Kilian Stoffel,et al.  Theoretical Comparison between the Gini Index and Information Gain Criteria , 2004, Annals of Mathematics and Artificial Intelligence.

[20]  Dariu Gavrila,et al.  Real-time object detection for "smart" vehicles , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[21]  Santokh Singh,et al.  Critical Reasons for Crashes Investigated in the National Motor Vehicle Crash Causation Survey , 2015 .

[22]  Sridhar Krishnan,et al.  Signal decomposition by multi-scale PCA and its applications to long-term EEG signal classification , 2011, The 2011 IEEE/ICME International Conference on Complex Medical Engineering.

[23]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[24]  K. Bathe.  Finite Element Procedures , 1995 .

[25]  T. Zwick,et al.  Millimeter-Wave Technology for Automotive Radar Sensors in the 77 GHz Frequency Band , 2012, IEEE Transactions on Microwave Theory and Techniques.

[26]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[27]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[28]  Tapio Elomaa,et al.  An Analysis of Reduced Error Pruning , 2001, J. Artif. Intell. Res..

[29]  Erik Cambria,et al.  Recent Trends in Deep Learning Based Natural Language Processing , 2017, IEEE Comput. Intell. Mag..

[30]  Shie Mannor,et al.  Sparse algorithms are not stable: A no-free-lunch theorem , 2008, Allerton 2008.

[31]  L. Biegler,et al.  Quadratic programming methods for reduced Hessian SQP , 1994 .

[32]  Nasser Mohammadiha,et al.  Offline object matching and evaluation process for verification of autonomous driving , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[33]  Thomas G. Dietterich.  An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization , 2000, Machine Learning.

[34]  Sanyam Shukla,et al.  Analysis of k-Fold Cross-Validation over Hold-Out Validation on Colossal Datasets for Quality Classification , 2016, 2016 IEEE 6th International Conference on Advanced Computing (IACC).

[35]  Margaret M. Peden,et al.  World Report on Road Traffic Injury Prevention , 2004 .