CB+NN Ensemble to Improve Tracking Accuracy in Air Surveillance

Finding or tracking the location of an object accurately is a crucial problem in defense applications, robotics and computer vision. Radars fall into the spectrum of high-end defense sensors or systems upon which the security and surveillance of the entire world depends. There has been a lot of focus on the topic of Multi Sensor Tracking in recent years, with radars as the sensors. The Indian Air Force uses a Multi Sensor Tracking (MST) system to detect flights pan India, developed and supported by BEL(Bharat Electronics Limited), a defense agency we are working with. In this paper, we describe our Machine Learning approach, which is built on top of the existing system, the Air force uses. For purposes of this work, we trained our models on about 13 million anonymized real Multi Sensor tracking data points provided by radars performing tracking activity across the Indian air space. The approach has shown an increase in the accuracy of tracking by 5 percent from 91 to 96. The model and the corresponding code were transitioned to BEL, which has been tested in their simulation environment with a plan to take forward for ground testing. Our approach comprises of 3 steps: (a) We train a Neural Network model and a CatBoost model and ensemble them using a Logistic Regression model to predict one type of error, namely Splitting error, which can help to improve the accuracy of tracking. (b) We again train a Neural Network model and a CatBoost model and ensemble them using a different Logistic Regression model to predict the second type of error, namely Merging error, which can further improve the accuracy of tracking. (c) We use cosine similarity to find the nearest neighbour and correct the data points, predicted to have Splitting/Merging errors, by predicting the original global track of these data points.

[1]  Praveen Paruchuri,et al.  An Ensemble Learning Approach to Improve Tracking Accuracy of Multi Sensor Fusion , 2020, ICONIP.

[2]  Petro Liashchynskyi,et al.  Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS , 2019, ArXiv.

[3]  Radosław Belka.  An indoor tracking system and pattern recognition algorithms as key components of IoT-based entertainment industry , 2019, Symposium on Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments (WILGA).

[4]  Anna Veronika Dorogush,et al.  CatBoost: unbiased boosting with categorical features , 2017, NeurIPS.

[5]  Juha Jylhä,et al.  Learning of a tracker model from multi-radar data for performance prediction of air surveillance system , 2017, 2017 IEEE Congress on Evolutionary Computation (CEC).

[6]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[7]  Kristin L. Sainani,et al.  Logistic Regression , 2014, PM & R : the journal of injury, function, and rehabilitation.

[8]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[9]  Mohammad A. Al-Khedher,et al.  Hybrid GPS-GSM Localization of Automobile Tracking System , 2011, ArXiv.

[10]  Heiko Wersing,et al.  Active 3D Object Localization Using a Humanoid Robot , 2011, IEEE Transactions on Robotics.

[11]  P. Fua,et al.  Pose estimation for category specific multiview object localization , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Anthony Widjaja,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[13]  Christopher K. I. Williams,et al.  Learning With Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2001 .

[14]  V. Rao Vemuri,et al.  Use of K-Nearest Neighbor classifier for intrusion detection , 2002, Comput. Secur..

[15]  Thomas J. Watson,et al.  An empirical study of the naive Bayes classifier , 2001 .