Abstract
Human-vehicle classification plays an important role in advanced driver assistance systems (ADAS). The use of millimeter wave (mmWave) radar sensor in human-vehicle classification algorithms is of great significance since the sensor maintains to be robust in severe weather (e.g. fog, snow, etc.). To improve classification accuracy under complex scenes of autonomous driving, a new mmWave radar point cloud classification algorithm is proposed in this paper, which realizes human-vehicle classification employing a newly proposed point cloud feature vector with eleven dimensions and based on kernel support vector machine (SVM) classifier. To verify the validity and robustness of the proposed feature vector, a 77 GHz radar is used to collect two datasets for static and moving objects, respectively, with each dataset taken for pedestrians and vehicles at different distances and angles. Experimental results show that the proposed algorithm achieves higher classification accuracy than a conventional one based on signal features. For the comparison based on the same number of dimensions, the number of dimensions of the proposed feature vector is decreased by removing the features with low significance. Experimental results verify that the proposed algorithm maintains advantage over the conventional one.
Highlights
Driven by the proliferation of Internet of Vehicles (IoV) and edge computing technology [1], many autonomous driving technologies [2], [3] have been developed rapidly
Considering that dimension number of feature vectors could influence computational efficiency and generalization ability of the classification algorithm, performance comparison based on the same dimension number of feature vectors are provided, by selecting and applying only part of features in the proposed classification algorithm
In this paper, a kernel support vector machine (SVM) classification algorithm for millimeter wave (mmWave) radar sensors is proposed, which realizes classification of pedestrians and vehicles by employing a newly proposed feature vector extracted from spatial distribution, velocity and echo intensity information of object point clouds
Summary
Driven by the proliferation of Internet of Vehicles (IoV) and edge computing technology [1], many autonomous driving technologies [2], [3] have been developed rapidly. The above pedestrian recognition algorithms based on micro-Doppler features suffer a high computational cost and result in increased difficulties of object classification in real time. For this reason, they are not suitable for automotive radar applications [23]. A new human-vehicle classification algorithm based on a newly defined point cloud feature vector is proposed to improve performance of identifying objects with different reflection angles. A new feature vector with eleven dimensions that describes the shape, velocity and echo intensity of point clouds is proposed, based on which kernel SVM classifier is used to classify pedestrians and vehicles. Where I represents an array of all object points’ reflected intensity values
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
