| Author | Gokaraju, Jnana Sai Abhishek Varma |
| Note | A thesis submitted in partial fulfillment of the requirements for the
degree of Master of Engineering in
Mechatronics |
| Publisher | Asian Institute of Technology |
| Abstract | Detection and classification of moving targets in the different weather conditions are of great significance in the autonomous vehicle driving. Deep Convolutional neural networks (DCNNs) has been used to detect and classify target since 1998. More complicated neural networks have been evolved in order to classification and detection of the objects. However, deep convolutional networks cannot detect and classify the targets in night time conditions due to the low pixel density in the image. By the advancement of the high precision radar, the classification of the targets can be obtained by the using the micro-Doppler signatures (MDS) features. This study was focused on creating the MDS of the pedestrian and bird at different views of radar and Classification of moving pedestrians and birds is implemented using DCNN at night time based on radar-vision dataset. Simulated dataset is used in the experiments and proposed deep convolutional network can learn features of the vision and the micro-Doppler signature of the target Different types of micro-Doppler signatures of targets are obtained by considering the different kinematics of body segments of the pedestrian and bird at different radar position. DCNN is applied to process the Vision and micro-Doppler signatures for detection and classification of pedestrian and bird. The experimental results show that the proposed deep convolutional network can achieve superior accuracy in classification of the pedestrian and bird by using MDS of target at night-time conditions. |
| Year | 2019 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Industrial Systems Engineering (DISE) |
| Academic Program/FoS | Microelectronics (ME) |
| Chairperson(s) | Keun, Song Weon ; |
| Examination Committee(s) | Manukid Parnichkun;Pisut Koomsap; |
| Scholarship Donor(s) | AIT Fellowship; |
| Degree | Thesis (M. Eng.) -- Asian Institute of Technology, 2019 |