Improving Single Shot Multibox Detector with Feature Pyramid Networks Structure and Postprocessing for Better Object Detection Performance

• Main Authors: Yao-Ren Chang, 張耀仁
• Other Authors: 丁建均
• Format: Others
• Language: en_US
• Published: 2017
• Online Access: http://ndltd.ncl.edu.tw/handle/tkguz5

碩士 === 國立臺灣大學 === 電信工程學研究所 === 105 === In recent years, Convolutional Neural Networks(CNNs) have gained a lot of popularity in computer vision. In this work, we will use convolutional neural networks for object detection. To start with, we use Single Shot Multibox Detector(SSD) [7] as our basic framework. We impose Feature Pyramid Networks on SSD to combine local and global information. We also adjust postprocessing with bounding box voting for better localization. For comparison, we test our model on Pascal VOC 2007 test dataset. During evaluation, we calculate Average Precision(AP) for each model and class. Then, we average each AP to get mean Average Precision(mAP) as our final evaluation metric. With original SSD, we can have 77.21% mAP in Pascal VOC 2007 test dataset. In this thesis, our simulation results show that, the proposed method outperforms the original SSD and has better performance for object detection. Our final model can achieve 77.85% mAP.