SSD-EMB: An Improved SSD Using Enhanced Feature Map Block for Object Detection

• Published in: Sensors (Basel, Switzerland) Vol. 21; no. 8; p. 2842
• Main Authors: Choi, Hong-Tae, Lee, Ho-Jun, Kang, Hoon, Yu, Sungwook, Park, Ho-Hyun
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 17-04-2021; MDPI
• Subjects: Accuracy; Approximation; attention mechanism; Computer vision; Datasets; feature map concatenation; Feature maps; Frames per second; Model accuracy; Neural networks; object detection; Semantics; SSD; feature map concatenation; object detection; SSD; attention mechanism
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s21082842

The development of deep learning has achieved great success in object detection, but small object detection is still a difficult and challenging task in computer vision. To address the problem, we propose an improved single-shot multibox detector (SSD) using enhanced feature map blocks (SSD-EMB). The enhanced feature map block (EMB) consists of attention stream and feature map concatenation stream. The attention stream allows the proposed model to focus on the object regions rather than background owing to channel averaging and the effectiveness of the normalization. The feature map concatenation stream provides additional semantic information to the model without degrading the detection speed. By combining the output of these two streams, the enhanced feature map, which improves the detection of a small object, is generated. Experimental results show that the proposed model has high accuracy in small object detection. The proposed model not only achieves good detection accuracy, but also has a good detection speed. The SSD-EMB achieved a mean average precision (mAP) of 80.4% on the PASCAL VOC 2007 dataset at 30 frames per second on an RTX 2080Ti graphics processing unit, an mAP of 79.9% on the VOC 2012 dataset, and an mAP of 26.6% on the MS COCO dataset.