Improved single shot detection using DenseNet for tiny target detection
- 6 November 2022
- journal article
- review article
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 35 (2)
Abstract
Summary: As the development of deep learning and the continuous improvement of computing power, as well as the needs of social production, target detection has become a research hotspot in recent years. However, target detection algorithm has the problem that it is more sensitive to large targets and does not consider the feature‐feature interrelationship, which leads to a high false detection or missed detection rate of small targets. An small target detection method (C‐SSD) based on improved SSD is proposed, that replaces the backbone network VGG‐16 of the SSD network with the improved dense convolution network (C‐DenseNet) network to achieves further feature fusion through fast connections between dense blocks. The Introduction of residuals in the prediction layer and DIoU‐NMS further improves the detection accuracy. Experimental results demonstrate that C‐SSD outperforms other networks at three different image scales and achieves the best performance of 83. A 8% accuracy on the PASCAL VOC2007 test set, proving the effectiveness of the algorithm. C‐SSD achieves a better balance of speed and accuracy, showing excellent performance in rapid detection of small targets.Keywords
Funding Information
- National Natural Science Foundation of China (41906177, 61733011, 51975324, 51505349, 51575407, 52075530)
This publication has 78 references indexed in Scilit:
- SSD: Single Shot MultiBox Detector2016
- Deep Residual Learning for Image Recognition2016
- Fast R-CNN2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Do we need to handle every temporal violation in scientific workflow systems?ACM Transactions on Software Engineering and Methodology, 2014
- A historical probability based noise generation strategy for privacy protection in cloud computingJournal of Computer and System Sciences, 2012
- A workflow framework for intelligent service compositionFuture Generation Computer Systems, 2011
- Trust‐based robust scheduling and runtime adaptation of scientific workflowConcurrency and Computation: Practice and Experience, 2009
- A throughput maximization strategy for scheduling transaction‐intensive workflows on SwinDeW‐GConcurrency and Computation: Practice and Experience, 2008