FPPNet: A Fixed-Perspective-Perception Module for Small Object Detection Based on Background Difference
- 5 April 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (10) , 11057-11069
Abstract
A roadside sensing unit can provide over-the-horizon perception information for autonomous vehicles due to its high perception perspective. However, numerous challenges need to be overcome such as the missing detection of small objects and occluded objects. To this end, this study proposed a Fixed Perspective Perception (FPP) module, which considered background subtraction and a fixed camera for small object detection. The proposed FPP module was divided into two parts: a Grayscale Background Subtraction (GBS) sub-module and a Background-Current Image Fusion (BCF) sub-module. Specifically, the GBS sub-module introduces background spatial information into a current frame and the BCF sub-module combines feature maps of a current frame and background by using channel attention. Moreover, we designed an object detection network called FPPNet which uses the FPP module to facilitate small object detection. Experimental results demonstrate that the FPPNet achieved 39.8% average precision small(AP S ) and 65.7% average precision( AP ) in a Dair-V2X-I dataset. Futhermore, we conducted an extension of the FPP module to mainstream object detection networks such as CenterNet, Faster-Rcnn and RetinaNet. Experimental results show that the proposed module can effectively improve small object detection accuracy of the networks mentioned above.Keywords
Funding Information
- National Natural Science Foundation of China (52102448)
This publication has 53 references indexed in Scilit:
- Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Deep background subtraction with scene-specific convolutional neural networks2016
- On-Road Vehicle Detection and Tracking Using MMW Radar and Monovision FusionIEEE Transactions on Intelligent Transportation Systems, 2016
- A Survey of Vision-Based Traffic Monitoring of Road IntersectionsIEEE Transactions on Intelligent Transportation Systems, 2016
- Fast R-CNN2015
- Probabilistic Inference for Occluded and Multiview On-road Vehicle DetectionIEEE Transactions on Intelligent Transportation Systems, 2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- ViBe: A Universal Background Subtraction Algorithm for Video SequencesIEEE Transactions on Image Processing, 2010