Real-Time Detection of Road-Based Objects using SSD MobileNet-v2 FPNlite with a new Benchmark Dataset
Authors:
- 17 March 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
This research paper presents a real-time detection of road-based objects using SSD MobileNet-v2 FPNlite. This model uses the Single Shot Detector (SSD) architecture with MobileNet-v2 as the backbone and Feature Pyramid Network lite (FPNlite) as the feature extractor. This approach combines the advantages of both SSD and MobileNet-v2 for object detection while maintaining low computational complexity. In order to evaluate the performance of the model, a new benchmark dataset is explicitly created for this study, which includes a wide range of images captured from various sources such as cameras mounted on vehicles and street-level cameras. The dataset contains a diverse set of objects and scenes, making it suitable for testing the robustness and generalization ability of the system. The results of the experiments demonstrate the effectiveness of the model. In addition, the newly developed benchmark dataset can be used as a reference for further research in the field.Keywords
This publication has 8 references indexed in Scilit:
- Object detection system based on SSD algorithm2020
- SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple VariabilitiesSensors, 2020
- Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks2019
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Feature Pyramid Networks for Object Detection2017
- SSD: Single Shot MultiBox Detector2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- You Only Look Once: Unified, Real-Time Object Detection2016