Optimized Fast R-CNN for Automated Parking Space Detection: Evaluating Efficiency with MiniFasterRCNN
DOI:
https://doi.org/10.4314/p272b841Keywords:
Parking Space Detection, fast R-CNN, transfer learning, computer vision, object detectionAbstract
Automated parking space detection is a crucial application of computer vision in intelligent transportation systems. In this study, we developed a Fast R-CNN-based model for classifying and localizing parking spaces into empty and occupied categories. The model architecture consists of a pre-trained CNN backbone (ResNet50) for feature extraction, a Region Proposal Network (RPN) for generating potential bounding boxes, and Region-of-Interest (RoI) pooling for feature refinement. The classification head utilizes a softmax activation function with cross-entropy loss, while the bounding box coordinates are refined using smooth L1 loss. To facilitate training, we employed Roboflow for dataset annotation, creating ground truth bounding boxes for parking spaces. The model was fine-tuned using transfer learning, leveraging knowledge from the COCO dataset. Training involved hyperparameter optimization, including learning rate scheduling and weight decay, to enhance convergence. Model selection was based on validation loss and accuracy to ensure generalization to unseen data. The model was deployed using Gradio, allowing real-time parking space detection from uploaded images. Despite achieving a final loss of 0.8280, the model exhibited some background noise distortions, impacting detection accuracy. To address this limitation, we explored a lightweight alternative, MiniFasterRCNN, optimized for efficiency with a simpler architecture. The MiniFasterRCNN was trained on a three-class dataset (empty, occupied, background), achieving a validation accuracy of 77.78%. However, attempts to achieve 100% accuracy proved inefficient, highlighting the need for further improvements, such as segmentation techniques (Masked R-CNN). This research demonstrates the feasibility of Fast R-CNN-based models for parking space detection while emphasizing the importance of architectural optimizations and hyperparameter tuning for improved accuracy and robustness in real-world applications
Downloads
Published
Issue
Section
Most read articles by the same author(s)
- Olumide Oni, Memory-Enhanced Conversational AI: A Generative Approach for Context-Aware and Personalized Chatbots , Communication In Physical Sciences: Vol. 12 No. 2 (2025): VOLUME 12 ISSUE 2
Similar Articles
- Fatima Binta Adamu, Muhammad Bashir Abdullahi, Sulaimon Adebayo Bashir, Abiodun Musa Aibinu, Conceptual Design Of A Hybrid Deep Learning Model For Classification Of Cervical Cancer Acetic Acid Images , Communication In Physical Sciences: Vol. 12 No. 2 (2025): VOLUME 12 ISSUE 2
- Humphrey Sam Samuel, Emmanuel Edet Etim, John Paul Shinggu, Bulus. Bako , Machine learning of Rotational spectra analysis in interstellar medium , Communication In Physical Sciences: Vol. 10 No. 1 (2023): VOLUME 10 ISSUE 1
- David Adetunji Ademilua, Edoise Areghan, Cloud Computing and Machine Learning for Scalable Predictive Analytics and Automation: A Framework for Solving Real-world Problems , Communication In Physical Sciences: Vol. 12 No. 2 (2025): VOLUME 12 ISSUE 2
- Emmanuel Gbenga Dada, David Opeoluwa Oyewola, Stephen Bassi Joseph, Deep Convolutional Neural Network Model for Detection of Sickle Cell Anemia in Peripheral Blood Images , Communication In Physical Sciences: Vol. 8 No. 1 (2022): VOLUME 8 ISSUE 1
- Assumpta Obianuju Ezugwu, Onyinye Nweke, Stephen Okechukwu Aneke, A survey on Students' Academic Performance in Smart Campuses , Communication In Physical Sciences: Vol. 8 No. 2 (2022): VOLUME 8 ISSUE 2
- Enefiok Archibong Etuk, Omankwu, Obinnaya Chinecherem Beloved, Spiking Neural Networks (SNNs): A Path towards Brain-Inspired AI , Communication In Physical Sciences: Vol. 12 No. 2 (2025): VOLUME 12 ISSUE 2
- F. S. Bakpo, A Petri Net Computational Model for Web-based Students Attendance Monitoring , Communication In Physical Sciences: Vol. 1 No. 1 (2010): VOLUME 1 ISSUE 1
- Felicia. O. Isiogugu, P. Pillay, C. C. Okeke, F. U. Ogbuisi, P. U.Nwokoro, Convergence Theorems for Modified Mann Reich-Sabach Iteration Scheme for Approximating the Common Solution of Equilibrium Problems and Fixed Point Problems in Hilbert Spaces with Numerical Examples , Communication In Physical Sciences: Vol. 5 No. 4 (2020): VOLUME 5 ISSUE 4
- Chukwuemeka. K. Onwuamaeze, Christopher. I. Ejiofor, An Improved Defragmentation Model for Distributed Customer’s Bank Transactions , Communication In Physical Sciences: Vol. 5 No. 3 (2020): VOLUME 5 ISSUE 3
- David Adetunji Ademilua, Cloud Security in the Era of Big Data and IoT: A Review of Emerging Risks and Protective Technologies , Communication In Physical Sciences: Vol. 7 No. 4 (2021): VOLUME 7 ISSUE 4
You may also start an advanced similarity search for this article.