A Smart, Efficient, and Reliable Parking Surveillance System With Edge Artificial Intelligence on IoT Devices
Open accessThe DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.
Abstract
Cloud computing has been a main-stream computing service for years. Recently, with the rapid development in urbanization, massive video surveillance data are produced at an unprecedented speed. A traditional solution to deal with the big data would require a large amount of computing and storage resources. With the advances in Internet of things (IoT), artificial intelligence, and communication technologies, edge computing offers a new solution to the problem by processing all or part of the data locally at the edge of a surveillance system. In this study, we investigate the feasibility of using edge computing for smart parking surveillance tasks, specifically, parking occupancy detection using the real-time video feed. The system processing pipeline is carefully designed with the consideration of flexibility, online surveillance, data transmission, detection accuracy, and system reliability. It enables artificial intelligence at the edge by implementing an enhanced single shot multibox detector (SSD). A few more algorithms are developed either locally at the edge of the system or on the centralized data server targeting optimal system efficiency and accuracy. Thorough field tests were conducted in the Angle Lake parking garage for three months. The experimental results are promising that the final detection method achieves over 95% accuracy in real-world scenarios with high efficiency and reliability. The proposed smart parking surveillance system is a critical component of smart cities and can be a solid foundation for future applications in intelligent transportation systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Smart Home: Edge AI can be used to power smart home devices such as voice assistants, thermostats, and security cameras [161].”
From Edge AI: A survey (2023) · cites this paper as [161]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Internetworking: It is typically difficult to transport significant volumes of data and models to and from smart edge devices because these systems frequently have restricted or inconsistent network access [161].”
From Edge AI: A survey (2023) · cites this paper as [161]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Without AI, it would be impossible for programmes to handle the vast variety of text, speech, and video data that they are asked to process [161].”
From Edge AI: A survey (2023) · cites this paper as [161]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“Though their CNNs are already quite efficient compared to most standard CNNs such as VGG [46], they still have a relatively slow classification speed even on a single image [16], [22].”
BackgroundThe pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · cited 1×
“In order to improve the detection performance to make it more appropriate for practical applications, we enhance a pre-trained SSD on the Pascal VOC dataset [49] with a new traffic surveillance dataset”
MethodYOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141 · cited 2×
“A normal state-of-the-art object detector like YOLO-V3 [48] with the TensorFlow platform still runs slowly with a speed lower than 0.05 frames-per-second (FPS) on Raspberry Pi 3B, and has a slightly lower detection accuracy as well.”
InfluentialA Multi-Modal Distributed Real-Time IoT System for Urban Traffic Control (Invited Paper)
Khanam, Z., Achari, V. P. S., Boukhennoufa, I., Jindal, A., & Singh, A. K. (2024) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/oasics.ng-res.2024.2 · Cited by 14,040
Simple online and realtime tracking with a deep association metric
Wojke, N., Bewley, A., & Paulus, D. (2017) · 2017 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2017.8296962 · Cited by 5,286
Simple online and realtime tracking
Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7533003 · Cited by 4,433 · cited 9×
“The original SORT does not have a re-identification process, which will lose track of an object if not detected for a few frames.”
MethodInfluentialRobust techniques for background subtraction in urban traffic video
Cheung, S.-C. S., & Kamath, C. (2004) · SPIE Proceedings · doi:10.1117/12.526886 · Cited by 679 · cited 1×
“BG-based detection is a widely used traditional method for traffic video surveillance that is sensitive to video noises and has no classification ability [51], [52].”
MethodA Survey of Smart Parking Solutions
Lin, T., Rivano, H., & Le Mouel, F. (2017) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2685143 · Cited by 545 · cited 3×
“The vision-based solution has received increasing attention for parking occupancy detection lately with the advance in computer vision and data transmission technologies [12], [13], [22]–[25], [14]–[21].”
BackgroundParkNet: drive-by sensing of road-side parking statistics
Mathur, S., Jin, T., Kasturirangan, N., Chandrasekaran, J., Xue, W., Gruteser, M., & Trappe, W. (2010) · Proceedings of the 8th international conference on Mobile systems, applications, and services · doi:10.1145/1814433.1814448 · Cited by 419 · cited 2×
“[12], [14], [34], [26]–[33], moving sensor solution [35], [36], [45], [37]–[44], and vision-based solution [12], [13],”
BackgroundDeep learning for decentralized parking lot occupancy detection
Amato, G., Carrara, F., Falchi, F., Gennaro, C., Meghini, C., & Vairo, C. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.10.055 · Cited by 397 · cited 4×
“The vision-based solution has received increasing attention for parking occupancy detection lately with the advance in computer vision and data transmission technologies [12], [13], [22]–[25], [14]–[21].”
BackgroundInfluential
Cited by
Items 201–247 of 247
Informative Path Planning of Autonomous Vehicle for Parking Occupancy Estimation
Hu, Y., Chen, J., Zhou, K., Gao, H., Li, Y., & Liu, C. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10422020 · Cited by 6
Online parking space sharing system for residential areas based on intelligent algorithms
Pan, Z., Guan, M., Zhong, Z., Xu, Z., & Luo, J. (2024) · International Conference on Smart Transportation and City Engineering (STCE) · doi:10.1117/12.3023971
“In order to solve this problem, many scholars have proposed the staggered sharing of parking spaces in neighborhoods [1-5] .”
BackgroundWSN-Based Secure and Energy-Efficient Smart Parking Management System (SPMS) Using FFA-ANN
Sharma, K. R., Sharma, T., Mittal, N., & Johar, A. K. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-7820-5_24
Internet of Things application and service reliability
Xing, L. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-15610-6.00006-2
Design and Development of Smart Parking System Using RFID Technology
Logeshvaran, -, D. K., Ahamed, R., & Giriprasad (2024) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2024.v06i02.18544
WinterWatch: An Automated Approach to Outdoor Parking Lot Vacancy Detection in Cold Climates
Kafková, J., Pirník, R., Nemec, D., Kuchár, P., Šišmišová, D., Valko, O., & Holečko, P. (2024) · International Carpathian Control Conference · doi:10.1109/iccc62069.2024.10569363
“Recent advancements in AI are driving the development of new automated approaches to outdoor parking lot vacancy detection [1].”
BackgroundInnovation IoT Solutions for Economic Animal Propagation Using Raspberry Pi Boards
Prachayagringkai, S., Thungsuk, N., Savangboon, T., & Chaithanakulwat, A. (2024) · International Journal of Computational Methods and Experimental Measurements · doi:10.18280/ijcmem.120205
“Additionally, with the advancement of the cloud computing system and big data analysis technology, researchers can use the molecular information of each animal to provide superior and critical genetic analysis [17-19].”
MethodTransforming parking systems in higher education institutions with IoT-enabled car plate recognition
Lim, B. G. S., Shanmugam, K., Rana, M. E., & Abdulla, R. (2024) · AIP conference proceedings · doi:10.1063/5.0230657
FindMySpot: AI & AR Based Parking SystemPreprint
Padmapriya, G., Prasad, A., & Panikar, V. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5083259
Evaluating the Effectiveness of Object Detection Algorithms for Autonomous Parking
Sharma, U., Subramonian, K., Dsouza, A., Sughosh, P., Savitha, G., & Girisha, S. (2024) · International Conference on Computer, Electronics & Electrical Engineering & their Applications (IC2E3) · doi:10.1109/ic2e362166.2024.10827792
“Thus, detecting parking slots using deep learning algorithms is widely explored [12]–[14].”
Zhang, S., & Zhao, W. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5210959
Enabling Autonomous and Intelligent Device Functionality Through IoT Integration
Shankar, S. P., Varadam, D., Shankar, A., Ashwath, N. J. R., Mohta, R., & Prasanna, V. K. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-4332-7.ch002
SmartSpot:QR and AI based Smart Parking System
Dixit, R. J., Madhwar, S., Garg, V., & Sharma, Y. (2025) · INTERNATIONAL JOURNAL OF RESEARCH AND ANALYTICAL REVIEWS · doi:10.56975/ijrar.v12i2.311769
Building an accurate and reliable AI system using effective mythology
Thakur, B., & Grover, V. (2025) · AIP conference proceedings · doi:10.1063/5.0258761
Bibliometric Analysis of Scientific Production of Intelligent Video Surveillance
Vicente-Ramos, W., Pumaleque, A. P., & Torres, J. G. (2025) · International journal of electrical and computer engineering systems · doi:10.32985/ijeces.16.6.4 · Cited by 2
“In addition, research is needed to improve the compression and efficient transmission of high-resolution video, ensuring the quality of images in real time without consuming too much bandwidth, especially in areas with limited infrastructure [28, 29].”
Putri, F. L. (2025) · Ultima Computing Jurnal Sistem Komputer · doi:10.31937/sk.v17i1.3802
Safety Support Network System Using Overhead Sensing by a UAV Equipped with 3D LiDAR
Miyaji, H., Shudo, T., & Yamamoto, H. (2025) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2025.3601303 · Cited by 1
Gliga, M., Munteanu, C., Andreica, S., Giurgiuman, A., Pacurar, C., Constantinescu, C., Ielciu, D., Opris, L. N., Botezatu, M. D., & Cartas, R. G. (2025) · Annual Conference of the European Association for Education in Electrical and Information Engineering (EAEEIE) · doi:10.1109/eaeeie65428.2025.11136528
“However, the implementation of such solutions within educational institutions is still in its early stages, with many of these projects still in the prototype phase [8].”
Study and Development of Real Time Smart Garage System
Chiang, J.-L., Kuncoro, C. B. D., & Suhartono, S. (2025) · International Symposium on Computer, Consumer and Control · doi:10.1109/is3c65361.2025.11130973
“An Android-based smart garage app for auto companies that saves time, helps consumers discover the nearest mechanic or service center, and lets users easily communicate [9].”
Design and Implementation of a Scalable Network Topology for Smart Megamall
Jadhav, V., Kajale, T., Chainani, A., Sayyad, J. K., Shukla, M. K., & Mishra, N. K. (2025) · International Conference on Energy, Power and Environment (ICEPE) · doi:10.1109/icepe65965.2025.11139593
“Edge AI technology combines with IoT devices according to Ke et al. (2020) to operate the smart parking surveillance system.”
Event-Based Vision Sensing and Its Application to Pedestrian Detection for Autonomous DrivingPreprint
Wang, H., Liu, S., Wu, J., Liu, M., Liu, H., Cheng, W., Wang, Y., Zhou, S., Nie, Y., & Li, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5457668 · Cited by 1
Self-citationMachine Learning Based Parking Space Classification Using R-CNN and Faster R-CNN FPN Architecture
Jayapandian, N. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-05802-7_8
Real-time parking spot recommendation system using artificial intelligence and big data analytics
Shetra, H. K. K., Mishra, D., Nagappan, B., Purohit, S., Sharma, P., & Minhas, D. (2025) · Multidisciplinary Science Journal · doi:10.31893/multiscience.2025ss0126
Bhande, A. S. (2025) · EPJ Web of Conferences · doi:10.1051/epjconf/202534101024
Duah, N. T., Jiang, S. X., Yadav, O. P., Nguyen, H. T., & Earle-Young, N. (2025) · Transportation Research Interdisciplinary Perspectives · doi:10.1016/j.trip.2025.101740
AI-Powered Smart Indoor Parking System for Dubai and Abu Dhabi Emirate Vehicles
Murugan, T., Alkaabi, S. S., Alderei, M. A., Alnuaimi, S. S. A., Murad, A. M., & Ahamed, N. N. (2025) · Student Research Conference on Applied Computing (SRC) · doi:10.1109/src65875.2025.11263678
“According to Ke et al. [7], cloud computing has been a popular computing solution for several years.”
Singh, T., Bharathi, B., Wunnava, A., Goyal, S. B., Vamalatha, B., & Rajendran, N. K. (2025) · Multidisciplinary Reviews · doi:10.31893/multirev.2025ss0122
“An IoT system requires constant monitoring, much like a city with carefully positioned cameras for surveillance (Ke et al., 2020).”
IoT Based Smart Parking Systems in Unity With ML-agents Toolkit
Dunaiev, B., & Olar, O. (2025) · Security of Infocommunication Systems and Internet of Things · doi:10.31861/sisiot2025.1.01002
“Research [6] describes a good use of the IoT framework.”
Alsanad, H. R., Al_Hassani, R. T., Alrawi, A. A., Graovac, S., & Mashhadany, Y. A. (2025) · Anbar journal for engineering sciences/Mağallaẗ al-anbār li-l-ʻulūm al-handasiyyaẗ · doi:10.37649/ajes-25-008
“Systems in smart cities monitor the locations where waste is disposed of, allowing them to identify any irregularities, such as hazardous leaks and illegal dumping [7][8].”
Lightweight, Privacy-compliant Motion Detection System for Constrained Devices
Shaju, A. T., Shifa, A., & Asghar, M. N. (2025) · Irish Signals and Systems Conference · doi:10.1109/issc67739.2025.11291268
“…recently, artificial intelligence (AI) integration has further enhanced these systems by allowing them to detect and interpret complex behaviors and patterns in real time, distinguishing between benign events (e.g, falling leaves) and actual security threats (e.g., an unauthorised intruder) [2].”
Jain, R., Sharma, A., Khilji, N., Ramesh Babu, P., Pulipati, V., Harikeerthan, M. K., & Gupta, H. (2026) · Acta Informatica Pragensia · doi:10.18267/j.aip.298 · Cited by 1
HAFNet: Hybrid-Stage Collaborative Perception via Agent-Foreground List
Wu, W., Jiang, P., Deng, X., & Wan, S. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3651733
“Ke et al. [22] implemented a hybrid system using edge artificial intelligence to monitor parking status with satisfactory results using only one camera.”
EdgeGuardNet: An Edge-AI Framework for Real-Time Anomaly Detection and Threat Assessment
Kamran, A., Islam, M. S. U., Imran, A., & Ahmad, M. A. (2025) · International Conference on Data Science and Information Technology (DSIT) · doi:10.1109/dsit67006.2025.11389958
“Prior studies based on cloud-edge design typically concentrate on accelerating heavyweight models for the cloud or compressing them with pruning,quantization, etc., which often sacrifice performance [9].”
Sari, Y. A., Suhenal, M. H., & Rifai, A. I. (2026) · Civil and Sustainable Urban Engineering · doi:10.53623/csue.v6i1.1023
“The smart parking cluster aligned with smart city and IoT implementations, leveraging edge computing, sensor networks, and real-time decision-making to enhance infrastructure flexibility and operational efficiency [8, 10, 15].”
Edge Assisted Multi-Camera Vehicle Tracking Framework for Real-Time and Scalable DeploymentPreprint
Lin, Y., Lockyer, S., Zhang, S., Stanek, F., Zarbock, M., Evans, A., Li, W., Wang, Y., & Zhang, N. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6626356
Self-citationShort Paper: Counting Parked Bicycles on the Edge - A TinyML Smart City Application
Stenkamp, J., Hunke, M., Karatas, C., Kirchhoff, S., Knaden, C., Naebers, P., Zhao, L., Karic, B., Gieseke, F. C., & Herrmann, N. (2026) · doi:10.1145/3774906.3802788
“Other approaches to monitoring car parking spaces usually utilize more capable and thus expensive hardware like Jetson Nanos [17] or split calculations [11].”
Ke, Z., Al-haimi, B., Jusoh, N. M., Khalid, H., & Zakaria, N. H. (2026) · International Journal of Academic Research in Business and Social Sciences · doi:10.6007/ijarbss/v16-i6/28448
IHBTD: Improved hybrid method for detection of brain tumour
Penugonda, H., Katuri, V. V., Thota, V. S. K., Boyapati, P., Mandalapu, N. S., Gulamajji, P. K., & Islam, M. S. U. (2026) · AIP conference proceedings · doi:10.1063/5.0286814
Smart Parking Systems: A Review of Optimization Techniques and Technological Advances
Sarvenoee, A. K., Kohzadipour, M., Valizadeh, M., Kia, M. S., Karimian, M., & Sharifirad, M. (2026) · Energy Science & Engineering · doi:10.1002/ese3.70636
Bridging Research Gaps in Smart Parking Systems: A Comparative Study of CNN and VANET Approaches
Sanan, M., & Kovuri, K. (2026) · International Journal of Computer Information Systems and Industrial Management Applications · doi:10.70917/ijcisim-2026-2958
“(Ke et al., 2021) implemented an enhanced Single Shot MultiBox Detector at RSU edge nodes, achieving occupancy detection with a 95% accuracy and real-time performance within a live urban environment.”
Bethu, S., & Babu, E. S. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112738
Federated Learning in Smart Healthcare, Homes, and Cities (FL-SHHC): A Systematic Literature Review
Jackson, T., Khan, J. A., & Mylonas, A. (2026) · Eng—Advances in Engineering · doi:10.3390/eng7090485
Salve, S. S., Ingale, P., Sarode, K., Munjal, P., Borey, M. S. R., & Kshirsagar, A. N. (2026) · International Conference on Computing Communication Control and automation · doi:10.1109/iccubea69821.2026.11702344
“…as application-based systems that utilise static or predefined thresholds, independent parameter-based sensors, with a centralised architecture performing the data processing, which influences their functioning and ultimately limits their adaptability to rapidly changing urban fields [23], [24].”
Sinaga, G. F. T., Prakasa, E., Rezaldi, M. Y., & Abdurrazzaq, A. (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715469
“An op-tionarily application of this technology is in the smartparking management, in which accurate 3D models of real scenes canbe used for mapping, space arrangement, and everyday problemsolving [4], [5], [6].”
Mobile Surveillance at the Edge: automatic license plate reading evaluationPreprint
Biase, L. C. D., MORAES, M. A. I. D., Bonadio, V. T., Barreto, C., Fedrecheski, G., & Zuffo, M. K. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7669136
Metadata
- Authors
- Ke, R., Zhuang, Y., Pu, Z., & Wang, Y.
- Affiliations
- University of Washington (US)
- Venue
- IEEE Transactions on Intelligent Transportation Systems
- Published
- 2021-08
- Volume
- 22
- Issue
- 8
- Pages
- 4962-4974
- ISSN
- 1524-9050 (ISSN-L)
- 1558-0016
- OpenAlex
- W2997298686
- Cited by
- 240
- References
- 56
- Citations by year
- 2026: 16 · 2025: 52 · 2024: 52 · 2023: 59 · 2022: 32 · 2021: 19
- FWCI
- 15.76
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Intelligent Transportation Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Central Puget Sound Regional Transit Authority
- Pacific Northwest Transportation Consortium
- Topics
- Social Sciences › Transportation › Smart Parking Systems Research
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- edge computing, parking occupancy detection, Single Shot MultiBox Detector, video surveillance, Internet of Things, smart parking, smart cities, real-time video processing, object detection, data transmission
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.